Fast Whole-Genome Phylogeny by Compression: the COVID-19 case | 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 Research Article Fast Whole-Genome Phylogeny by Compression: the COVID-19 case Rudi L. Cilibrasi, Paul M.B. Vitanyi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-851224/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract We analyze the whole-genome phylogeny and taxonomy of the SARS-CoV-2 virus, causing the COVID-19 disease, using compres- sion in the form of the alignment-free NCD (Normalized Compression Distance) method to assess similarity. We compare the SARS-CoV-2 virus with a database of over 6,500 viruses. The results comprise that the SARS- CoV-2 virus is closest in that database to the RaTG13 virus and rather close to the bat SARS-like corona viruses bat-SL-CoVZXC21 and bat-SL- CoVZC45. Over 6,500 viruses are identified (given by their registration code) with larger NCD’s. The NCD’s are compared with the NCD’s between the mtDNA’s of familiar species. We treat the question whether Pangolins are involved in the SARS-CoV-2 virus. The NCD method or shortly the compression method is simpler and possibly faster than any other whole-genome method, which makes it the ideal tool to explore phylogeny. Here we use it for the complex case of determining this similarity between the COVID-19 virus SARS-CoV-2 and many other viruses. The resulting phylogeny and taxonomy closely matches earlier efforts by alignment-based methods and a machine-learning method, providing the most compelling evidence to date for the compression method showing that one can achieve equivalent results both simply and fast. Computational Biology Bioinformatics Medical Genetics Compression Phylogeny Covid-19 virus Full Text Additional Declarations No competing interests reported. Supplementary Files si.pdf Cite Share Download PDF Status: Posted 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-851224","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":48901894,"identity":"52c0aa91-b00d-4bba-aaca-29f4b55cc7b2","order_by":0,"name":"Rudi L. Cilibrasi","email":"","orcid":"","institution":"Centrum Wiskunde \u0026 Informatica","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Rudi","middleName":"L.","lastName":"Cilibrasi","suffix":""},{"id":48901895,"identity":"fede9cf6-eec3-4cc1-84fb-d64a430c3387","order_by":1,"name":"Paul M.B. Vitanyi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAl0lEQVRIiWNgGAWjYHACxgMMFQwMbGAGseAAwxmwFgYStDC2wfQSA8zZzxgc5p1nl9jHwHuAOC2WPTlALduSE9sY+BKI02JwIMfg4MxtB3LbGHgMiNRy/g1QyxyStNzIMTjwsYEULZYznhUc+HAsub6NmVgt5vzJGx8k1NgZy7f3GD4gzmFwFjNR6lG0jIJRMApGwSjABQBgOzHbf89oSQAAAABJRU5ErkJggg==","orcid":"","institution":"Centrum Wiskunde \u0026 Informatica","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Paul","middleName":"M.B.","lastName":"Vitanyi","suffix":""}],"badges":[],"createdAt":"2021-08-27 16:59:02","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-851224/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-851224/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":13673906,"identity":"798af9bf-6cf9-4164-8e69-ff839b9e2232","added_by":"auto","created_at":"2021-09-17 11:19:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":390908,"visible":true,"origin":"","legend":"","description":"","filename":"phylo.pdf","url":"https://assets-eu.researchsquare.com/files/rs-851224/v1_covered.pdf"},{"id":12901019,"identity":"ba02af3e-5292-4eea-942a-984de29bfe8d","added_by":"auto","created_at":"2021-08-30 17:14:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":387400,"visible":true,"origin":"","legend":"","description":"","filename":"phylo.pdf","url":"https://assets-eu.researchsquare.com/files/rs-851224/v1_covered.pdf"},{"id":12901018,"identity":"9bd86f7d-457e-4802-bf6a-18c48bee5750","added_by":"auto","created_at":"2021-08-30 17:13:56","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":313687,"visible":true,"origin":"","legend":"","description":"","filename":"si.pdf","url":"https://assets-eu.researchsquare.com/files/rs-851224/v1/a2b96fce67e539887d620857.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Fast Whole-Genome Phylogeny by Compression: the COVID-19 case","fulltext":[{"header":"Full Text","content":"This preprint is available for \u003ca href='/article/rs-851224/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e."}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"
[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Compression, Phylogeny, Covid-19 virus","lastPublishedDoi":"10.21203/rs.3.rs-851224/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-851224/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eWe analyze the whole-genome phylogeny and taxonomy of the SARS-CoV-2 virus, causing the COVID-19 disease, using compres- sion in the form of the alignment-free NCD (Normalized Compression Distance) method to assess similarity. We compare the SARS-CoV-2 virus with a database of over 6,500 viruses. The results comprise that the SARS- CoV-2 virus is closest in that database to the RaTG13 virus and rather close to the bat SARS-like corona viruses bat-SL-CoVZXC21 and bat-SL- CoVZC45. Over 6,500 viruses are identified (given by their registration code) with larger NCD’s. The NCD’s are compared with the NCD’s between the mtDNA’s of familiar species. We treat the question whether Pangolins are involved in the SARS-CoV-2 virus. The NCD method or shortly the compression method is simpler and possibly faster than any other whole-genome method, which makes it the ideal tool to explore phylogeny. Here we use it for the complex case of determining this similarity between the COVID-19 virus SARS-CoV-2 and many other viruses. The resulting phylogeny and taxonomy closely matches earlier efforts by alignment-based methods and a machine-learning method, providing the most compelling evidence to date for the compression method showing that one can achieve equivalent results both simply and fast. \u003c/p\u003e","manuscriptTitle":"Fast Whole-Genome Phylogeny by Compression: the COVID-19 case","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2021-08-30 17:13:55","doi":"10.21203/rs.3.rs-851224/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"
[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"8461c0c6-7c76-4e1f-97ce-b5f62623eb23","owner":[],"postedDate":"August 30th, 2021","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":6824891,"name":"Computational Biology"},{"id":6824892,"name":"Bioinformatics"},{"id":6824893,"name":"Medical Genetics"}],"tags":[],"updatedAt":"2021-10-07T04:14:07+00:00","versionOfRecord":[],"versionCreatedAt":"2021-08-30 17:13:55","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-851224","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-851224","identity":"rs-851224","version":["v1"]},"buildId":"cBFmMYwuxLRRLfASyISRj","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.