VITAP: A High Precision Tool for DNA and RNA Viral Classification Based On Meta-omic Data

VITAP: A High Precision Tool for DNA and RNA Viral Classification Based On Meta-omic Data | 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 VITAP: A High Precision Tool for DNA and RNA Viral Classification Based On Meta-omic Data Min Wang, Kaiyang Zheng, Jianhua Sun, Yantao Liang, David Paez-Espino, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4406120/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 05 Mar, 2025 Read the published version in Nature Communications → Version 1 posted You are reading this latest preprint version Abstract The rapid growth in the number of newly identified DNA and RNA viral sequences underscores the urgent need for an accurate and comprehensive classification system for all viral realms at different levels. Here, a new Viral Taxonomic Assignment Pipeline (VITAP) is established, which addresses these challenges by integrating alignment-based techniques with graph, offering high precision in classifying both DNA and RNA viral sequences and providing confidence scores for each taxonomic unit. This tool automatically updates its database in sync with the latest references from the International Committee on Taxonomy of Viruses (ICTV), efficiently classifying viral sequences as short as 1000 base pairs to genus level. VITAP's performance surpasses existing methods in accuracy, precision and recall across all DNA and RNA viral phyla. Its application in deep-sea viromes has led to significant taxonomic updates, providing more comprehensive diversity information of viruses from deep-sea. The VITAP is available at https://github.com/DrKaiyangZheng/VITAP . Biological sciences/Computational biology and bioinformatics/Sequence annotation Biological sciences/Computational biology and bioinformatics/Software Full Text Additional Declarations There is NO Competing Interest. Supplementary Files TableS1.txt Supplementary table 1 TableS2.txt Supplementary table 2 TableS3.txt Supplementary table 3 TableS4.txt Supplementary table 4 TableS5.txt Supplementary table 5 TableS6.txt Supplementary table 6 TableS7.txt Supplementary table 7 TableS8.tsv Supplementary table 8 TableS9.tsv Supplementary table 9 manuscript240511sm.pdf Cite Share Download PDF Status: Published Journal Publication published 05 Mar, 2025 Read the published version in Nature Communications → 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-4406120","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":302579555,"identity":"202ae3a7-5afc-4e32-a742-6d088ff9afa1","order_by":0,"name":"Min Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzklEQVRIiWNgGAWjYDACZijNj8olRotkA9FaYMDgALFadNt5D7/mqbljt/l4j+EHhgrrxAb2swfwajE7zJdmzXPsWfK2M2eMJRjOpCc28OQlENDCY2acw3Y42exGjhkDY9vhxAYJHgMitPw7nGw8A6TlH3FajB/nth22M5AAaWkg0hbmv32HEyTOHCuWSDiWbtzGk0NAy/kzxh9nfDtsz9/evPHDhxpr2X72M/i1AAGbBJBIbAAxE0BcQuqBgPkDkLAnQuEoGAWjYBSMVAAA29tDlnMc1m0AAAAASUVORK5CYII=","orcid":"","institution":"Ocean university of China","correspondingAuthor":true,"prefix":"","firstName":"Min","middleName":"","lastName":"Wang","suffix":""},{"id":302579556,"identity":"25793b6a-46c2-4aa7-b61d-0f7559e0f167","order_by":1,"name":"Kaiyang Zheng","email":"","orcid":"","institution":"Ocean university of China","correspondingAuthor":false,"prefix":"","firstName":"Kaiyang","middleName":"","lastName":"Zheng","suffix":""},{"id":302579557,"identity":"2e24e55d-6e25-4cd1-bc04-dc96724ad3f3","order_by":2,"name":"Jianhua Sun","email":"","orcid":"","institution":"Ocean university of China","correspondingAuthor":false,"prefix":"","firstName":"Jianhua","middleName":"","lastName":"Sun","suffix":""},{"id":302579558,"identity":"d9d9da55-7f26-4916-9f36-8ba34c6ddae2","order_by":3,"name":"Yantao Liang","email":"","orcid":"","institution":"Ocean university of China","correspondingAuthor":false,"prefix":"","firstName":"Yantao","middleName":"","lastName":"Liang","suffix":""},{"id":302579559,"identity":"e817b123-2c89-4ddb-822f-79018bd2bb43","order_by":4,"name":"David