Multi-Omics Modality Completion and Knowledge Distillation for Drug Response Prediction in Cervical Cancer

Multi-Omics Modality Completion and Knowledge Distillation for Drug Response Prediction in Cervical Cancer | 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 Multi-Omics Modality Completion and Knowledge Distillation for Drug Response Prediction in Cervical Cancer DongZi Li, Kai Liao, Bowei Yan, Jian Huang, Jing Zhang, YiChen Chen, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6590717/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 In clinical practice, the development of personalized treatment strategies for cervical cancer is hindered by the limited accuracy of drug response prediction, partly due to missing modalities in multi-omics data. We present MKDR, a deep learning framework that integrates variational autoencoder-based modality completion with knowledge distillation to transfer information from complete omics data to incomplete samples. MKDR-Student achieves state-of-the-art performance On cervical cancer cell lines, with an MSE of 0.0034 (34% lower than Xgboost), R² of 0.8126, and MAE of 0.0431, while maintaining high Spearman (0.8647) and Pearson (0.9033) correlations. Data ablation experiments highlight the contributions of knowledge distillation and modality completion: removing the teacher increases MSE by 23%, and VAE reduces error by 15% with 40% missingness. Interpretability analysis shows balanced feature contributions from gene expression (38%), copy number variation (30%), and mutation data (32%), indicating effective multi-omics learning and integration by the student model. Under limited-input conditions, MKDR’ s accuracy drops less than 5%, supporting its robustness and potential for clinical application. 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-6590717","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":452129780,"identity":"02a82074-b9ad-47ad-8a54-be52e6fd7280","order_by":0,"name":"DongZi Li","email":"","orcid":"","institution":"The Affiliated Women and Children's Hospital of Ningbo University","correspondingAuthor":false,"prefix":"","firstName":"DongZi","middleName":"","lastName":"Li","suffix":""},{"id":452129781,"identity":"5875db15-a8c4-497d-bb38-d37d80b2128d","order_by":1,"name":"Kai Liao","email":"","orcid":"","institution":"The Affiliated Women and Children's Hospital of Ningbo University","correspondingAuthor":false,"prefix":"","firstName":"Kai","middleName":"","lastName":"Liao","suffix":""},{"id":452129782,"identity":"b89a567a-e1d6-40d6-b54a-f930d645c221","order_by":2,"name":"Bowei Yan","email":"","orcid":"","institution":"Institutes of Biomedical Sciences，Fudan University","correspondingAuthor":false,"prefix":"","firstName":"Bowei","middleName":"","lastName":"Yan","suffix":""},{"id":452129783,"identity":"569f6f31-d1e9-4bfc-8336-8cee3aa357e7","order_by":3,"name":"Jian Huang","email":"","orcid":"","institution":"Chongqing University","correspondingAuthor":false,"prefix":"","firstName":"Jian","middleName":"","lastName":"Huang","suffix":""},{"id":452129784,"identity":"973b8001-d9c4-4510-a06c-eee5df2aefd3","order_by":4,"name":"Jing Zhang","email":"","orcid":"","institution":"The Affiliated Women and Children's Hospital of Ningbo University","correspondingAuthor":false,"prefix":"","firstName":"Jing","middleName":"","lastName":"Zhang","suffix":""},{"id":452129785,"identity":"2e19eb70-ecfd-4660-823d-7b6176d2e4ab","order_by":5,"name":"YiChen Chen","email":"","orcid":"","institution":"The Affiliated Women and Children's Hospital of Ningbo University","correspondingAuthor":false,"prefix":"","firstName":"YiChen","middleName":"","lastName":"Chen","suffix":""},{"id":452129786,"identity":"926605ab-c6b2-4351-85fd-dee9007fcccf","order_by":6,"name":"Jue Zhu","email":"","orcid":"","institution":"The Affiliated Women and Children's Hospital of Ningbo University","correspondingAuthor":false,"prefix":"","firstName":"Jue","middleName":"","lastName":"Zhu","suffix":""},{"id":452129787,"identity":"254298f8-d077-4ff0-9972-8e5fbc243292","order_by":7,"name":"Shuang Zhi","email":"","orcid":"","institution":"The Affiliated Women and Children's Hospital of Ningbo University","correspondingAuthor":false,"prefix":"","firstName":"Shuang","middleName":"","lastName":"Zhi","suffix":""},{"id":452129788,"identity":"391b23ba-2624-47fd-bc26-9eee73573092","order_by":8,"name":"Pingli chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDUlEQVRIiWNgGAWjYBAC+wMMjB8YGOxg/MOJ/czMhx/g08LGwMAswcCQjNAys50tzYCAFiBiOADjpxkbnOdRkMCrhb3HjOFHxQE5c/41ho8LftnIGR/mYTBgqLGJxqmF54wZY8+ZA8aWM94YG8/sk+AxO8x74AHDsbTcBlxaJHLMLHjbjiduuHHGTJq3B6SFL8GAseEwXi2Sf9sOw7XIGTfzGEgQ0iLNC9JyvsdMmueHhLEBMyEtPMeKpWXOJBsb3GArNuZtkEiccRgYyAn4/MLevPHjmwo7OYPzhzc+5vkjkdjff/jwgw81Nji1IIBEhgEDYxuUk0BQOQjwH3/AwPCHKKWjYBSMglEwwgAALBtaivvMYP0AAAAASUVORK5CYII=","orcid":"","institution":"The Affiliated Women and Children's Hospital of Ningbo University","correspondingAuthor":true,"prefix":"","firstName":"Pingli","middleName":"","lastName":"chen","suffix":""}],"badges":[],"createdAt":"2025-05-05 02:23:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6590717/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6590717/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":82059426,"identity":"4589dd67-0e34-41bb-92fd-d7746aa7703d","added_by":"auto","created_at":"2025-05-06 11:14:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":970325,"visible":true,"origin":"","legend":"","description":"","filename":"MKDRcomple.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6590717/v1_covered_f3147e1d-533e-4835-9122-7743e653e2ca.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multi-Omics Modality Completion and Knowledge Distillation for Drug Response Prediction in Cervical Cancer","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"","lastPublishedDoi":"10.21203/rs.3.rs-6590717/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6590717/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In clinical practice, the development of personalized treatment strategies for cervical cancer is hindered by the limited accuracy of drug response prediction, partly due to missing modalities in multi-omics data. We present MKDR, a deep learning framework that integrates variational autoencoder-based modality completion with knowledge distillation to transfer information from complete omics data to incomplete samples. MKDR-Student achieves state-of-the-art performance On cervical cancer cell lines, with an MSE of 0.0034 (34% lower than Xgboost), R² of 0.8126, and MAE of 0.0431, while maintaining high Spearman (0.8647) and Pearson (0.9033) correlations. Data ablation experiments highlight the contributions of knowledge distillation and modality completion: removing the teacher increases MSE by 23%, and VAE reduces error by 15% with 40% missingness. Interpretability analysis shows balanced feature contributions from gene expression (38%), copy number variation (30%), and mutation data (32%), indicating effective multi-omics learning and integration by the student model. Under limited-input conditions, MKDR’ s accuracy drops less than 5%, supporting its robustness and potential for clinical application.","manuscriptTitle":"Multi-Omics Modality Completion and Knowledge Distillation for Drug Response Prediction in Cervical Cancer","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-06 10:58:01","doi":"10.21203/rs.3.rs-6590717/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":"1683a555-1102-4c67-bb0c-070b39892fb0","owner":[],"postedDate":"May 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-05-06T10:58:03+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-06 10:58:01","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6590717","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6590717","identity":"rs-6590717","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}