CTransformer: Deep-transformer-based 3D cell membrane tracking with subcellular-resolved molecular quantification

CTransformer: Deep-transformer-based 3D cell membrane tracking with subcellular-resolved molecular quantification | 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 CTransformer: Deep-transformer-based 3D cell membrane tracking with subcellular-resolved molecular quantification Rigaudiere Z.L. Li, Guoye Guan, Xian Xiu, Dongying Xie, Yiming Ma, and 11 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8944271/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Deep learning segmentation and fluorescence imaging techniques allow the cellular morphology of living embryos to be constructed spatiotemporally. These development processes involve numerous molecules distributed at the subcellular scale, such as cell adhesion (E-cadherin), which accumulate at cell-cell interfaces to regulate intercellular connections. However, quantifying molecular distributions within specific subcellular regions across the entire embryo, where cell movement and molecular redistribution occur rapidly, is challenging due to the need for simultaneous cell morphology reconstruction and lineage tracing due to photobleaching and phototoxicity. We report a transformer-based pipeline, CTransformer, that establishes a 4D cellular morphology map before the 550-cell (late) stage. CTransformer constructed 4D cellular morphology atlases, reaching 80% accuracy at the 550-cell stage. Through this advanced architecture, we use only one channel to reconstruct cell morphology and achieve cell tracing. With each cell’s morphology as a reference, the distribution of specific molecules throughout the cell body and at cell interfaces can be quantitatively measured in another fluorescence channel. We apply this methodology to track E-cadherin during embryonic development of the worm Caenorhabditis elegans, from fertilization to gastrulation. Our results reveal that E-cadherin is tightly regulated across individual embryos, both within single cells and at cell-cell interfaces, displaying an anterior-posterior gradient and cell- and lineage-specific patterns. Furthermore, its spatiotemporal heterogeneity influences cell mechanics and embryonic morphogenesis, helping explain how C. elegans achieves stereotypical developmental patterns at cellular resolution. In summary, CTransformer offers a high-throughput approach for measuring molecular distributions at subcellular resolution, providing valuable knowledge for cellular and developmental biology, biophysics, and bioinformatics. Biological sciences/Computational biology and bioinformatics/Computational models Biological sciences/Cell biology/Cell adhesion Biological sciences/Biological techniques/Biological models/Genetic models Cell Morphology Molecular Quantification Subcellular Resolution E-cadherin Cell Adhesion Transformer Generative Adversarial Network (GAN) Human-in-the-loop Full Text Additional Declarations There is NO Competing Interest. Supplementary Files SupplementaryInformationsumitting1.pdf Supplementary Information of paper Cite Share Download PDF Status: Under Review 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-8944271","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":599517030,"identity":"c185d484-17c3-42df-ab39-c1f8384a9d6d","order_by":0,"name":"Rigaudiere Z.L. Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFUlEQVRIiWNgGAWjYFAC5oYDDAUSckDGARCXByLKxsBgwINLCyNQi4GEMVBVAlgLDzFagLIMiUDFBgwIa/BokW9vbDxcYGCRwMB+5utmHgY7GXuJHAOGD2WHGcx5DmC3o+dgw+EZBhJ5DDy5227zMCTz8AC1MM44d5jBsrcBu+clEhsO8xhIFNvf4AVpOQDWwszbdpjB4Dx2h7HJPwRrSWyQ4HmG0PIXjxYeCUa4FjaEFkaQlrPYHSbBA3GYMQNPmtnNOQZAv5x5VnCw51w6j8EZ7N6Xbz98+DNPRZ0cA/vhZzfeVNjZs7cnb3zwo8xazuBMAnaXIQMmcNQIJDCAjMcZkSiA8QeI5MfunlEwCkbBKBi5AABoS1TOPqIKswAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-0985-8420","institution":"City University of Hong Kong","correspondingAuthor":true,"prefix":"","firstName":"Rigaudiere","middleName":"Z.L.","lastName":"Li","suffix":""},{"id":599517031,"identity":"10727f9c-86b1-498d-b412-80d4ceb01804","order_by":1,"name":"Guoye Guan","email":"","orcid":"https://orcid.org/0000-0003-4479-4722","institution":"Harvard Medical School and Dana-Farber Cancer Institute","correspondingAuthor":false,"prefix":"","firstName":"Guoye","middleName":"","lastName":"Guan","suffix":""},{"id":599517032,"identity":"9433dc41-fdef-4593-8fd0-85851bf86880","order_by":2,"name":"Xian