A Morphology-Based Machine Learning Model for Scoring Epithelial-Mesenchymal Plasticity using Organelle Dynamics.

A Morphology-Based Machine Learning Model for Scoring Epithelial-Mesenchymal Plasticity using Organelle Dynamics. | 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 A Morphology-Based Machine Learning Model for Scoring Epithelial-Mesenchymal Plasticity using Organelle Dynamics. Jonas Fuxe, Justin Slager, Francesca Gatto, Benjamin Frey, Bartlomiej Porebski, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5859608/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 10 Dec, 2025 Read the published version in Communications Biology → Version 1 posted You are reading this latest preprint version Abstract Epithelial-mesenchymal transition (EMT) is a key biological process in development and its reactivation plays an important role in cancer progression and resistance to various therapies. There is a lack of EMT targeting strategies and current methods to assess EMT are limited by low scalability and insufficient capacity to score EMT and capture hybrid EMT states. To address this, we developed a novel morphology-based machine learning method to predict epithelial-mesenchymal plasticity (EMP) by using organelle dynamics. Using the Cell Painting assay and high-throughput microscopy we trained a histogram gradient boosting classifier to identify changes in organelle dynamics at different stages of TGF-β1-induced EMT in mammary gland epithelial cells. The model achieved robust performance across multiple datasets and was capable of capturing EMT kinetics and hybrid states, as well as reversal of EMT by mesenchymal-epithelial transition (MET). Importantly, the EMT model was capable to accurately score EMT in human breast cancer cells in an annotation-independent fashion. The method is scalable, cost-effective and offers a powerful tool for drug discovery and for targeting cellular plasticity and therapy resistance in cancer. Furthermore, it can be used to gain deepened understanding of the cellular pathophysiological mechanisms involved in the EMT process. Biological sciences/Cancer/Breast cancer Biological sciences/Cell biology/Cellular imaging Biological sciences/Cell biology/Organelles Biological sciences/Stem cells/Transdifferentiation Health sciences/Medical research/Experimental models of disease Cell Painting Epithelial-mesenchymal transition (EMT) Epithelial-mesenchymal plasticity (EMP) Machine-learning Organelle morphology Full Text Additional Declarations There is NO Competing Interest. Supplementary Files SupplementaryTable1.xlsx Supplementary Table 1 SupplementaryTable2.xlsx Supplementary Table 2 MSSLAGERETALSUPPLINFO.pdf Supplementary Data RS453.pdf Reporting Summary Cite Share Download PDF Status: Published Journal Publication published 10 Dec, 2025 Read the published version in Communications Biology → 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-5859608","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":431506592,"identity":"61974ab3-45c2-4c8e-b155-82c89e62d89f","order_by":0,"name":"Jonas Fuxe","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwklEQVRIiWNgGAWjYBACxgYwJQfEzIcZEkjQYgzEbMnEaYECkBYeY+LUMrf3Hvz4g8EgccPxns8GDxjq5Ag7rOdcsjQPUMvMnrObExIYDhO2inFGjoE0A8OfxH6J3M0HEhgOJDYQocX4J8hhbfJvHgO11NUTo8VMAuSwfgkeZqDDmBOI8MsZM2seAwPjmT1pxgYJBocNCdpi2N5jfPNHhYHshuOHH0v+qKiTJ2gLxFADGNcAp0IEIGzoKBgFo2AUjAIA6Jo4HiUSSHIAAAAASUVORK5CYII=","orcid":"","institution":"Karolinska Institutet","correspondingAuthor":true,"prefix":"","firstName":"Jonas","middleName":"","lastName":"Fuxe","suffix":""},{"id":431506593,"identity":"10a87761-cd27-492c-a76e-72372efafd5c","order_by":1,"name":"Justin Slager","email":"","orcid":"https://orcid.org/0009-0005-0481-8154","institution":"Karolinska Institutet","correspondingAuthor":false,"prefix":"","firstName":"Justin","middleName":"","lastName":"Slager","suffix":""},{"id":431506594,"identity":"11872145-9585-4ec9-8cc4-aae74827a436","order_by":2,"name":"Francesca Gatto","email":"","orcid":"","institution":"Karolinska Institutet","correspondingAuthor":false,"prefix":"","firstName":"Francesca","middleName":"","lastName":"Gatto","suffix":""},{"id":431506595,"identity":"1b4d438c-78d5-448b-9ce1-1d81ba520ae8","order_by":3,"name":"Benjamin Frey","email":"","orcid":"https://orcid.org/0009-0004-7649-8340","institution":"Uppsala University","correspondingAuthor":false,"prefix":"","firstName":"Benjamin","middleName":"","lastName":"Frey","suffix":""},{"id":431506596,"identity":"1b16dd39-c1f8-40d0-a764-b4fb3f696f61","order_by":4,"name":"Bartlomiej Porebski","email":"","orcid":"","institution":"Karolinska Institutet","correspondingAuthor":false,"prefix":"","firstName":"Bartlomiej","middleName":"","lastName":"Porebski","suffix":""},{"id":431506597,"identity":"6ed139c3-4d08-44e6-9ef6-e756841ceec8","order_by":5,"name":"Jordi Carreras-Puigvert","email":"","orcid":"","institution":"Uppsala University","correspondingAuthor":false,"prefix":"","firstName":"Jordi","middleName":"","lastName":"Carreras-Puigvert","suffix":""},{"id":431506598,"identity":"a3d3061f-1b11-4590-b8ca-15e4be9f48d6","order_by":6,"name":"Malgorzata Parniewska","email":"","orcid":"","institution":"Karolinska Institutet","correspondingAuthor":false,"prefix":"","firstName":"Malgorzata","middleName":"","lastName":"Parniewska","suffix":""},{"id":431506599,"identity":"a0536326-b760-4d8f-8a84-7df02d379373","order_by":7,"name":"Wenyang Shi","email":"","orcid":"","institution":"Karolinska Institutet","correspondingAuthor":false,"prefix":"","firstName":"Wenyang","middleName":"","lastName":"Shi","suffix":""}],"badges":[],"createdAt":"2025-01-19 13:10:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5859608/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5859608/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s42003-025-09326-8","type":"published","date":"2025-12-10T05:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":100213179,"identity":"089ad50a-1fa8-4782-988a-a9a191a7a47a","added_by":"auto","created_at":"2026-01-14 08:06:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1683656,"visible":true,"origin":"","legend":"Article File","description":"","filename":"MSSLAGERETALTEXTXFIGS.