Y-mer: A k-mer based method for determining human Y chromosome haplogroups from ultra-low sequencing depth data

Y-mer: A k-mer based method for determining human Y chromosome haplogroups from ultra-low sequencing depth 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 Method Article Y-mer: A k-mer based method for determining human Y chromosome haplogroups from ultra-low sequencing depth data Tarmo Puurand, Märt Möls, Lauris Kaplinski, Kadri Maal, Kaarel Krjutskov, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5042960/v2 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 12 Aug, 2025 Read the published version in Genome Biology → Version 2 posted 10 You are reading this latest preprint version Show more versions Abstract Determining genetic ancestry of an individual is challenging from poorly preserved or mixed samples that permit only ultra-low coverage sequence (ulcWGS) depth < 0.1x to be gained at target loci. Leveraging the recent advances in telomere-to-telomere sequencing of the whole genomes with long reads we develop a new k-mer based method Y-mer and show how information from hundreds of thousands of k-mers in distance-based models enables accurate inference of chrY haplogroup from WGS sequence at depth less than 0.01x without additional PCR or capture. We test the performance of Y-mer on ancient DNA and prenatal screening data showing its potential for genetic ancestry inference for cell-free, forensic and ancient DNA research from short read WGS data. aDNA ulcWGS NIPS NIPT k-mer human chrY haplogroups prediction Full Text Additional Declarations No competing interests reported. Supplementary Files Ymer240823Model.pdf Ymerrevisedsuppltables070525.xlsx YmerSIrevised070525.docx Cite Share Download PDF Status: Published Journal Publication published 12 Aug, 2025 Read the published version in Genome Biology → Version 2 posted Editorial decision: Revision requested 20 Jun, 2025 Reviews received at journal 11 Jun, 2025 Reviews received at journal 10 Jun, 2025 Reviews received at journal 02 Jun, 2025 Reviewers agreed at journal 18 May, 2025 Reviewers agreed at journal 16 May, 2025 Reviewers agreed at journal 13 May, 2025 Reviewers invited by journal 13 May, 2025 Submission checks completed at journal 13 May, 2025 First submitted to journal 12 May, 2025 You are reading this latest preprint version Show more versions 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-5042960","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Method Article","associatedPublications":[],"authors":[{"id":472134088,"identity":"25aaf0f4-4ad8-11f0-91e4-06cc9d20a69f","order_by":0,"name":"Tarmo Puurand","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzklEQVRIiWNgGAWjYNADngpiFKHyzjBIkKiFt40ILfbsZ59u+MBwJ3HD7cPPHrydd7iOgb35AH5beNLNbs5geJa44VyaueHcbYclGHiOJRBwWBrbbR6Gw4kbzjCYSfOCtEjkGODXwv8MpoX9mzTvHKAW+fcf8GuRgNvCA7SlAWQLD14dDDw3nrHdnGHwzHjmGZ4yyTnH0iXbeNLwO4y9P43txoeKO7J9Z9i3SbypsebnZz/8AL81YGBwAMFmI0I9CBwgqGIUjIJRMApGMAAAejFDOQOUll8AAAAASUVORK5CYII=","orcid":"","institution":"Institute of Molecular and Cell Biology, University of Tartu, Tartu, Estonia","correspondingAuthor":true,"prefix":"","firstName":"Tarmo","middleName":"","lastName":"Puurand","suffix":""},{"id":472134132,"identity":"3083bf9e-4ad8-11f0-91e4-06cc9d20a69f","order_by":1,"name":"Märt Möls","email":"","orcid":"","institution":"Institute of Mathematics and Statistics, University of Tartu, Tartu, Estonia","correspondingAuthor":false,"prefix":"","firstName":"Märt","middleName":"","lastName":"Möls","suffix":""},{"id":472134145,"identity":"38ee7b8f-4ad8-11f0-91e4-06cc9d20a69f","order_by":2,"name":"Lauris Kaplinski","email":"","orcid":"","institution":"Institute of Molecular and Cell Biology, University of Tartu, Tartu, Estonia","correspondingAuthor":false,"prefix":"","firstName":"Lauris","middleName":"","lastName":"Kaplinski","suffix":""},{"id":472134177,"identity":"41b6cb52-4ad8-11f0-91e4-06cc9d20a69f","order_by":3,"name":"Kadri Maal","email":"","orcid":"","institution":"Department of Physiology and Pharmacology, Karolinska Institutet, Stockholm, Sweden","correspondingAuthor":false,"prefix":"","firstName":"Kadri","middleName":"","lastName":"Maal","suffix":""},{"id":472134385,"identity":"4daba92f-4ad8-11f0-91e4-06cc9d20a69f","order_by":4,"name":"Kaarel Krjutskov","email":"","orcid":"","institution":"Department