Interpretable machine learning reveals a diverse arsenal of anti-defenses in 1 bacterial viruses

Interpretable machine learning reveals a diverse arsenal of anti-defenses in 1 bacterial viruses | 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 Biological Sciences - Article Interpretable machine learning reveals a diverse arsenal of anti-defenses in 1 bacterial viruses Martin Polz, Anna Lopatina, Mariusz Ferenc, Nina Bartlau, Michael Wolfram, and 6 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4571006/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 Antagonistic interactions with viruses are an important driver of the ecology and evolution of bacteria, and associating genetic signatures to these interactions is of fundamental importance to predict viral infection success. Recent studies have highlighted that bacteria possess a large, rapidly changing arsenal of defense genes and that viruses can neutralize at least some of these genes with matching anti-defenses. However, a broadly applicable approach for discovering the genetic underpinnings of such interactions is missing since typically used methods such as comparative genomics are limited by the rampant horizontal gene transfer and poor annotation of viral and bacterial genes. Here we show that genes that allow the viruses to overcome bacterial defenses can be systematically identified using an interpretable machine-learning approach even when using diverse bacteria-virus infection data. To verify the predictions, we experimentally characterized eight previously unknown anti-defense proteins in viruses specific for Vibrio bacteria and showed that they counteract a wide range of bacterial immune systems, including AbiH, AbiU, Septu, DRT, CBASS, and Retron. The power of our computational approach is highlighted by the identification of anti-defense proteins that inhibit non-homologous defense systems, which we verify for Retron and AbiH. We suggest that the computational prediction based on experimental interactions offers a promising avenue to unravel the genetic mechanisms of co-evolution between bacteria and their viruses. Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Microbiology/Phage biology Biological sciences/Microbiology/Microbial genetics/Bacterial genetics Biological sciences/Ecology/Microbial ecology Full Text Additional Declarations There is NO Competing Interest. Supplementary Files SupplementaryData1.xlsx Dataset 1 SupplementaryData2.xlsx Dataset 2 SupplementaryData3.xlsx Dataset 3 SupplementaryData4.xlsx Dataset 4 SupplementaryData5.xlsx Dataset 5 SupplementaryData6.xlsx Dataset 6 SupplementaryData7.xlsx Dataset 7 SupplementaryFiguresandTables.pdf Extended Data 1 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-4571006","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Biological Sciences - Article","associatedPublications":[],"authors":[{"id":327387629,"identity":"194aaeae-dcb6-458d-9877-c68cd961bb0e","order_by":0,"name":"Martin Polz","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDElEQVRIie3PP0sDMRzG8SfLdTm89Vcq9RUId0sXpa/lwsF1ERcXhyIpB+nm7CD2XRTHhINMJ66OvaWudZF2EdMrhRsudXXIdwkh+eQP4PP911IgsgNTuAcCMPEXYMKS/n6bQtUmwQmCI2GyveAgl/O3z1X9CsKgUHr3Ut6eUTZbYTpGtOh+4KiaJIJXlpybVPWX5V1AvIhhMpDpvmWkcia4xAPoJlbJsuQy1JIQKMBF3tcNoYbw54bMt/hRuHCRj7xFtLCkN5NgUiF2kjV74pIosH/Rwkz2pCD+mIWJSR0Py/G1k9cUDQpdb6dXfFH06s3mezwclqr7mkP2v9Se2/PDU/uPyufz+Xzd/QLSYl4K1qbjMwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0001-9296-3733","institution":"University of Vienna","correspondingAuthor":true,"prefix":"","firstName":"Martin","middleName":"","lastName":"Polz","suffix":""},{"id":327387630,"identity":"44dc0daf-dae7-44b3-a55e-e03b9a65e622","order_by":1,"name":"Anna Lopatina","email":"","orcid":"https://orcid.org/0000-0002-3484-6819","institution":"University of Vienna","correspondingAuthor":false,"prefix":"","firstName":"Anna","middleName":"","lastName":"Lopatina","suffix":""},{"id":327387631,"identity":"a900b14b-bf94-432f-bc20-3fd735859734","order_by":2,"name":"Mariusz Ferenc","email":"","orcid":"","institution":"Institute of Biocybernetics and Biomedical Engineering","correspondingAuthor":false,"prefix":"","firstName":"Mariusz","middleName":"","lastName":"Ferenc","suffix":""},{"id":327387632,"identity":"3bcea9d5-b0cf-4f6f-b744-0d6c18b3a79d","order_by":3,"name":"Nina Bartlau","email":"","orcid":"https://orcid.org/0000-0002-7803-5444","institution":"University of Vienna","correspondingAuthor":false,"prefix":"","firstName":"Nina","middleName":"","lastName":"Bartlau","suffix":""},{"id":327387633,"identity":"40d209b7-ff8d-4744-b368-0d757ee9ea4f","order_by":4,"name":"Michael