Single and Multi-Objective Optimization of De Novo Drug Design for Sophisticated Biomarkers, RET Alterations

Single and Multi-Objective Optimization of De Novo Drug Design for Sophisticated Biomarkers, RET Alterations | 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 Single and Multi-Objective Optimization of De Novo Drug Design for Sophisticated Biomarkers, RET Alterations Surendra Kumar, Vinay Pogaku, Mi-Hyun Kim This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8916489/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 9 You are reading this latest preprint version Abstract Biomarker based oncology therapeutics leverage molecular signatures to identify patient populations most likely to benefit from a specific treatment, thereby increasing clinical success rates. Despite the significant merits of these biomarkers, the high rate of mutations across various therapeutic markers continues to impede innovative drug design. RET is a complex therapeutic biomarker, characterized by high alteration rates that complicate the development of targeted therapies in oncology. Herein, this study provides a systematic evaluation of single-objective (SO) and multi-objective (MO) reinforcement learning strategies aimed at the de novo design of inhibitors targeting complicated RET malignancies. Both approaches employed the identical downstream selection logic comprising hinge-core analysis, scaffold novelty assessment, drug-likeness filtering, and drug-target affinity (DTA) predictions using SMPLIP-Score and ChargeNET models. The SO approach optimized solely for RET-MUT potency, generating compounds with favorable synthesizability profiles (Tanimoto similarity 0.4–0.6). The MO approach incorporated 23 off-target kinase classification models and 108 NSCLC focused phenotype models; 85% of MO candidates simultaneously achieved high RET potency (pIC50 ≥ 7.0), favorable selectivity (off-target probability ≤ 0.3), and predicted phenotypic activity (NSCLC probability ≥ 0.3). Consequently, while SO optimization achieved rapid output with acceptable multi-parameter performance (off-target selectivity: 0.686 ± 0.126; phenotype: 0.945 ± 0.093), MO optimization provided enhanced selectivity consistency (0.555 ± 0.084, 3.2-fold reduced variability) without sacrificing target potency (mean pIC50 7.03 vs 7.6 for SO). The downstream selection and experimental validation further yielded novel amino quinoxaline derivatives to show the high potency against multiple RET alterations (IC 50 : 0.78 nM for RET V804M , 142 nM for RET G810R , 0.53 nM for RET I788N ), representing an unseen scaffold for RET-driven cancers. Scientific Contribution This work provides three key contributions: (1) the first systematic comparison of single-objective versus multi-objective reinforcement learning for kinase inhibitor discovery using identical evaluation workflows; (2) integration of 23 off-target kinase and 108 phenotype classification models into generative molecular design, enabling prospective selectivity optimization; and (3) experimental validation of a novel amino quinoxaline scaffold with sub-nanomolar activity against clinically relevant RET resistance mutations (V804M, G810R, I788N). Reinforcement Learning De Novo Design RET Kinase Multi Objective Optimization Full Text Additional Declarations No competing interests reported. Supplementary Files SupplementaryfileJCHEMV3.docx Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 24 Mar, 2026 Reviews received at journal 22 Mar, 2026 Reviews received at journal 02 Mar, 2026 Reviewers agreed at journal 02 Mar, 2026 Reviewers agreed at journal 02 Mar, 2026 Reviewers invited by journal 28 Feb, 2026 Editor assigned by journal 20 Feb, 2026 Submission checks completed at journal 20 Feb, 2026 First submitted to journal 19 Feb, 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-8916489","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":596417988,"identity":"9daff223-0ca2-4b56-a7a9-5c1b40250d7b","order_by":0,"name":"Surendra Kumar","email":"","orcid":"","institution":"Gachon University","correspondingAuthor":false,"prefix":"","firstName":"Surendra","middleName":"","lastName":"Kumar","suffix":""},{"id":596417989,"identity":"e5bd33fc-1d0c-47c8-bf18-aa7d21ed005c","order_by":1,"name":"Vinay Pogaku","email":"","orcid":"","institution":"Gachon University","correspondingAuthor":false,"prefix":"","firstName":"Vinay","middleName":"","lastName":"Pogaku","suffix":""},{"id":596417994,"identity":"ea36e624-c402-40ca-be8f-e72c280242d6","order_by":2,"name":"Mi-Hyun Kim","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA70lEQVRIiWNgGAWjYBACCQYehsM/DP7JAdlsUDE2fBrAWhgfMxQcMCZJC7Mxw4cDiQ1Ea5GcdvaYdIHBnfT57oefPfi4g0Gev4Et7QM+LdLSeWnSMwye5W48k2ZuOPMMg+GMA2yHZ+DTIiedYybBY8Ccu7Ehh02at42BcQMDezNeh8G0pBv2vwFrsSeoRVo6x9iYx+BwgrwExJbEDQxsh/FqkZydY/hwhkGa4QaJZ2aSM9skkmccZkvGq0Xido7BgQ9/bOTl+5OfSXxss7Htb28zxqsFDgwOQIxgYGAmTgMDg3wDsSpHwSgYBaNgxAEAKzdDEXGa0L4AAAAASUVORK5CYII=","orcid":"","institution":"Gachon University","correspondingAuthor":true,"prefix":"","firstName":"Mi-Hyun","middleName":"","lastName":"Kim","suffix":""}],"badges":[],"createdAt":"2026-02-19 10:24:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8916489/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8916489/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":103577559,"identity":"ec1ae78b-be8d-4d3e-85a1-9286e55f0253","added_by":"auto","created_at":"2026-02-27 09:28:28","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3068797,"visible":true,"origin":"","legend":"","description":"","filename":"RETMSJCHEMV5Submitted.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8916489/v1_covered_2290afe8-7d70-4571-b184-33c5b98d7b09.pdf"},{"id":103577278,"identity":"5e93f039-59b8-4d45-9e24-4002f678ccfc","added_by":"auto","created_at":"2026-02-27 09:27:15","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":61656824,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryfileJCHEMV3.docx","url":"https://assets-eu.researchsquare.com/files/rs-8916489/v1/8a03977b33f9e7829866f8dc.