of Obstetrics and Gynaecology, Institute of Clinical Medicine, University of Tartu, Tartu, Estonia; Celvia CC, Competence Centre on Health Technologies, Tartu, Estonia","correspondingAuthor":false,"prefix":"","firstName":"Kaarel","middleName":"","lastName":"Krjutskov","suffix":""},{"id":472134439,"identity":"5710c486-4ad8-11f0-91e4-06cc9d20a69f","order_by":5,"name":"Andres Salumets","email":"","orcid":"","institution":"Department of Obstetrics and Gynaecology, Institute of Clinical Medicine, University of Tartu, Tartu, Estonia; Celvia CC, Competence Centre on Health Technologies, Tartu, Estonia; Division of Obstetrics and Gynecology, Department of Clinical Science, Intervention and Technology, Karolinska Institutet and Karolinska University Hospital, Stockholm, Sweden","correspondingAuthor":false,"prefix":"","firstName":"Andres","middleName":"","lastName":"Salumets","suffix":""},{"id":472134479,"identity":"5f8901d3-4ad8-11f0-91e4-06cc9d20a69f","order_by":6,"name":"Toomas Kivisild","email":"","orcid":"","institution":"Department of Human Genetics, KU Leuven, Belgium; Institute of Genomics, University of Tartu, Estonia","correspondingAuthor":false,"prefix":"","firstName":"Toomas","middleName":"","lastName":"Kivisild","suffix":""},{"id":472134533,"identity":"6ca91d82-4ad8-11f0-91e4-06cc9d20a69f","order_by":7,"name":"Maido Remm","email":"","orcid":"","institution":"Institute of Molecular and Cell Biology, University of Tartu, Tartu, Estonia","correspondingAuthor":false,"prefix":"","firstName":"Maido","middleName":"","lastName":"Remm","suffix":""}],"badges":[],"createdAt":"2024-09-06 09:01:17","currentVersionCode":2,"declarations":"","doi":"10.21203/rs.3.rs-5042960/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-5042960/v2","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s13059-025-03714-3","type":"published","date":"2025-08-12T15:57:40+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":89310651,"identity":"20ea3462-14f9-41b8-b43d-bb3f07336804","added_by":"auto","created_at":"2025-08-18 16:09:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":693393,"visible":true,"origin":"","legend":"","description":"","filename":"Ymerrevised120525.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5042960/v2_covered_a82e2324-b67a-4762-aba4-9efec48bea02.pdf"},{"id":84733680,"identity":"b4715412-df97-4a98-9d40-cef56b16c2b2","added_by":"auto","created_at":"2025-06-16 17:48:23","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":153140,"visible":true,"origin":"","legend":"","description":"","filename":"Ymer240823Model.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5042960/v2/3dfc945a76e4a13851b76f4e.pdf"},{"id":84733690,"identity":"2e6c1246-147e-40ea-a22a-0f0d964f596d","added_by":"auto","created_at":"2025-06-16 17:48:23","extension":"xlsx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":772337,"visible":true,"origin":"","legend":"","description":"","filename":"Ymerrevisedsuppltables070525.xlsx","url":"https://assets-eu.researchsquare.com/files/rs-5042960/v2/6ef37a163af0177a58157b26.xlsx"},{"id":84735165,"identity":"ac4a08c6-39c3-4e4f-b27d-33bcf0965b0b","added_by":"auto","created_at":"2025-06-16 18:12:23","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":17625,"visible":true,"origin":"","legend":"","description":"","filename":"YmerSIrevised070525.docx","url":"https://assets-eu.researchsquare.com/files/rs-5042960/v2/084206e947212390470c7f81.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Y-mer: A k-mer based method for determining human Y chromosome haplogroups from ultra-low sequencing depth data","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"genome-biology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"gbio","sideBox":"Learn more about [Genome Biology](https://genomebiology.biomedcentral.com/)","snPcode":"13059","submissionUrl":"https://submission.springernature.com/new-submission/13059/3","title":"Genome Biology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"aDNA, ulcWGS, NIPS, NIPT, k-mer, human, chrY, haplogroups, prediction","lastPublishedDoi":"10.21203/rs.3.rs-5042960/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5042960/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDetermining genetic ancestry of an individual is challenging from poorly preserved or mixed samples that permit only ultra-low coverage sequence (ulcWGS) depth\u0026thinsp;\u0026lt;\u0026thinsp;0.1x to be gained at target loci. Leveraging the recent advances in telomere-to-telomere sequencing of the whole genomes with long reads we develop a new k-mer based method Y-mer and show how information from hundreds of thousands of k-mers in distance-based models enables accurate inference of chrY haplogroup from WGS sequence at depth less than 0.01x without additional PCR or capture. We test the performance of Y-mer on ancient DNA and prenatal screening data showing its potential for genetic ancestry inference for cell-free, forensic and ancient DNA research from short read WGS data.