Integrating Transformers and Many-Objective Optimization for Cancer Drug Design

Integrating Transformers and Many-Objective Optimization for Cancer Drug Design | 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 Integrating Transformers and Many-Objective Optimization for Cancer Drug Design Nicholas Aksamit, Jinqiang Hou, Yifeng Li, Beatrice Ombuki-Berman This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4229436/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract Background : Drug design is a challenging and important task that requires the generation of novel and effective molecules that can bind to specific protein targets. Artificial intelligence (AI) algorithms have recently showed promising potential to expedite the drug design process. However, existing methods adopt multi-objective approaches which limits the number of objectives. Results : In this paper, we expand this thread of research from the many-objective perspective, by proposing a novel framework that integrates a latent Transformer-based model for molecular generation, with a drug design system that incorporates absorption, distribution, metabolism, excretion, and toxicity (ADMET) prediction, molecular docking, and many-objective metaheuristics. We compared the performance of two latent Transformer models (ReLSO and FragNet) on a molecular generation task and show that ReLSO outperforms FragNet in terms of reconstruction and latent space organization. We then explored six different many-objective metaheuristics based on evolutionary algorithms and particle swarm optimization on a drug design task involving potential drug candidates to human lysophosphatidic acid receptor 1 (LPA1), a cancer-related protein target. Conclusion : We show that multi-objective evolutionary algorithm based on dominance and decomposition (MOEA/DD) performs the best in terms of finding molecules that satisfy many objectives, such as high binding affinity and low toxicity, and high drug-likeness. Our framework demonstrates the potential of combining Transformers and many-objective computational intelligence for cancer drug design. cancer drug design molecular generation Transformers many-objective optimization evolutionary algorithm particle swarm optimization ADMET Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 25 Apr, 2024 Reviews received at journal 24 Apr, 2024 Reviews received at journal 20 Apr, 2024 Reviewers agreed at journal 17 Apr, 2024 Reviewers agreed at journal 15 Apr, 2024 Reviewers invited by journal 15 Apr, 2024 Editor assigned by journal 09 Apr, 2024 Submission checks completed at journal 09 Apr, 2024 First submitted to journal 06 Apr, 2024 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-4229436","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":289142684,"identity":"b351e8fe-54ba-4358-b82f-6fca8dd8b7de","order_by":0,"name":"Nicholas Aksamit","email":"","orcid":"","institution":"Brock University","correspondingAuthor":false,"prefix":"","firstName":"Nicholas","middleName":"","lastName":"Aksamit","suffix":""},{"id":289142685,"identity":"4c7694e7-e556-4257-ac84-7536ad6ac5f0","order_by":1,"name":"Jinqiang Hou","email":"","orcid":"","institution":"Lakehead University","correspondingAuthor":false,"prefix":"","firstName":"Jinqiang","middleName":"","lastName":"Hou","suffix":""},{"id":289142686,"identity":"b19de6f8-d96d-4f18-a54a-1b618e9685b3","order_by":2,"name":"Yifeng Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAq0lEQVRIiWNgGAWjYDACdsbGBx8bgAweorUwMzYbziRRCwObNC9JWgwOMzdI2+64J8ffc8aA4UcNUVoYG4xzzxQbS5ztMWDsOUakluTctoTEDfw8BkBHEqnlsCVcyz/itDQ2M4K08PYYMDO2EaFF8jBjM2PvmQRjiTPHCg729hGhhe94+/MfP3ckAEMseeODH9+I0KJwAIlzAIciVCDfQJSyUTAKRsEoGNEAAOA+NXacepyUAAAAAElFTkSuQmCC","orcid":"","institution":"Brock University","correspondingAuthor":true,"prefix":"","firstName":"Yifeng","middleName":"","lastName":"Li","suffix":""},{"id":289142687,"identity":"113e3fff-ac61-4b52-989c-1d686bfa3135","order_by":3,"name":"Beatrice Ombuki-Berman","email":"","orcid":"","institution":"Brock University","correspondingAuthor":false,"prefix":"","firstName":"Beatrice","middleName":"","lastName":"Ombuki-Berman","suffix":""}],"badges":[],"createdAt":"2024-04-07 03:44:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4229436/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4229436/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":54536256,"identity":"de467d90-8d6c-430f-94b0-dd0ef007dfed","added_by":"auto","created_at":"2024-04-12 02:58:28","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3117519,"visible":true,"origin":"","legend":"","description":"","filename":"MODD.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4229436/v1_covered_317d0c38-7315-403c-b7eb-9125094f81f6.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Integrating Transformers and Many-Objective Optimization for Cancer Drug Design","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-bioinformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"binf","sideBox":"Learn more about [BMC Bioinformatics](http://bmcbioinformatics.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/binf","title":"BMC Bioinformatics","twitterHandle":"@BMC_Bioinformatics","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"cancer drug design, molecular generation, Transformers, many-objective optimization, evolutionary algorithm, particle swarm optimization, ADMET","lastPublishedDoi":"10.21203/rs.3.rs-4229436/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4229436/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground\u003c/strong\u003e: Drug design is a challenging and important task that requires the generation of novel and effective molecules that can bind to specific protein targets. Artificial intelligence (AI) algorithms have recently showed promising potential to expedite the drug design process. However, existing methods adopt multi-objective approaches which limits the number of objectives.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults\u003c/strong\u003e: In this paper, we expand this thread of research from the many-objective perspective, by proposing a novel framework that integrates a latent Transformer-based model for molecular generation, with a drug design system that incorporates absorption, distribution, metabolism, excretion, and toxicity (ADMET) prediction, molecular docking, and many-objective metaheuristics. We compared the performance of two latent Transformer models (ReLSO and FragNet) on a molecular generation task and show that ReLSO outperforms FragNet in terms of reconstruction and latent space organization. We then explored six different many-objective metaheuristics based on evolutionary algorithms and particle swarm optimization on a drug design task involving potential drug candidates to human lysophosphatidic acid receptor 1 (LPA1), a cancer-related protein target.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion\u003c/strong\u003e: We show that multi-objective evolutionary algorithm based on dominance and decomposition (MOEA/DD) performs the best in terms of finding molecules that satisfy many objectives, such as high binding affinity and low toxicity, and high drug-likeness. Our framework demonstrates the potential of combining Transformers and many-objective computational intelligence for cancer drug design.\u003c/p\u003e","manuscriptTitle":"Integrating Transformers and Many-Objective Optimization for Cancer Drug Design","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-12 02:50:14","doi":"10.21203/rs.3.rs-4229436/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-04-25T10:51:55+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-04-24T16:17:34+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-04-20T17:24:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"02540739-e296-40ce-8608-e1ead21374d1","date":"2024-04-17T12:56:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"ef299250-2623-468e-83b9-6474bcd14ff5","date":"2024-04-15T13:22:53+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-04-15T12:51:16+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-04-09T07:09:42+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-04-09T04:28:25+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Bioinformatics","date":"2024-04-07T03:34:13+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-bioinformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"binf","sideBox":"Learn more about [BMC Bioinformatics](http://bmcbioinformatics.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/binf","title":"BMC Bioinformatics","twitterHandle":"@BMC_Bioinformatics","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"633989c4-3392-43a5-8574-b40e5e848040","owner":[],"postedDate":"April 12th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2024-05-30T09:29:09+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-12 02:50:14","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4229436","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4229436","identity":"rs-4229436","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}