Wolfram","email":"","orcid":"","institution":"University of Vienna","correspondingAuthor":false,"prefix":"","firstName":"Michael","middleName":"","lastName":"Wolfram","suffix":""},{"id":327387634,"identity":"bbaacc79-a935-4ee1-822a-7bab9f12607d","order_by":5,"name":"Kerrin Steensen","email":"","orcid":"","institution":"University of Vienna","correspondingAuthor":false,"prefix":"","firstName":"Kerrin","middleName":"","lastName":"Steensen","suffix":""},{"id":327387635,"identity":"add57be1-69e2-4320-b813-5cd198a77a4c","order_by":6,"name":"Sebastiano Muscia","email":"","orcid":"","institution":"University of Vienna","correspondingAuthor":false,"prefix":"","firstName":"Sebastiano","middleName":"","lastName":"Muscia","suffix":""},{"id":327387636,"identity":"24a6162c-df17-469c-a635-ac7ab4a1bbca","order_by":7,"name":"Fatima Hussain","email":"","orcid":"","institution":"Massachusetts Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Fatima","middleName":"","lastName":"Hussain","suffix":""},{"id":327387637,"identity":"a92736fc-1077-47bc-9342-783753400fef","order_by":8,"name":"Madeleine Schnurer","email":"","orcid":"https://orcid.org/0000-0001-6657-0215","institution":"University of Vienna","correspondingAuthor":false,"prefix":"","firstName":"Madeleine","middleName":"","lastName":"Schnurer","suffix":""},{"id":327387638,"identity":"358f21da-0c95-43bc-8b09-73cf4f313852","order_by":9,"name":"Leila Afjehi","email":"","orcid":"","institution":"University of Vienna/UZA II/2F243","correspondingAuthor":false,"prefix":"","firstName":"Leila","middleName":"","lastName":"Afjehi","suffix":""},{"id":327387639,"identity":"0cda3297-4fa0-49c6-a5ef-587475de0701","order_by":10,"name":"Shaul Pollak","email":"","orcid":"https://orcid.org/0000-0002-8976-5944","institution":"University of Vienna","correspondingAuthor":false,"prefix":"","firstName":"Shaul","middleName":"","lastName":"Pollak","suffix":""}],"badges":[],"createdAt":"2024-06-12 14:35:47","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4571006/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4571006/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":60464419,"identity":"e7bad550-8fc8-44aa-becf-c561faea1a84","added_by":"auto","created_at":"2024-07-17 04:43:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":856953,"visible":true,"origin":"","legend":"Article File","description":"","filename":"Interpretablemachinelearningrevealsadiversearsenalofantidefensesinbacterialviruses.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4571006/v1_covered_a15ac5c5-faea-4952-9feb-a8add41503b5.pdf"},{"id":60463492,"identity":"b4ba7aa3-d105-4c48-98d5-d205655c4696","added_by":"auto","created_at":"2024-07-17 04:27:39","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":278046,"visible":true,"origin":"","legend":"Dataset 1","description":"","filename":"SupplementaryData1.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-4571006/v1/b7b18b0a660b037938c8d0cb.xlsx"},{"id":60463493,"identity":"1a7e7bfc-1109-46f0-9447-e13c9ce7ac20","added_by":"auto","created_at":"2024-07-17 04:27:39","extension":"xlsx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":141507,"visible":true,"origin":"","legend":"\u003cp\u003eDataset 2\u003c/p\u003e","description":"","filename":"SupplementaryData2.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-4571006/v1/17b972fbf517c3fcf9752a0d.xlsx"},{"id":60463904,"identity":"4e929e46-31d5-484d-b502-70cfb4ca44d1","added_by":"auto","created_at":"2024-07-17 04:35:39","extension":"xlsx","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":15080,"visible":true,"origin":"","legend":"\u003cp\u003eDataset 3\u003c/p\u003e","description":"","filename":"SupplementaryData3.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-4571006/v1/6d5a065f12ce97ebb9ff400e.xlsx"},{"id":60463490,"identity":"9748fd72-52c3-498d-8e37-7a38fb38ee96","added_by":"auto","created_at":"2024-07-17 04:27:39","extension":"xlsx","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":351068,"visible":true,"origin":"","legend":"Dataset 4","description":"","filename":"SupplementaryData4.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-4571006/v1/7748d42b0b52cdd1986076d5.xlsx"},{"id":60463496,"identity":"abd2bce9-5a3d-490c-837c-48823bb00907","added_by":"auto","created_at":"2024-07-17 04:27:39","extension":"xlsx","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":24425,"visible":true,"origin":"","legend":"Dataset 5","description":"","filename":"SupplementaryData5.