Personalized Breast Cancer Therapy Optimization Using Deep Q-Learning and TCGA Data

Personalized Breast Cancer Therapy Optimization Using Deep Q-Learning and TCGA Data | 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 Personalized Breast Cancer Therapy Optimization Using Deep Q-Learning and TCGA Data Branislav Čeperković This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6665743/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 Breast cancer therapy is challenged by tumor heterogeneity and limited personalization. This study presents a Deep Q-Learning (DQN) model trained on The Cancer Genome Atlas (TCGA) data to optimize personalized treatment plans for breast cancer patients. The model achieved an average tumor reduction of 129.71 mm, a minimum of 95.01 mm, and a maximum of 150.0 mm (indicating complete tumor elimination in some simulated cases), with side effects below 0.0802. Genetic differentiation for key markers (TP53, KRAS, BRAF) ranged from 9.53 to 12.96, enabling targeted therapy adjustments. These results demonstrate a promising framework for precision oncology, with potential to guide future clinical trials while maintaining minimal side effects. Bioinformatics Medical Informatics Medical Genetics breast cancer TCGA precision medicine AI in oncology Deep Q-Learning 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-6665743","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":456645255,"identity":"19dd070d-7086-42ec-ab69-58d2a3abc9ab","order_by":0,"name":"Branislav Čeperković","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABPElEQVRIie3Qv2qDQBzA8ZMDs1xw/QUhfYUTQRto6YN0UQJ2iWtxSINQsEtoVgMlfYV0cepwcqCL0AfoYpbM6RIcHHoWAvmj6Vqo3+G8g98H7kSore0PRqvFQpe7s4UQRohtPLHH2D9D4IBIqzCriNRM0AERs3o3qL71xFT5Os9LuKApT/Kvd6dPU7yG7uLhVnkSpPCiYzJ4dkxqB6AtM+dOC9cjnXLZgF6UuiGXfGmafZ5cLEMG2D5I85AYKmGePX8kMmhR4vqCYCmoIZ0tWCXczENlq5Y7Yr8k7msjIQZYYmYGRFYRG9kzTDCN/bG7bCCDKbkH8ZbhjDimNmWOrmBZW/kJc98EiWveYpJO1CvKq+ugI35dwYZ9WeE5L8cTd/HB47zwTsh+8v6B/6zs3Pwxmfwy3NbW1vaP+gYoxHRQKCEx1QAAAABJRU5ErkJggg==","orcid":"","institution":"University of medical sciences","correspondingAuthor":true,"prefix":"","firstName":"Branislav","middleName":"","lastName":"Čeperković","suffix":""}],"badges":[],"createdAt":"2025-05-14 15:41:54","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":true,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":true},"doi":"10.21203/rs.3.rs-6665743/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6665743/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":82852140,"identity":"a23f919b-925d-4187-8637-99b1c9004aa8","added_by":"auto","created_at":"2025-05-16 03:37:15","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":172828,"visible":true,"origin":"","legend":"","description":"","filename":"Researchgate.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6665743/v1_covered_2fb1e5be-9c3d-4441-8464-b6b0204fb84e.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003ePersonalized Breast Cancer Therapy Optimization Using Deep Q-Learning and TCGA Data\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Faculty of Medical Sciences, University of Kragujevac, Kragujevac, Serbia","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":"breast cancer, TCGA, precision medicine, AI in oncology, Deep Q-Learning,","lastPublishedDoi":"10.21203/rs.3.rs-6665743/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6665743/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBreast cancer therapy is challenged by tumor heterogeneity and limited personalization. This study presents a Deep Q-Learning (DQN) model trained on The Cancer Genome Atlas (TCGA) data to optimize personalized treatment plans for breast cancer patients. The model achieved an average tumor reduction of 129.71 mm, a minimum of 95.01 mm, and a maximum of 150.0 mm (indicating complete tumor elimination in some simulated cases), with side effects below 0.0802. Genetic differentiation for key markers (TP53, KRAS, BRAF) ranged from 9.53 to 12.96, enabling targeted therapy adjustments. These results demonstrate a promising framework for precision oncology, with potential to guide future clinical trials while maintaining minimal side effects.\u003c/p\u003e","manuscriptTitle":"Personalized Breast Cancer Therapy Optimization Using Deep Q-Learning and TCGA Data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-16 03:29:08","doi":"10.21203/rs.3.rs-6665743/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":"7a8756c3-b1f4-4c4f-bc2d-19ca9e5c6bc1","owner":[],"postedDate":"May 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":48536099,"name":"Bioinformatics"},{"id":48536100,"name":"Medical Informatics"},{"id":48536101,"name":"Medical Genetics"}],"tags":[],"updatedAt":"2025-05-16T03:29:08+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-16 03:29:08","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6665743","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6665743","identity":"rs-6665743","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}