Xiu","email":"","orcid":"","institution":"City University of Hong Kong","correspondingAuthor":false,"prefix":"","firstName":"Xian","middleName":"","lastName":"Xiu","suffix":""},{"id":599517033,"identity":"90bca27e-fb6c-4e1e-9741-78ef88bf7a39","order_by":3,"name":"Dongying Xie","email":"","orcid":"","institution":"Hong Kong Baptist University","correspondingAuthor":false,"prefix":"","firstName":"Dongying","middleName":"","lastName":"Xie","suffix":""},{"id":599517034,"identity":"22cbdd04-d365-4df0-9a8f-19125dbfb8d7","order_by":4,"name":"Yiming Ma","email":"","orcid":"https://orcid.org/0000-0002-3646-3619","institution":"Hong Kong Baptist University","correspondingAuthor":false,"prefix":"","firstName":"Yiming","middleName":"","lastName":"Ma","suffix":""},{"id":599517035,"identity":"14d727a9-800d-46e8-8cc9-0fa980889789","order_by":5,"name":"Chenwei Wang","email":"","orcid":"","institution":"Centre for Intelligent Multidimensional Data Analysis","correspondingAuthor":false,"prefix":"","firstName":"Chenwei","middleName":"","lastName":"Wang","suffix":""},{"id":599517036,"identity":"95224f75-5edf-4d5b-82f8-9314bc37205e","order_by":6,"name":"Sicheng You","email":"","orcid":"","institution":"Centre for Intelligent Multidimensional Data Analysis","correspondingAuthor":false,"prefix":"","firstName":"Sicheng","middleName":"","lastName":"You","suffix":""},{"id":599517037,"identity":"fc9f8a68-066a-4657-83c7-516ff9ea7471","order_by":7,"name":"Zhen Zhu","email":"","orcid":"","institution":"Centre for Intelligent Multidimensional Data Analysis","correspondingAuthor":false,"prefix":"","firstName":"Zhen","middleName":"","lastName":"Zhu","suffix":""},{"id":599517038,"identity":"08667e91-caa8-404d-91f5-5eebf51fbcaa","order_by":8,"name":"Darrick Lee","email":"","orcid":"","institution":"University of Edinburgh","correspondingAuthor":false,"prefix":"","firstName":"Darrick","middleName":"","lastName":"Lee","suffix":""},{"id":599517039,"identity":"536f4144-f36b-4d81-bcc0-154a2c213388","order_by":9,"name":"Zirui Zhang","email":"","orcid":"","institution":"City University of Hong Kong","correspondingAuthor":false,"prefix":"","firstName":"Zirui","middleName":"","lastName":"Zhang","suffix":""},{"id":599517040,"identity":"f3e1082b-fc26-42c3-acaa-c3a0fea72302","order_by":10,"name":"Zhuoheng Ran","email":"","orcid":"","institution":"City University of Hong Kong","correspondingAuthor":false,"prefix":"","firstName":"Zhuoheng","middleName":"","lastName":"Ran","suffix":""},{"id":599517041,"identity":"48c6fd63-7e50-4891-b6ee-fc85f3427b4f","order_by":11,"name":"Chao Tang","email":"","orcid":"https://orcid.org/0000-0003-1474-3705","institution":"Academy for Advanced Interdisciplinary Studies, Peking University","correspondingAuthor":false,"prefix":"","firstName":"Chao","middleName":"","lastName":"Tang","suffix":""},{"id":599517042,"identity":"aacf8c1e-5038-4d92-99d9-6b0d85973145","order_by":12,"name":"Jianfeng Cao","email":"","orcid":"","institution":"Harbin Institute of Technology (Shenzhen)","correspondingAuthor":false,"prefix":"","firstName":"Jianfeng","middleName":"","lastName":"Cao","suffix":""},{"id":599517043,"identity":"03041c04-e987-4dce-a0fa-6cad28cb1c05","order_by":13,"name":"Zhaoke Huang","email":"","orcid":"https://orcid.org/0000-0003-1837-9760","institution":"City University of Hong Kong","correspondingAuthor":false,"prefix":"","firstName":"Zhaoke","middleName":"","lastName":"Huang","suffix":""},{"id":599517044,"identity":"b09f19e1-bd13-4fcc-86e4-d74d1f2d8f76","order_by":14,"name":"Zhongying Zhao","email":"","orcid":"https://orcid.org/0000-0003-2743-9008","institution":"Hong Kong Baptist University","correspondingAuthor":false,"prefix":"","firstName":"Zhongying","middleName":"","lastName":"Zhao","suffix":""},{"id":599517045,"identity":"1e489139-58d2-4e46-afb1-d0db6cd4983b","order_by":15,"name":"Hong Yan","email":"","orcid":"https://orcid.org/0000-0001-9661-3095","institution":"City University of Hong Kong","correspondingAuthor":false,"prefix":"","firstName":"Hong","middleName":"","lastName":"Yan","suffix":""}],"badges":[],"createdAt":"2026-02-23 07:41:46","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8944271/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8944271/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105566173,"identity":"14a742d1-5335-4c33-940c-27232b5ea957","added_by":"auto","created_at":"2026-03-27 12:55:32","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1530220,"visible":true,"origin":"","legend":"Article File","description":"","filename":"Manuscriptsubmitting1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8944271/v1_covered_9dba2807-852d-4d21-a386-952e3eb5e697.pdf"},{"id":103881851,"identity":"46e6638f-3821-49bb-8eca-295b0dda26c1","added_by":"auto","created_at":"2026-03-04 05:48:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2461954,"visible":true,"origin":"","legend":"Supplementary Information of paper","description":"","filename":"SupplementaryInformationsumitting1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8944271/v1/27e5498ccee74524d99e0103.