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-4571006/v1/17e1a9adf5e6ce2fdc0d6d03.xlsx"},{"id":60463905,"identity":"a4c79c6e-9628-4f8a-88c0-376318303656","added_by":"auto","created_at":"2024-07-17 04:35:39","extension":"xlsx","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":33043,"visible":true,"origin":"","legend":"Dataset 6","description":"","filename":"SupplementaryData6.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-4571006/v1/7f021343f5baf12d7f3def16.xlsx"},{"id":60463495,"identity":"f7693466-7125-4da8-9cd8-b6e147cf7194","added_by":"auto","created_at":"2024-07-17 04:27:39","extension":"xlsx","order_by":7,"title":"","display":"","copyAsset":false,"role":"supplement","size":58629,"visible":true,"origin":"","legend":"Dataset 7","description":"","filename":"SupplementaryData7.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-4571006/v1/edff7e92d9831dbb7e5a7b37.xlsx"},{"id":60463497,"identity":"330b7336-8004-41ea-94f6-7bf218e0440a","added_by":"auto","created_at":"2024-07-17 04:27:39","extension":"pdf","order_by":8,"title":"","display":"","copyAsset":false,"role":"supplement","size":3076078,"visible":true,"origin":"","legend":"Extended Data 1","description":"","filename":"SupplementaryFiguresandTables.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4571006/v1/c917516d358e69c65f275899.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Interpretable machine learning reveals a diverse arsenal of anti-defenses in 1 bacterial viruses","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":"","lastPublishedDoi":"10.21203/rs.3.rs-4571006/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4571006/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Antagonistic interactions with viruses are an important driver of the ecology and evolution of bacteria, and associating genetic signatures to these interactions is of fundamental importance to predict viral infection success. Recent studies have highlighted that bacteria possess a large, rapidly changing arsenal of defense genes and that viruses can neutralize at least some of these genes with matching anti-defenses. However, a broadly applicable approach for discovering the genetic underpinnings of such interactions is missing since typically used methods such as comparative genomics are limited by the rampant horizontal gene transfer and poor annotation of viral and bacterial genes. Here we show that genes that allow the viruses to overcome bacterial defenses can be systematically identified using an interpretable machine-learning approach even when using diverse bacteria-virus infection data. To verify the predictions, we experimentally characterized eight previously unknown anti-defense proteins in viruses specific for Vibrio bacteria and showed that they counteract a wide range of bacterial immune systems, including AbiH, AbiU, Septu, DRT, CBASS, and Retron. The power of our computational approach is highlighted by the identification of anti-defense proteins that inhibit non-homologous defense systems, which we verify for Retron and AbiH. We suggest that the computational prediction based on experimental interactions offers a promising avenue to unravel the genetic mechanisms of co-evolution between bacteria and their viruses.","manuscriptTitle":"Interpretable machine learning reveals a diverse arsenal of anti-defenses in 1 bacterial viruses","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-17 04:27:34","doi":"10.21203/rs.3.rs-4571006/v1","editorialEvents":[],"status":"published","journal":{"display":false,"email":"[email protected]","identity":"nature","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"nature","sideBox":"Learn more about [Nature](http://www.nature.com/nature/)","snPcode":"","submissionUrl":"","title":"Nature","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"93478c71-c8d1-4728-b70c-d60e90845c24","owner":[],"postedDate":"July 17th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":34647264,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":34647265,"name":"Biological sciences/Microbiology/Phage biology"},{"id":34647266,"name":"Biological sciences/Microbiology/Microbial genetics/Bacterial genetics"},{"id":34647267,"name":"Biological sciences/Ecology/Microbial ecology"}],"tags":[],"updatedAt":"2024-08-23T18:50:22+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-17 04:27:34","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4571006","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4571006","identity":"rs-4571006","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}