\u003c/p\u003e","manuscriptTitle":"Y-mer: A k-mer based method for determining human Y chromosome haplogroups from ultra-low sequencing depth data","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2025-06-16 17:40:19","doi":"10.21203/rs.3.rs-5042960/v2","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-06-20T13:11:30+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-11T14:45:04+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-10T08:52:54+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-02T12:49:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"265148273547436808900439588240720576006","date":"2025-05-18T13:23:22+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"135258064265628894630432270589817573701","date":"2025-05-16T10:06:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"11995050356810287448773143671264164036","date":"2025-05-13T12:26:23+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-05-13T10:56:45+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-13T06:20:11+00:00","index":"","fulltext":""},{"type":"submitted","content":"Genome Biology","date":"2025-05-12T12:39:47+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"genome-biology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"gbio","sideBox":"Learn more about [Genome Biology](https://genomebiology.biomedcentral.com/)","snPcode":"13059","submissionUrl":"https://submission.springernature.com/new-submission/13059/3","title":"Genome Biology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}},{"code":1,"date":"2024-10-09 05:05:32","doi":"10.21203/rs.3.rs-5042960/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-02-19T17:45:15+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-02-19T16:19:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"265148273547436808900439588240720576006","date":"2025-01-26T21:54:17+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-01-09T02:31:06+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-29T13:55:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"11995050356810287448773143671264164036","date":"2024-11-12T10:29:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"135258064265628894630432270589817573701","date":"2024-11-11T09:07:58+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-11-08T15:58:28+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-09-12T12:46:04+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-09-06T09:18:22+00:00","index":"","fulltext":""},{"type":"submitted","content":"Genome Biology","date":"2024-09-06T08:59:38+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"genome-biology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"gbio","sideBox":"Learn more about [Genome Biology](https://genomebiology.biomedcentral.com/)","snPcode":"13059","submissionUrl":"https://submission.springernature.com/new-submission/13059/3","title":"Genome Biology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"209a546b-3205-4905-8e6f-3b8874a4a783","owner":[],"postedDate":"June 16th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-08-18T16:05:02+00:00","versionOfRecord":{"articleIdentity":"rs-5042960","link":"https://doi.org/10.1186/s13059-025-03714-3","journal":{"identity":"genome-biology","isVorOnly":false,"title":"Genome Biology"},"publishedOn":"2025-08-12 15:57:40","publishedOnDateReadable":"August 12th, 2025"},"versionCreatedAt":"2025-06-16 17:40:19","video":"","vorDoi":"10.1186/s13059-025-03714-3","vorDoiUrl":"https://doi.org/10.1186/s13059-025-03714-3","workflowStages":[]},"version":"v2","identity":"rs-5042960","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5042960","identity":"rs-5042960","version":["v2"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}