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"CTransformer: Deep-transformer-based 3D cell membrane tracking with subcellular-resolved molecular quantification","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Cell Morphology, Molecular Quantification, Subcellular Resolution, E-cadherin, Cell Adhesion, Transformer, Generative Adversarial Network (GAN), Human-in-the-loop","lastPublishedDoi":"10.21203/rs.3.rs-8944271/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8944271/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Deep learning segmentation and fluorescence imaging techniques allow the cellular morphology of living embryos to be constructed spatiotemporally. These development processes involve numerous molecules distributed at the subcellular scale, such as cell adhesion (E-cadherin), which accumulate at cell-cell interfaces to regulate intercellular connections. However, quantifying molecular distributions within specific subcellular regions across the entire embryo, where cell movement and molecular redistribution occur rapidly, is challenging due to the need for simultaneous cell morphology reconstruction and lineage tracing due to photobleaching and phototoxicity. We report a transformer-based pipeline, CTransformer, that establishes a 4D cellular morphology map before the 550-cell (late) stage. CTransformer constructed 4D cellular morphology atlases, reaching 80% accuracy at the 550-cell stage. Through this advanced architecture, we use only one channel to reconstruct cell morphology and achieve cell tracing. With each cell’s morphology as a reference, the distribution of specific molecules throughout the cell body and at cell interfaces can be quantitatively measured in another fluorescence channel. We apply this methodology to track E-cadherin during embryonic development of the worm Caenorhabditis elegans, from fertilization to gastrulation. Our results reveal that E-cadherin is tightly regulated across individual embryos, both within single cells and at cell-cell interfaces, displaying an anterior-posterior gradient and cell- and lineage-specific patterns. Furthermore, its spatiotemporal heterogeneity influences cell mechanics and embryonic morphogenesis, helping explain how C. elegans achieves stereotypical developmental patterns at cellular resolution. In summary, CTransformer offers a high-throughput approach for measuring molecular distributions at subcellular resolution, providing valuable knowledge for cellular and developmental biology, biophysics, and bioinformatics.","manuscriptTitle":"CTransformer: Deep-transformer-based 3D cell membrane tracking with subcellular-resolved molecular quantification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-04 05:48:21","doi":"10.21203/rs.3.rs-8944271/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-methods","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"nmeth","sideBox":"Learn more about [Nature Methods](http://www.nature.com/nmeth)","snPcode":"","submissionUrl":"","title":"Nature Methods","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Research","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"5d9c4f2d-e7a4-4785-85ee-4bb2d8605c06","owner":[],"postedDate":"March 4th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":63794229,"name":"Biological sciences/Computational biology and bioinformatics/Computational models"},{"id":63794230,"name":"Biological sciences/Cell biology/Cell adhesion"},{"id":63794231,"name":"Biological sciences/Biological techniques/Biological models/Genetic models"}],"tags":[],"updatedAt":"2026-05-08T19:55:18+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-04 05:48:21","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8944271","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8944271","identity":"rs-8944271","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}