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Single and Multi-Objective Optimization of De Novo Drug Design for Sophisticated Biomarkers, RET Alterations","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"journal-of-cheminformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"chin","sideBox":"Learn more about [Journal of Cheminformatics](https://jcheminf.biomedcentral.com/)","snPcode":"13321","submissionUrl":"https://submission.nature.com/new-submission/13321/3","title":"Journal of Cheminformatics","twitterHandle":"@jcheminf","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Reinforcement Learning, De Novo Design, RET, Kinase, Multi Objective Optimization","lastPublishedDoi":"10.21203/rs.3.rs-8916489/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8916489/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBiomarker based oncology therapeutics leverage molecular signatures to identify patient populations most likely to benefit from a specific treatment, thereby increasing clinical success rates. Despite the significant merits of these biomarkers, the high rate of mutations across various therapeutic markers continues to impede innovative drug design. RET is a complex therapeutic biomarker, characterized by high alteration rates that complicate the development of targeted therapies in oncology. Herein, this study provides a systematic evaluation of single-objective (SO) and multi-objective (MO) reinforcement learning strategies aimed at the de novo design of inhibitors targeting complicated RET malignancies. Both approaches employed the identical downstream selection logic comprising hinge-core analysis, scaffold novelty assessment, drug-likeness filtering, and drug-target affinity (DTA) predictions using SMPLIP-Score and ChargeNET models. The SO approach optimized solely for RET-MUT potency, generating compounds with favorable synthesizability profiles (Tanimoto similarity 0.4\u0026ndash;0.6). The MO approach incorporated 23 off-target kinase classification models and 108 NSCLC focused phenotype models; 85% of MO candidates simultaneously achieved high RET potency (pIC50\u0026thinsp;\u0026ge;\u0026thinsp;7.0), favorable selectivity (off-target probability\u0026thinsp;\u0026le;\u0026thinsp;0.3), and predicted phenotypic activity (NSCLC probability\u0026thinsp;\u0026ge;\u0026thinsp;0.3). Consequently, while SO optimization achieved rapid output with acceptable multi-parameter performance (off-target selectivity: 0.686\u0026thinsp;\u0026plusmn;\u0026thinsp;0.126; phenotype: 0.945\u0026thinsp;\u0026plusmn;\u0026thinsp;0.093), MO optimization provided enhanced selectivity consistency (0.555\u0026thinsp;\u0026plusmn;\u0026thinsp;0.084, 3.2-fold reduced variability) without sacrificing target potency (mean pIC50 7.03 vs 7.6 for SO). The downstream selection and experimental validation further yielded novel amino quinoxaline derivatives to show the high potency against multiple RET alterations (IC\u003csub\u003e50\u003c/sub\u003e: 0.78 nM for RET\u003csup\u003eV804M\u003c/sup\u003e, 142 nM for RET\u003csup\u003eG810R\u003c/sup\u003e, 0.53 nM for RET\u003csup\u003eI788N\u003c/sup\u003e), representing an unseen scaffold for RET-driven cancers.\u003c/p\u003e \u003cp\u003eScientific Contribution\u003c/p\u003e \u003cp\u003eThis work provides three key contributions: (1) the first systematic comparison of single-objective versus multi-objective reinforcement learning for kinase inhibitor discovery using identical evaluation workflows; (2) integration of 23 off-target kinase and 108 phenotype classification models into generative molecular design, enabling prospective selectivity optimization; and (3) experimental validation of a novel amino quinoxaline scaffold with sub-nanomolar activity against clinically relevant RET resistance mutations (V804M, G810R, I788N).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e","manuscriptTitle":"Single and Multi-Objective Optimization of De Novo Drug Design for Sophisticated Biomarkers, RET Alterations","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-27 09:24:30","doi":"10.21203/rs.3.rs-8916489/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-24T09:41:06+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-22T16:33:16+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-02T14:23:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"153946443808122576076514465515895100069","date":"2026-03-02T09:57:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"208401189745272350377135492491809175445","date":"2026-03-02T06:45:16+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-28T14:58:52+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-20T07:57:04+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-20T07:55:48+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Cheminformatics","date":"2026-02-19T10:10:10+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-cheminformatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"chin","sideBox":"Learn more about [Journal of Cheminformatics](https://jcheminf.biomedcentral.com/)","snPcode":"13321","submissionUrl":"https://submission.nature.com/new-submission/13321/3","title":"Journal of Cheminformatics","twitterHandle":"@jcheminf","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"14fadae0-aded-403d-b218-5aa80f611513","owner":[],"postedDate":"February 27th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-05-13T15:19:32+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-27 09:24:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8916489","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8916489","identity":"rs-8916489","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}