Machine Learning Reveals Biocontrol Agents Shaping Disease Protection in Natural Arabidopsis Populations and Synthetic Communities

Machine Learning Reveals Biocontrol Agents Shaping Disease Protection in Natural Arabidopsis Populations and Synthetic Communities | 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 Machine Learning Reveals Biocontrol Agents Shaping Disease Protection in Natural Arabidopsis Populations and Synthetic Communities Eric Kemen, Maryam Mahmoudi, Yiheng Hu, Juliana Almario, Paolo Stincone, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6130404/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 Plants recruit beneficial microbes to defend against phytopathogens, and some are developed as biocontrol agents. However, identifying biocontrol agents depends on empirical screenings to assess microbial activity against pathogens of interest. In this study, we explored the association between infection status and phyllosphere microbiome dynamics over six generations from natural Arabidopsis populations and compared plants infected by the oomycete pathogen Albugo laibachii with uninfected controls. We found that infected plants exhibited reduced microbial diversity, a pattern driven primarily by site-dependent environmental factors rather than host genotypes. Microbial interaction networks of infected plants were less connected and highly modular, indicating a disruption in microbial community resilience. Using machine learning, we predicted the disease-associated and health-associated microbial signatures with 86–91% accuracy and identified key taxa correlated with disease outcomes. We selected bacteria, fungi, and cercozoa from these key taxa to test their biocontrol activeity against A. laibachii infection. We found all selected microbes exhibit various levels of plant protection, and disease-associated microbes offered less protection than health-associated microbes. We further validated the biocontrol capacity of the best candidate agent, Cystofilobasidium, by testing it within a synthetic community derived from the Arabidopsis core microbiome. This study reveals how microbial dynamics and functional connectivity support plant protection, providing a roadmap for using machine learning to devise robust biocontrol strategies that enhance crop resilience. Biological sciences/Microbiology/Microbial communities/Microbiome Biological sciences/Plant sciences/Plant ecology Biological sciences/Microbiology/Pathogens Microbe-microbe interaction biocontrol agent host genotype infected and uninfected leaves machine learning Full Text Additional Declarations There is NO Competing Interest. Supplementary Files SFig2sharedSelectedOTUs.pdf Supplementary figure S2 SuppTableS2SamplesSamplingLocations.xlsx Table S2 SFig4Plantweights.pdf Supplementary figure S4 SFig3MLselectedNetwork.pdf Supplementary figure S3 SuppTableS1adonisModels.xlsx Table S1 Sfig6SynCom.pdf Supplementary figure S6 SuppTable.S4SequenceOFStrains.xlsx Table S4 SuppTableS3BlastSelectedOTUs.xlsx Table S3 SupplementaryVideo1.mp4 Supplementary Video S1 SuppTable.S5Stainsgrowthconditions.pdf Table S5 SFig1composition.pdf Supplementary figure S1 Sfig5RhogostomaAlbugomicroscopy.pdf Supplementary figure S5 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-6130404","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":428051849,"identity":"35c72c4e-69af-4e2c-a720-4fd45488f0ff","order_by":0,"name":"Eric Kemen","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0002-7924-116X","institution":"Universität Tübingen","correspondingAuthor":true,"prefix":"","firstName":"Eric","middleName":"","lastName":"Kemen","suffix":""},{"id":428051850,"identity":"69ba74b4-2cbb-4ac9-aed6-87313a5fc2bc","order_by":1,"name":"Maryam Mahmoudi","email":"","orcid":"","institution":"Universität Tübingen","correspondingAuthor":false,"prefix":"","firstName":"Maryam","middleName":"","lastName":"Mahmoudi","suffix":""},{"id":428051851,"identity":"52536817-bd00-4745-ab18-9efddc089382","order_by":2,"name":"Yiheng Hu","email":"","orcid":"","institution":"Universität Tübingen","correspondingAuthor":false,"prefix":"","firstName":"Yiheng","middleName":"","lastName":"Hu","suffix":""},{"id":428051852,"identity":"72db78cd-6b63-4686-8242-a9b03f3e0a7b","order_by":3,"name":"Juliana Almario","email":"","orcid":"https://orcid.org/0000-0002-1475-7819","institution":"Université Lyon 1, CNRS","correspondingAuthor":false,"prefix":"","firstName":"Juliana","middleName":"","lastName":"Almario","suffix":""},{"id":428051853,"identity":"f6f1d685-5446-4d28-bb89-cb6b5ffd31fa","order_by":4,"name":"Paolo Stincone","email":"","orcid":"","institution":"University of Tuebingen","correspondingAuthor":false,"prefix":"","firstName":"Paolo","middleName":"","lastName":"Stincone","suffix":""},{"id":428051854,"identity":"2ce32d25-ac52-4625-b2f6-ab81dde74c94","order_by":5,"name":"Lynn-Marie