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5859608/v1_covered_cb509229-ed0d-459c-8d52-bce2e66e1bb7.pdf"},{"id":78933841,"identity":"a6825501-c407-487e-b925-31b0d0876dcb","added_by":"auto","created_at":"2025-03-21 04:03:05","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":17646,"visible":true,"origin":"","legend":"Supplementary Table 1","description":"","filename":"SupplementaryTable1.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5859608/v1/9d44d1b2581b597334e11325.xlsx"},{"id":78934547,"identity":"cf516dbf-1b77-474f-a638-380586dd7c6b","added_by":"auto","created_at":"2025-03-21 04:11:05","extension":"xlsx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":29076,"visible":true,"origin":"","legend":"Supplementary Table 2","description":"","filename":"SupplementaryTable2.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5859608/v1/ad70cc268612b734f8156974.xlsx"},{"id":78933846,"identity":"f35ddca9-01a0-465e-b17a-c64ae69b98f7","added_by":"auto","created_at":"2025-03-21 04:03:05","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":7887185,"visible":true,"origin":"","legend":"Supplementary Data","description":"","filename":"MSSLAGERETALSUPPLINFO.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5859608/v1/5476e0d292d97bc2ed9c8351.pdf"},{"id":78933845,"identity":"ea6932c8-c76c-45ca-b416-fc4fdbaf6bbc","added_by":"auto","created_at":"2025-03-21 04:03:05","extension":"pdf","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":1460051,"visible":true,"origin":"","legend":"Reporting Summary","description":"","filename":"RS453.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5859608/v1/b1bb22c6774827b9d7c81afd.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"A Morphology-Based Machine Learning Model for Scoring Epithelial-Mesenchymal Plasticity using Organelle Dynamics.","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"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 Painting, Epithelial-mesenchymal transition (EMT), Epithelial-mesenchymal plasticity (EMP), Machine-learning, Organelle morphology","lastPublishedDoi":"10.21203/rs.3.rs-5859608/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5859608/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Epithelial-mesenchymal transition (EMT) is a key biological process in development and its reactivation plays an important role in cancer progression and resistance to various therapies. There is a lack of EMT targeting strategies and current methods to assess EMT are limited by low scalability and insufficient capacity to score EMT and capture hybrid EMT states. To address this, we developed a novel morphology-based machine learning method to predict epithelial-mesenchymal plasticity (EMP) by using organelle dynamics. Using the Cell Painting assay and high-throughput microscopy we trained a histogram gradient boosting classifier to identify changes in organelle dynamics at different stages of TGF-β1-induced EMT in mammary gland epithelial cells. The model achieved robust performance across multiple datasets and was capable of capturing EMT kinetics and hybrid states, as well as reversal of EMT by mesenchymal-epithelial transition (MET). Importantly, the EMT model was capable to accurately score EMT in human breast cancer cells in an annotation-independent fashion. The method is scalable, cost-effective and offers a powerful tool for drug discovery and for targeting cellular plasticity and therapy resistance in cancer. Furthermore, it can be used to gain deepened understanding of the cellular pathophysiological mechanisms involved in the EMT process.","manuscriptTitle":"A Morphology-Based Machine Learning Model for Scoring Epithelial-Mesenchymal Plasticity using Organelle Dynamics.","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-21 04:03:01","doi":"10.21203/rs.3.rs-5859608/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"communications-biology","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"commsbio","sideBox":"Learn more about [Communications Biology](http://www.nature.com/commsbio/)","snPcode":"","submissionUrl":"","title":"Communications Biology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Communications Series","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"3280b8ea-aba9-4565-8f28-ebab1e13c7da","owner":[],"postedDate":"March 21st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":45959531,"name":"Biological sciences/Cancer/Breast cancer"},{"id":45959532,"name":"Biological sciences/Cell biology/Cellular imaging"},{"id":45959533,"name":"Biological sciences/Cell biology/Organelles"},{"id":45959534,"name":"Biological sciences/Stem cells/Transdifferentiation"},{"id":45959535,"name":"Health sciences/Medical research/Experimental models of disease"}],"tags":[],"updatedAt":"2026-01-14T08:06:22+00:00","versionOfRecord":{"articleIdentity":"rs-5859608","link":"https://doi.org/10.1038/s42003-025-09326-8","journal":{"identity":"communications-biology","isVorOnly":false,"title":"Communications Biology"},"publishedOn":"2025-12-10 05:00:00","publishedOnDateReadable":"December 10th, 2025"},"versionCreatedAt":"2025-03-21 04:03:01","video":"","vorDoi":"10.1038/s42003-025-09326-8","vorDoiUrl":"https://doi.org/10.1038/s42003-025-09326-8","workflowStages":[]},"version":"v1","identity":"rs-5859608","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5859608","identity":"rs-5859608","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}