Paez-Espino","email":"","orcid":"https://orcid.org/0000-0002-2939-5398","institution":"Mammoth Biosciences","correspondingAuthor":false,"prefix":"","firstName":"David","middleName":"","lastName":"Paez-Espino","suffix":""},{"id":302579560,"identity":"b3837ead-122e-4bf7-a507-5ab37ba22baa","order_by":5,"name":"Andrew Mcminn","email":"","orcid":"","institution":"University of Tasmania","correspondingAuthor":false,"prefix":"","firstName":"Andrew","middleName":"","lastName":"Mcminn","suffix":""}],"badges":[],"createdAt":"2024-05-11 16:20:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4406120/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4406120/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41467-025-57500-7","type":"published","date":"2025-03-05T05:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":77857106,"identity":"5dfb84f6-9889-49af-9063-6508b74ca065","added_by":"auto","created_at":"2025-03-06 08:05:58","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1382107,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript240511main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4406120/v1_covered_d3bb5b97-e712-4599-80ce-1a91be906515.pdf"},{"id":57386340,"identity":"8fba030e-3c26-4924-a25e-2ed885599adc","added_by":"auto","created_at":"2024-05-30 03:57:00","extension":"txt","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":7871,"visible":true,"origin":"","legend":"Supplementary table 1","description":"","filename":"TableS1.txt","url":"https://assets-eu.researchsquare.com/files/rs-4406120/v1/d60e2bef4fb4822cfbde42ba.txt"},{"id":57386341,"identity":"ee9419b2-35a3-4716-9c12-73dca748468f","added_by":"auto","created_at":"2024-05-30 03:57:00","extension":"txt","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":5208,"visible":true,"origin":"","legend":"Supplementary table 2","description":"","filename":"TableS2.txt","url":"https://assets-eu.researchsquare.com/files/rs-4406120/v1/cfe811ca9012838900e6ff07.txt"},{"id":57386342,"identity":"d04fa914-b6f8-47c3-913e-2306cbc3d298","added_by":"auto","created_at":"2024-05-30 03:57:00","extension":"txt","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":6377,"visible":true,"origin":"","legend":"Supplementary table 3","description":"","filename":"TableS3.txt","url":"https://assets-eu.researchsquare.com/files/rs-4406120/v1/d8acdfcb4b17caa0c17e1661.txt"},{"id":57386343,"identity":"9592a402-c4dc-4abf-878b-713ba932578a","added_by":"auto","created_at":"2024-05-30 03:57:00","extension":"txt","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":3968217,"visible":true,"origin":"","legend":"Supplementary table 4","description":"","filename":"TableS4.txt","url":"https://assets-eu.researchsquare.com/files/rs-4406120/v1/653775d69034ffa36969989a.txt"},{"id":57386752,"identity":"cdba4e05-b43e-4e59-9dd5-aea73e0360cc","added_by":"auto","created_at":"2024-05-30 04:05:00","extension":"txt","order_by":5,"title":"","display":"","copyAsset":false,"role":"supplement","size":3825,"visible":true,"origin":"","legend":"Supplementary table 5","description":"","filename":"TableS5.txt","url":"https://assets-eu.researchsquare.com/files/rs-4406120/v1/f03f83321c35cc6ac68453f9.txt"},{"id":57386347,"identity":"1cdcc51c-99cd-4756-93bd-4f9463243cf7","added_by":"auto","created_at":"2024-05-30 03:57:01","extension":"txt","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":219459,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary table 6\u003c/p\u003e","description":"","filename":"TableS6.txt","url":"https://assets-eu.researchsquare.com/files/rs-4406120/v1/a5a64514277ff2a7506a8cb6.txt"},{"id":57386345,"identity":"3e45b50f-79ab-4745-b200-9f68debaf6d3","added_by":"auto","created_at":"2024-05-30 03:57:01","extension":"txt","order_by":7,"title":"","display":"","copyAsset":false,"role":"supplement","size":4062791,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary table 7\u003c/p\u003e","description":"","filename":"TableS7.txt","url":"https://assets-eu.researchsquare.com/files/rs-4406120/v1/dc48b5a4fd22f7625b2d2bc2.txt"},{"id":57386349,"identity":"d9fba82a-308e-4b91-bc81-eae66a106dc6","added_by":"auto","created_at":"2024-05-30 