{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T15:01:35Z","timestamp":1790262095244,"version":"4.1.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:00:00Z","timestamp":1783036800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"content-version":"vor","delay-in-days":83,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"NSF","award":["DBI2138585"],"award-info":[{"award-number":["DBI2138585"]}]},{"name":"NIH","award":["R01GM146462"],"award-info":[{"award-number":["R01GM146462"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Algorithms Mol Biol"],"DOI":"10.1186\/s13015-026-00304-1","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T14:56:16Z","timestamp":1783090576000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A k-mer-based estimator of the substitution rate between repetitive sequences"],"prefix":"10.1186","volume":"21","author":[{"given":"Haonan","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonio","family":"Blanca","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Medvedev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,3]]},"reference":[{"issue":"7","key":"304_CR1","doi-asserted-by":"publisher","first-page":"1075","DOI":"10.1038\/s41587-022-01220-6","volume":"40","author":"A Bankevich","year":"2022","unstructured":"Bankevich A, Bzikadze AV, Kolmogorov M, Antipov D, Pevzner PA. Multiplex de Bruijn graphs enable genome assembly from long, high-fidelity reads. Nat Biotechnol. 2022;40(7):1075\u201381.","journal-title":"Nat Biotechnol"},{"issue":"5","key":"304_CR2","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1089\/cmb.2012.0021","volume":"19","author":"A Bankevich","year":"2012","unstructured":"Bankevich A, Nurk S, Antipov D, Gurevich AA, Dvorkin M, Kulikov AS, et al. SPAdes: a new genome assembly algorithm and its applications to single-cell sequencing. J Comput Biol. 2012;19(5):455\u201377. https:\/\/doi.org\/10.1089\/cmb.2012.0021.","journal-title":"J Comput Biol"},{"issue":"9","key":"304_CR3","doi-asserted-by":"publisher","first-page":"btad512","DOI":"10.1093\/bioinformatics\/btad512","volume":"39","author":"B Kille","year":"2023","unstructured":"Kille B, Garrison E, Treangen TJ, Phillippy AM. Minmers are a generalization of minimizers that enable unbiased local Jaccard estimation. Bioinformatics. 2023;39(9):btad512. https:\/\/doi.org\/10.1093\/bioinformatics\/btad512.","journal-title":"Bioinformatics"},{"key":"304_CR4","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.isci.2019.07.032","volume":"18","author":"DS Standage","year":"2019","unstructured":"Standage DS, Brown CT, Hormozdiari F. Kevlar: a mapping-free framework for accurate discovery of de novo variants. IScience. 2019;18:28\u201336.","journal-title":"IScience"},{"issue":"3","key":"304_CR5","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1093\/bioinformatics\/bty641","volume":"35","author":"C Sun","year":"2018","unstructured":"Sun C, Medvedev P. Toward fast and accurate snp genotyping from whole genome sequencing data for bedside diagnostics. Bioinformatics. 2018;35(3):415\u201320. https:\/\/doi.org\/10.1093\/bioinformatics\/bty641.","journal-title":"Bioinformatics"},{"key":"304_CR6","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.isci.2019.07.011","volume":"18","author":"L Denti","year":"2019","unstructured":"Denti L, Previtali M, Bernardini G, Sch\u00f6nhuth A, Bonizzoni P. MALVA: genotyping by Mapping-free ALlele detection of known VAriants. IScience. 2019;18:20\u20137.","journal-title":"IScience"},{"issue":"2","key":"304_CR7","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1038\/s43588-024-00596-6","volume":"4","author":"T Lemane","year":"2024","unstructured":"Lemane T, Lezzoche N, Lecubin J, Pelletier E, Lescot M, Chikhi R, et al. Indexing and real-time user-friendly queries in terabyte-sized complex genomic datasets with kmindex and ORA. Nat Comput Sci. 2024;4(2):104\u20139. https:\/\/doi.org\/10.1038\/s43588-024-00596-6.","journal-title":"Nat Comput Sci"},{"issue":"3","key":"304_CR8","doi-asserted-by":"publisher","first-page":"721","DOI":"10.1093\/bioinformatics\/btz662","volume":"36","author":"RS Harris","year":"2020","unstructured":"Harris RS, Medvedev P. Improved representation of Sequence Bloom Trees. Bioinformatics. 2020;36(3):721\u20137. https:\/\/doi.org\/10.1093\/bioinformatics\/btz662.","journal-title":"Bioinformatics"},{"issue":"11","key":"304_CR9","doi-asserted-by":"publisher","first-page":"1661","DOI":"10.1038\/s41592-023-02018-3","volume":"20","author":"J Shaw","year":"2023","unstructured":"Shaw J, Yu YW. Fast and robust metagenomic sequence comparison through sparse chaining with Skani. Nat Methods. 