OCR: OmniNet-Fusion: A Hybrid Attention-Based CNN-RNN Model for Multi-Omics Integration in Precision Cancer Drug Response Prediction

OCR: OmniNet-Fusion: A Hybrid Attention-Based CNN-RNN Model for Multi-Omics Integration in Precision Cancer Drug Response Prediction | 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 OCR: OmniNet-Fusion: A Hybrid Attention-Based CNN-RNN Model for Multi-Omics Integration in Precision Cancer Drug Response Prediction Syed Mohammed Azmal, Sajja Tulasi Krishna This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6274280/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 increasing complexity of cancer treatment necessitates advanced computational models for accurate drug response prediction. OmniNet-Fusion (OCR) is a hybrid deep learning model designed to integrate multi-omics data—genomics, transcriptomics, proteomics, and metabolomics—enhancing precision medicine. The model leverages a Convolutional Neural Network (CNN) to analyze spatial omics data and a Recurrent Neural Network (RNN) to process sequential data, with an attention mechanism highlighting crucial features across omics layers. To optimize predictive accuracy, feature selection techniques such as Lasso regression and mutual information filtering are utilized, while Principal Component Analysis (PCA) reduces dimensionality, ensuring computational efficiency. The model undergoes evaluation using key performance metrics, including accuracy, precision, recall, F1-score, and AUC-ROC, demonstrating superior predictive performance over existing methods. By integrating multi-omics fusion and deep learning, OCR enhances biological interpretability and facilitates personalized cancer treatment. This approach not only improves drug response prediction but also provides deeper insights into cancer mechanisms, supporting precision oncology and advancing AI-driven cancer therapy. Biological sciences/Cancer Biological sciences/Drug discovery Attention Mechanism Cancer Drug Response Convolutional Neural Networks (CNN) Multi-Omics Integration Recurrent Neural Networks (RNN) Precision Medicine Full Text Additional Declarations No competing interests reported. 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-6274280","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":441844691,"identity":"c28b3eb9-2911-41eb-8bdf-4ea98615af7e","order_by":0,"name":"Syed Mohammed Azmal","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9klEQVRIie3PsQqCQBjA8TuENqlRiPAVgiCCHqXFQ2jyaL3B5CZbilaHsFcwBGflwIYMV6mGWpqdwrHTrUGlLej+w8fJ3Q/8ABCJfjQFgBDS8nQnfEgS/YJoSUngNwTZ5WwhqqNHl4zcBtvtCeXIXc66K04KEtSSYTbXp0byHDnh2VdQcMQOgxSuk2s9UYxxH9sM0WjjcRJjyokE7XqiOotXRfZM9gu0i/G+jYDM6FTEi+VAQdTEXhsZ8jX4Lmx0SORgosUhPnASNe2irvTH1SBs4KZnP8tNC7spi+4FafixnvbxyaoZ1r/ndT+vrcbHIpFI9J+9AT8oaR4HKNWgAAAAAElFTkSuQmCC","orcid":"","institution":"Koneru Lakshmaiah Education Foundation","correspondingAuthor":true,"prefix":"","firstName":"Syed","middleName":"Mohammed","lastName":"Azmal","suffix":""},{"id":441844692,"identity":"4af445a7-f37f-47c0-9569-f545a0ff0d4d","order_by":1,"name":"Sajja Tulasi Krishna","email":"","orcid":"","institution":"Koneru Lakshmaiah Education Foundation","correspondingAuthor":false,"prefix":"","firstName":"Sajja","middleName":"Tulasi","lastName":"Krishna","suffix":""}],"badges":[],"createdAt":"2025-03-21 05:38:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6274280/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6274280/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":83487661,"identity":"0e0576da-1bd1-44ab-add7-4198ff34ddd8","added_by":"auto","created_at":"2025-05-27 09:02:22","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1014931,"visible":true,"origin":"","legend":"","description":"","filename":"springersubmission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6274280/v1_covered_4f32fb5a-2133-4fed-b837-c256bbdbba12.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"OCR: OmniNet-Fusion: A Hybrid Attention-Based CNN-RNN Model for Multi-Omics Integration in Precision Cancer Drug Response Prediction","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"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":"Attention Mechanism, Cancer Drug Response, Convolutional Neural Networks (CNN), Multi-Omics Integration, Recurrent Neural Networks (RNN), Precision Medicine","lastPublishedDoi":"10.21203/rs.3.rs-6274280/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6274280/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe increasing complexity of cancer treatment necessitates advanced computational models for accurate drug response prediction. OmniNet-Fusion (OCR) is a hybrid deep learning model designed to integrate multi-omics data\u0026mdash;genomics, transcriptomics, proteomics, and metabolomics\u0026mdash;enhancing precision medicine. The model leverages a Convolutional Neural Network (CNN) to analyze spatial omics data and a Recurrent Neural Network (RNN) to process sequential data, with an attention mechanism highlighting crucial features across omics layers. To optimize predictive accuracy, feature selection techniques such as Lasso regression and mutual information filtering are utilized, while Principal Component Analysis (PCA) reduces dimensionality, ensuring computational efficiency. The model undergoes evaluation using key performance metrics, including accuracy, precision, recall, F1-score, and AUC-ROC, demonstrating superior predictive performance over existing methods. By integrating multi-omics fusion and deep learning, OCR enhances biological interpretability and facilitates personalized cancer treatment. This approach not only improves drug response prediction but also provides deeper insights into cancer mechanisms, supporting precision oncology and advancing AI-driven cancer therapy.\u003c/p\u003e","manuscriptTitle":"OCR: OmniNet-Fusion: A Hybrid Attention-Based CNN-RNN Model for Multi-Omics Integration in Precision Cancer Drug Response Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-16 18:29:36","doi":"10.21203/rs.3.rs-6274280/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":"676383c6-a7f2-4c29-afc2-963e2f9270ec","owner":[],"postedDate":"April 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":47050049,"name":"Biological sciences/Cancer"},{"id":47050050,"name":"Biological sciences/Drug discovery"}],"tags":[],"updatedAt":"2025-05-27T08:54:03+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-16 18:29:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6274280","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6274280","identity":"rs-6274280","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}