ZipAEr: A compressive convolutional autoencoder for high-dimensional spatial omics data at subcellular resolution

ZipAEr: A compressive convolutional autoencoder for high-dimensional spatial omics data at subcellular resolution | 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 ZipAEr: A compressive convolutional autoencoder for high-dimensional spatial omics data at subcellular resolution Habil Zare, Shiva Kazempour, Javad Razavian, Sogand Sajedi, Miranda Orr, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7541289/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 Recent advances in spatial transcriptomics have produced rich, high-throughput datasets, but their biological interpretation remains challenging due to analytical complexity. We present ZipAEr, a convolutional autoencoder tailored to extract informative latent features from spatial omics data. Unlike traditional methods that reduce data at the cell level, ZipAEr operates at the transcript level, preserving both subcellular and extracellular spatial context. Conventional autoencoders, built for images with three channels (red, green, blue), cannot handle spatial omics data with thousands of input channelsrepresenting genes and proteins. ZipAEr addresses this by reducing both spatial dimensions and channel count through its convolutional layers. It also introduces channel weighting in the loss function to ensure balanced representation of lowly expressed genes. ZipAEr effectively compresses spatial omics data by two to three orders of magnitude while preserving key spatial and molecular features. The resulting latent representation enables downstream analyses, such as classification and clustering, which would otherwise be computationally infeasible with raw data. Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Computational biology and bioinformatics/Computational models Biological sciences/Molecular biology/Transcriptomics Biological sciences/Biological techniques/Software Full Text Additional Declarations There is NO Competing Interest. 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-7541289","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":516240705,"identity":"a00ee515-065f-4a78-ace0-d058c50f34de","order_by":0,"name":"Habil Zare","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6ElEQVRIiWNgGAWjYLCCD2CSh+EATECCkA7GGQgtBsRpYeaBamEgSot8+9mHj23bGBL7+88ePFzw64+cOQPzwds8+BzVk25snAvUMuNGXsLhmX0GxpYNbMnW+LQwM6SxSQO15Dbc4DE4zNtjkLjhAI+ZND4tbPzP2H9bArXMP38GpoX/G14tPBJpbMyMQC0bDuQYHOb5AbaFDa8WCYlnzJI95yTqN94AauFtMDY2OMxmbDkHjxb5/jTGDz/KbIzlzp8x/szzR07O4Hjzwxtv8GiBWQahgC4EhQhJ4A9pykfBKBgFo2BkAAD9WUhsgnBsrQAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0001-5902-6238","institution":"University of Texas Health Science Center in San Antonio","correspondingAuthor":true,"prefix":"","firstName":"Habil","middleName":"","lastName":"Zare","suffix":""},{"id":516240706,"identity":"b75c49f6-f585-48b4-96e5-8d5e7d678a81","order_by":1,"name":"Shiva Kazempour","email":"","orcid":"","institution":"University of Texas Health Science Center in San Antonio","correspondingAuthor":false,"prefix":"","firstName":"Shiva","middleName":"","lastName":"Kazempour","suffix":""},{"id":516240707,"identity":"a1372381-2b6d-41d9-8fd6-6682e577bf27","order_by":2,"name":"Javad Razavian","email":"","orcid":"https://orcid.org/0000-0002-0222-7570","institution":"The University of Texas Health Science Center, San Antonio, Texas, USA","correspondingAuthor":false,"prefix":"","firstName":"Javad","middleName":"","lastName":"Razavian","suffix":""},{"id":516240708,"identity":"b99f055c-af13-487e-a917-3938509d3116","order_by":3,"name":"Sogand Sajedi","email":"","orcid":"","institution":"University of Texas Health Science Center in San Antonio","correspondingAuthor":false,"prefix":"","firstName":"Sogand","middleName":"","lastName":"Sajedi","suffix":""},{"id":516240709,"identity":"4b58681b-0120-4adc-acff-58ed9315996c","order_by":4,"name":"Miranda Orr","email":"","orcid":"","institution":"Department of Neurology, Washington University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Miranda","middleName":"","lastName":"Orr","suffix":""},{"id":516240710,"identity":"a34eb3ea-6583-4f85-a5ab-b3f530e57c54","order_by":5,"name":"Megan Pater","email":"","orcid":"","institution":"School of Medicine, Saint Louis University","correspondingAuthor":false,"prefix":"","firstName":"Megan","middleName":"","lastName":"Pater","suffix":""},{"id":516240711,"identity":"331c52e4-5aff-4df9-80d3-5d7d2b5eabfd","order_by":6,"name":"Grant Kolar","email":"","orcid":"","institution":"Department of Biological Sciences, Missouri University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Grant","middleName":"","lastName":"Kolar","suffix":""},{"id":516240712,"identity":"1e1bb16d-ae95-4b52-996e-661cf7c5b712","order_by":7,"name":"Soroosh Solhjoo","email":"","orcid":"","institution":"Johns Hopkins University School of Medicine","correspondingAuthor":false,"prefix":"","firstName":"Soroosh","middleName":"","lastName":"Solhjoo","suffix":""}],"badges":[],"createdAt":"2025-09-05 06:35:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7541289/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7541289/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91512976,"identity":"3dd4239a-c236-4011-bb16-648fd734631b","added_by":"auto","created_at":"2025-09-17 08:55:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2725096,"visible":true,"origin":"","legend":"Article File","description":"","filename":"ZipAErCosMx.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7541289/v1_covered_703268f5-b0a7-47b2-895f-e089f314be97.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"ZipAEr: A compressive convolutional autoencoder for high-dimensional spatial omics data at subcellular resolution","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-7541289/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7541289/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Recent advances in spatial transcriptomics have produced rich, high-throughput datasets, but their biological interpretation remains challenging due to analytical complexity. We present ZipAEr, a convolutional autoencoder tailored to extract informative latent features from spatial omics data. Unlike traditional methods that reduce data at the cell level, ZipAEr operates at the transcript level, preserving both subcellular and extracellular spatial context. Conventional autoencoders, built for images with three channels (red, green, blue), cannot handle spatial omics data with thousands of input channelsrepresenting genes and proteins. ZipAEr addresses this by reducing both spatial dimensions and channel count through its convolutional layers. It also introduces channel weighting in the loss function to ensure balanced representation of lowly expressed genes. ZipAEr effectively compresses spatial omics data by two to three orders of magnitude while preserving key spatial and molecular features. The resulting latent representation enables downstream analyses, such as classification and clustering, which would otherwise be computationally infeasible with raw data.","manuscriptTitle":"ZipAEr: A compressive convolutional autoencoder for high-dimensional spatial omics data at subcellular resolution","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-17 08:30:52","doi":"10.21203/rs.3.rs-7541289/v1","editorialEvents":[],"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":"4ba7c395-9b83-4e71-adf9-6dacdded0d60","owner":[],"postedDate":"September 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":54845221,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":54845222,"name":"Biological sciences/Computational biology and bioinformatics/Computational models"},{"id":54845223,"name":"Biological sciences/Molecular biology/Transcriptomics"},{"id":54845224,"name":"Biological sciences/Biological techniques/Software"}],"tags":[],"updatedAt":"2025-09-18T09:17:19+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-17 08:30:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7541289","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7541289","identity":"rs-7541289","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}