PRISM: A Proteomics Robust Imputation framework for Structure-aware Modeling of missingness

PRISM: A Proteomics Robust Imputation framework for Structure-aware Modeling of missingness | 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 PRISM: A Proteomics Robust Imputation framework for Structure-aware Modeling of missingness Tiannan Guo, Zhaoxing Li, Yi Chen, Zhiwen Yang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7480159/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 Missing values in mass spectrometry (MS)-based proteomics, particularly within label-free quantification(LFQ) workflows, hinders downstream data analysis. These missing values are predominantly categorized as Missing Not At Random(MNAR),as they often arise when the signals ofl ow-abundance proteinsor peptides fall below the instrument’s limit of detection. To address this, we introduce PRISM, a novel imputation framework comprising two complementary deep learning models: a Denoising Convolutional Autoencoder (DCAE)and a Deep Matrix Factorization(DMF).The core innovation of the framework is its explicit modeling of the intrinsic MNAR missingness mechanism through a gradient downsampling strategy and a dual-task learning objective. We conducted a comprehensive evaluation on multiple real-world and synthetic proteomics datasets, assessing performance on metrics including numerical accuracy(RMSE),downstream classification task performance,and preservation of clustering structure. The results demonstrate that PRISM not only surpasses existing methods in imputation accuracybut,more importantly,also excels at preserving the inherent biological structure of the data,thereby supporting more accurate downstream prediction and exploratory analysis. Therefore, PRISM provides the proteomics research community with a more accurate toolkit that better preserves the original structure of data,thereby enhancing the credibility of biological discoveries obtained from incomplete data. Biological sciences/Biotechnology/Proteomics Biological sciences/Computational biology and bioinformatics/Machine learning proteomics mass spectrometry deep learning imputation missing values autoencoder matrix factorization Full Text Additional Declarations Yes there is potential Competing Interest. T.G. is a shareholder of Westlake Omics Inc. 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-7480159","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":509674887,"identity":"796acef4-f9e2-4d75-a634-79cac6744736","order_by":0,"name":"Tiannan Guo","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFUlEQVRIie2QMUvDQBiGLwQyfSXrCZL8hS84OPhHHHME6hJdhE4ON8UldY4U9C/o0jlyUJemXQ+SISJkjktJIUp7FrckdHS4Z/heuLuH9+MI0Wj+K/7vNFM1TwmosAYFgx8USwXCccohAY9T3MvgvSzviht7Fm9o3bZgxyIl9UQQe8Y7FU+OGfcX1S0tsvnJY4RAs8g3kpUgtEi7lST0uG8JxuX1PB/x/WJrQHMUCYLUH1B+BHuWYZW3LYK7tmvze0Bx6V5hkWAvMrRyYiFgFhPTGFAQKpawB8Fe5fh8O43OwFsu8C1eXQGVPS33QfrVbAR7ksEnNq3jOMvgo2wmF46d9LR0/oo6hM73qoX33Wg0Go3mjx3nTWdhsbgDdAAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0003-3869-7651","institution":"Westlake University","correspondingAuthor":true,"prefix":"","firstName":"Tiannan","middleName":"","lastName":"Guo","suffix":""},{"id":509674888,"identity":"588c92d4-bf75-45dc-9f38-49e5187dfe09","order_by":1,"name":"Zhaoxing Li","email":"","orcid":"","institution":"Westlake University","correspondingAuthor":false,"prefix":"","firstName":"Zhaoxing","middleName":"","lastName":"Li","suffix":""},{"id":509674889,"identity":"2ca88ab0-91ab-47c9-bb1a-a25f965beca9","order_by":2,"name":"Yi Chen","email":"","orcid":"","institution":"Westlake University","correspondingAuthor":false,"prefix":"","firstName":"Yi","middleName":"","lastName":"Chen","suffix":""},{"id":509674890,"identity":"0b641334-9294-46ef-8f4d-6f4611d9332b","order_by":3,"name":"Zhiwen Yang","email":"","orcid":"https://orcid.org/0009-0009-1608-7554","institution":"Yangzhou University","correspondingAuthor":false,"prefix":"","firstName":"Zhiwen","middleName":"","lastName":"Yang","suffix":""}],"badges":[],"createdAt":"2025-08-28 12:10:41","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7480159/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7480159/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93779085,"identity":"d8292679-b0ac-417a-aeff-0eebbbfc0d98","added_by":"auto","created_at":"2025-10-17 12:50:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":12368834,"visible":true,"origin":"","legend":"Article File","description":"","filename":"PRISM202508262224.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7480159/v1_covered_cc3048ca-3b62-4c2a-aa6f-aa626c43e2d1.pdf"}],"financialInterests":"\u003cb\u003eYes\u003c/b\u003e there is potential Competing Interest.\nT.G. is a shareholder of Westlake Omics Inc.","formattedTitle":"PRISM: A Proteomics Robust Imputation framework for Structure-aware Modeling of missingness","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":"proteomics, mass spectrometry, deep learning, imputation, missing values, autoencoder, matrix factorization","lastPublishedDoi":"10.21203/rs.3.rs-7480159/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7480159/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Missing values in mass spectrometry (MS)-based proteomics, particularly within label-free quantification(LFQ) workflows, hinders downstream data analysis. These missing values are predominantly categorized as Missing Not At Random(MNAR),as they often arise when the signals ofl ow-abundance proteinsor peptides fall below the instrument’s limit of detection. To address this, we introduce PRISM, a novel imputation framework comprising two complementary deep learning models: a Denoising Convolutional Autoencoder (DCAE)and a Deep Matrix Factorization(DMF).The core innovation of the framework is its explicit modeling of the intrinsic MNAR missingness mechanism through a gradient downsampling strategy and a dual-task learning objective. We conducted a comprehensive evaluation on multiple real-world and synthetic proteomics datasets, assessing performance on metrics including numerical accuracy(RMSE),downstream classification task performance,and preservation of clustering structure. The results demonstrate that PRISM not only surpasses existing methods in imputation accuracybut,more importantly,also excels at preserving the inherent biological structure of the data,thereby supporting more accurate downstream prediction and exploratory analysis. Therefore, PRISM provides the proteomics research community with a more accurate toolkit that better preserves the original structure of data,thereby enhancing the credibility of biological discoveries obtained from incomplete data.","manuscriptTitle":"PRISM: A Proteomics Robust Imputation framework for Structure-aware Modeling of missingness","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-04 07:32:27","doi":"10.21203/rs.3.rs-7480159/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":"85b8ebfb-689a-4900-a36b-ec9d3c2f8a08","owner":[],"postedDate":"September 4th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":54134179,"name":"Biological sciences/Biotechnology/Proteomics"},{"id":54134180,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"}],"tags":[],"updatedAt":"2025-10-17T12:41:15+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-04 07:32:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7480159","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7480159","identity":"rs-7480159","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}