03:57:01","extension":"tsv","order_by":8,"title":"","display":"","copyAsset":false,"role":"supplement","size":266146,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary table 8\u003c/p\u003e","description":"","filename":"TableS8.tsv","url":"https://assets-eu.researchsquare.com/files/rs-4406120/v1/8ee4a44590854bf27a6b7bd2.tsv"},{"id":57386346,"identity":"17c6ccac-73a4-4b92-bdbc-06e325703d66","added_by":"auto","created_at":"2024-05-30 03:57:01","extension":"tsv","order_by":9,"title":"","display":"","copyAsset":false,"role":"supplement","size":3574191,"visible":true,"origin":"","legend":"\u003cp\u003eSupplementary table 9\u003c/p\u003e","description":"","filename":"TableS9.tsv","url":"https://assets-eu.researchsquare.com/files/rs-4406120/v1/cdc185f6ae9a2ac15e8b4bf9.tsv"},{"id":57386348,"identity":"2fb19ae8-27af-45ad-a2e8-e574c970448f","added_by":"auto","created_at":"2024-05-30 03:57:01","extension":"pdf","order_by":10,"title":"","display":"","copyAsset":false,"role":"supplement","size":1822640,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cbr\u003e\u003c/p\u003e","description":"","filename":"manuscript240511sm.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4406120/v1/beacea998950f62256e294da.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"VITAP: A High Precision Tool for DNA and RNA Viral Classification Based On Meta-omic Data","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":"","lastPublishedDoi":"10.21203/rs.3.rs-4406120/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4406120/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The rapid growth in the number of newly identified DNA and RNA viral sequences underscores the urgent need for an accurate and comprehensive classification system for all viral realms at different levels. Here, a new Viral Taxonomic Assignment Pipeline (VITAP) is established, which addresses these challenges by integrating alignment-based techniques with graph, offering high precision in classifying both DNA and RNA viral sequences and providing confidence scores for each taxonomic unit. This tool automatically updates its database in sync with the latest references from the International Committee on Taxonomy of Viruses (ICTV), efficiently classifying viral sequences as short as 1000 base pairs to genus level. VITAP's performance surpasses existing methods in accuracy, precision and recall across all DNA and RNA viral phyla. Its application in deep-sea viromes has led to significant taxonomic updates, providing more comprehensive diversity information of viruses from deep-sea. The VITAP is available at https://github.com/DrKaiyangZheng/VITAP.","manuscriptTitle":"VITAP: A High Precision Tool for DNA and RNA Viral Classification Based On Meta-omic Data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-05-30 03:56:56","doi":"10.21203/rs.3.rs-4406120/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":"31b8b6de-8579-44da-839b-b9f0ad4ae40c","owner":[],"postedDate":"May 30th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":31926374,"name":"Biological sciences/Computational biology and bioinformatics/Sequence annotation"},{"id":31926375,"name":"Biological sciences/Computational biology and bioinformatics/Software"}],"tags":[],"updatedAt":"2025-03-06T08:05:49+00:00","versionOfRecord":{"articleIdentity":"rs-4406120","link":"https://doi.org/10.1038/s41467-025-57500-7","journal":{"identity":"nature-communications","isVorOnly":false,"title":"Nature Communications"},"publishedOn":"2025-03-05 05:00:00","publishedOnDateReadable":"March 5th, 2025"},"versionCreatedAt":"2024-05-30 03:56:56","video":"","vorDoi":"10.1038/s41467-025-57500-7","vorDoiUrl":"https://doi.org/10.1038/s41467-025-57500-7","workflowStages":[]},"version":"v1","identity":"rs-4406120","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4406120","identity":"rs-4406120","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}