Tenzer","email":"","orcid":"","institution":"Universität Tübingen","correspondingAuthor":false,"prefix":"","firstName":"Lynn-Marie","middleName":"","lastName":"Tenzer","suffix":""},{"id":428051855,"identity":"431cd313-fb4c-4358-a393-a9494c2f323b","order_by":6,"name":"Vasvi Chaudhry","email":"","orcid":"","institution":"Universität Tübingen","correspondingAuthor":false,"prefix":"","firstName":"Vasvi","middleName":"","lastName":"Chaudhry","suffix":""},{"id":428051856,"identity":"157f6081-a275-4723-bdd6-de0233d16f7a","order_by":7,"name":"Kay Nieselt","email":"","orcid":"https://orcid.org/0000-0002-1283-7065","institution":"University of Tuebingen","correspondingAuthor":false,"prefix":"","firstName":"Kay","middleName":"","lastName":"Nieselt","suffix":""}],"badges":[],"createdAt":"2025-02-28 16:56:34","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6130404/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6130404/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":78492058,"identity":"7e180d5c-e72a-4cce-aa6f-859001c511c7","added_by":"auto","created_at":"2025-03-14 02:53:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3726837,"visible":true,"origin":"","legend":"Article File","description":"","filename":"MSMLHealthInfectionv2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6130404/v1_covered_40384e39-5f40-4bf5-adab-92e56dc8e593.pdf"},{"id":78490567,"identity":"74273e23-ced6-4a50-a403-3aa58516381b","added_by":"auto","created_at":"2025-03-14 02:21:21","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":217327,"visible":true,"origin":"","legend":"Supplementary figure S2","description":"","filename":"SFig2sharedSelectedOTUs.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6130404/v1/c56a7963666cebf77bff1e1a.pdf"},{"id":78490558,"identity":"7a8e0f2b-8258-4010-ba2b-c1ba1ac58a35","added_by":"auto","created_at":"2025-03-14 02:21:21","extension":"xlsx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":10386,"visible":true,"origin":"","legend":"Table S2","description":"","filename":"SuppTableS2SamplesSamplingLocations.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-6130404/v1/0228d4dca2c5ca39bf8a9719.xlsx"},{"id":78490559,"identity":"20243ca0-420e-49c2-993b-d28416c7ee2a","added_by":"auto","created_at":"2025-03-14 02:21:21","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":28187,"visible":true,"origin":"","legend":"Supplementary figure S4","description":"","filename":"SFig4Plantweights.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6130404/v1/be85907b55d1808397daa8f9.pdf"},{"id":78490561,"identity":"89f2159a-de91-422f-a7b0-6f1fd1bd1194","added_by":"auto","created_at":"2025-03-14 02:21:21","extension":"pdf","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":915435,"visible":true,"origin":"","legend":"Supplementary figure S3","description":"","filename":"SFig3MLselectedNetwork.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6130404/v1/ef11ddb0d47384ca7876a59d.pdf"},{"id":78490867,"identity":"c8ad081c-06f1-4ae5-ae95-bfcf153ec8fb","added_by":"auto","created_at":"2025-03-14 02:29:21","extension":"xlsx","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":14413,"visible":true,"origin":"","legend":"Table S1","description":"","filename":"SuppTableS1adonisModels.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-6130404/v1/ec36eedcef4d57ae5b8c9e23.xlsx"},{"id":78490570,"identity":"a27ffaf2-26d3-4459-8f8c-d0ab1ed50dd2","added_by":"auto","created_at":"2025-03-14 02:21:21","extension":"pdf","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":197796,"visible":true,"origin":"","legend":"Supplementary figure S6","description":"","filename":"Sfig6SynCom.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6130404/v1/8b710b5498ac9233c4a6dc06.pdf"},{"id":78490564,"identity":"75f24067-f410-4b5e-aaa7-e20cee8b6502","added_by":"auto","created_at":"2025-03-14 02:21:21","extension":"xlsx","order_by":7,"title":"","display":"","copyAsset":false,"role":"supplement","size":23869,"visible":true,"origin":"","legend":"Table S4","description":"","filename":"SuppTable.S4SequenceOFStrains.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-6130404/v1/58b3b1d936c5d0be4b6b3b12.xlsx"},{"id":78491075,"identity":"1e9c2c58-e97e-4c5f-bc0c-63fca2cb2c12","added_by":"auto","created_at":"2025-03-14 02:37:21","extension":"xlsx","order_by":8,"title":"","display":"","copyAsset":false,"role":"supplement","size":38066,"visible":true,"origin":"","legend":"Table S3","description":"","filename":"SuppTableS3BlastSelectedOTUs.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-6130404/v1/1928b2ba1591233d76045ce0.xlsx"},{"id":78490583,"identity":"afbbe372-65ac-4ebe-a31f-d1f6487a3939","added_by":"auto","created_at":"2025-03-14 02:21:21","extension":"mp4","order_by":9,"title":"","display":"","copyAsset":false,"role":"supplement","size":5015038,"visible":true,"origin":"","legend":"Supplementary Video S1","description":"","filename":"SupplementaryVideo1.mp4","url":"https://assets-eu.researchsquare.com/files/rs-6130404/v1/d085ffa7083fa39c158da3b5.mp4"},{"id":78490582,"identity":"99d9eab8-cb4c-4436-b345-4fa86cfcebdf","added_by":"auto","created_at":"2025-03-14 02:21:21","extension":"pdf","order_by":10,"title":"","display":"","copyAsset":false,"role":"supplement","size":3105877,"visible":true,"origin":"","legend":"Table S5","description":"","filename":"SuppTable.S5Stainsgrowthconditions.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6130404/v1/ba81bdb196f9f1f062a74a9e.pdf"},{"id":78491535,"identity":"b7666ee8-f3ef-443f-a797-c895665807f0","added_by":"auto","created_at":"2025-03-14 02:45:21","extension":"pdf","order_by":11,"title":"","display":"","copyAsset":false,"role":"supplement","size":23150,"visible":true,"origin":"","legend":"Supplementary figure S1","description":"","filename":"SFig1composition.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6130404/v1/465b5e22e561661cb523c91a.pdf"},{"id":78490876,"identity":"3f78a7d5-a4c9-4e45-97b5-e7a80937c2a8","added_by":"auto","created_at":"2025-03-14 02:29:21","extension":"pdf","order_by":12,"title":"","display":"","copyAsset":false,"role":"supplement","size":171109,"visible":true,"origin":"","legend":"Supplementary figure S5","description":"","filename":"Sfig5RhogostomaAlbugomicroscopy.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6130404/v1/6053074a64feb22a9558381b.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Machine Learning Reveals Biocontrol Agents Shaping Disease Protection in Natural Arabidopsis Populations and Synthetic Communities","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":"Microbe-microbe interaction, biocontrol agent, host genotype, infected and uninfected leaves, machine learning","lastPublishedDoi":"10.21203/rs.3.rs-6130404/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6130404/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Plants recruit beneficial microbes to defend against phytopathogens, and some are developed as biocontrol agents. However, identifying biocontrol agents depends on empirical screenings to assess microbial activity against pathogens of interest. In this study, we explored the association between infection status and phyllosphere microbiome dynamics over six generations from natural Arabidopsis populations and compared plants infected by the oomycete pathogen Albugo laibachii with uninfected controls. We found that infected plants exhibited reduced microbial diversity, a pattern driven primarily by site-dependent environmental factors rather than host genotypes. Microbial interaction networks of infected plants were less connected and highly modular, indicating a disruption in microbial community resilience. Using machine learning, we predicted the disease-associated and health-associated microbial signatures with 86–91% accuracy and identified key taxa correlated with disease outcomes. We selected bacteria, fungi, and cercozoa from these key taxa to test their biocontrol activeity against A. laibachii infection. We found all selected microbes exhibit various levels of plant protection, and disease-associated microbes offered less protection than health-associated microbes. We further validated the biocontrol capacity of the best candidate agent, Cystofilobasidium, by testing it within a synthetic community derived from the Arabidopsis core microbiome. This study reveals how microbial dynamics and functional connectivity support plant protection, providing a roadmap for using machine learning to devise robust biocontrol strategies that enhance crop resilience.","manuscriptTitle":"Machine Learning Reveals Biocontrol Agents Shaping Disease Protection in Natural Arabidopsis Populations and Synthetic Communities","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-14 02:21:16","doi":"10.21203/rs.3.rs-6130404/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"f4366b9b-4eeb-4e3e-9c2f-4d07e22a18c8","owner":[],"postedDate":"March 14th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":45607052,"name":"Biological sciences/Microbiology/Microbial communities/Microbiome"},{"id":45607053,"name":"Biological sciences/Plant sciences/Plant ecology"},{"id":45607054,"name":"Biological sciences/Microbiology/Pathogens"}],"tags":[],"updatedAt":"2026-03-24T19:20:24+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-14 02:21:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6130404","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6130404","identity":"rs-6130404","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}