2023;20(11):1661\u20135.","journal-title":"Nat Methods"},{"issue":"3","key":"304_CR10","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1093\/bib\/bbt067","volume":"15","author":"K Song","year":"2014","unstructured":"Song K, Ren J, Reinert G, Deng M, Waterman MS, Sun F. New developments of alignment-free sequence comparison: measures, statistics and next-generation sequencing. Brief Bioinform. 2014;15(3):343\u201353. https:\/\/doi.org\/10.1093\/bib\/bbt067.","journal-title":"Brief Bioinform"},{"issue":"1","key":"304_CR11","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1186\/s13059-016-0997-x","volume":"17","author":"BD Ondov","year":"2016","unstructured":"Ondov BD, Treangen TJ, Melsted P, Mallonee AB, Bergman NH, Koren S, et al. Mash: fast genome and metagenome distance estimation using MinHash. Genome Biol. 2016;17(1):132.","journal-title":"Genome Biol"},{"issue":"1","key":"304_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13059-019-1632-4","volume":"20","author":"S Sarmashghi","year":"2019","unstructured":"Sarmashghi S, Bohmann K, Gilbert MTP, Bafna V, Mirarab S. Skmer: assembly-free and alignment-free sample identification using genome skims. Genome Biol. 2019;20(1):1\u201320.","journal-title":"Genome Biol"},{"issue":"18","key":"304_CR13","doi-asserted-by":"publisher","first-page":"3094","DOI":"10.1093\/bioinformatics\/bty191","volume":"34","author":"H Li","year":"2018","unstructured":"Li H. Minimap2: pairwise alignment for nucleotide sequences. Bioinformatics. 2018;34(18):3094\u2013100. https:\/\/doi.org\/10.1093\/bioinformatics\/bty191.","journal-title":"Bioinformatics"},{"issue":"1","key":"304_CR14","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1186\/s13015-024-00261-7","volume":"19","author":"T Schulz","year":"2024","unstructured":"Schulz T, Medvedev P. ESKEMAP: exact sketch-based read mapping. Algorithms Mol Biol. 2024;19(1):19. https:\/\/doi.org\/10.1186\/s13015-024-00261-7.","journal-title":"Algorithms Mol Biol"},{"issue":"7","key":"304_CR15","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1101\/gr.277637.122","volume":"33","author":"J Shaw","year":"2023","unstructured":"Shaw J, Yu YW. Proving sequence aligners can guarantee accuracy in almost $$O(m \\log n)$$ time through an average-case analysis of the seed-chain-extend heuristic. Genome Res. 2023;33(7):1175\u201387.","journal-title":"Genome Res"},{"issue":"1","key":"304_CR16","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1146\/annurev-biodatasci-072018-021156","volume":"2","author":"G Mar\u00e7ais","year":"2019","unstructured":"Mar\u00e7ais G, Solomon B, Patro R, Kingsford C. Sketching and sublinear data structures in genomics. Annu Rev Biomed Data Sci. 2019;2(1):93\u2013118.","journal-title":"Annu Rev Biomed Data Sci"},{"issue":"1","key":"304_CR17","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1186\/s13059-019-1809-x","volume":"20","author":"WPM Rowe","year":"2019","unstructured":"Rowe WPM. When the levee breaks: a practical guide to sketching algorithms for processing the flood of genomic data. Genome Biol. 2019;20(1):199.","journal-title":"Genome Biol"},{"issue":"7","key":"304_CR18","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1093\/nar\/gkt003","volume":"41","author":"H Yi","year":"2013","unstructured":"Yi H, Jin L. Co-phylog: an assembly-free phylogenomic approach for closely related organisms. Nucleic Acids Res. 2013;41(7):75\u201375.","journal-title":"Nucleic Acids Res"},{"issue":"8","key":"304_CR19","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.1093\/bioinformatics\/btu815","volume":"31","author":"B Haubold","year":"2014","unstructured":"Haubold B, Kl\u00f6tzl F, Pfaffelhuber P. Andi: fast and accurate estimation of evolutionary distances between closely related genomes. Bioinformatics. 2014;31(8):1169\u201375. https:\/\/doi.org\/10.1093\/bioinformatics\/btu815.","journal-title":"Bioinformatics"},{"issue":"1","key":"304_CR20","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1186\/s13015-015-0032-x","volume":"10","author":"B Morgenstern","year":"2015","unstructured":"Morgenstern B, Zhu B, Horwege S, Leimeister CA. Estimating evolutionary distances between genomic sequences from spaced-word matches. Algorithms Mol Biol. 2015;10(1):5.","journal-title":"Algorithms Mol Biol"},{"issue":"2","key":"304_CR21","doi-asserted-by":"publisher","first-page":"0228070","DOI":"10.1371\/journal.pone.0228070","volume":"15","author":"S R\u00f6hling","year":"2020","unstructured":"R\u00f6hling S, Linne A, Schellhorn J, Hosseini M, Dencker T, Morgenstern B. The number of k-mer matches between two DNA sequences as a function of k and applications to estimate phylogenetic distances. PLoS ONE. 2020;15(2):0228070.","journal-title":"PLoS ONE"},{"issue":"2","key":"304_CR22","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1089\/cmb.2021.0431","volume":"29","author":"A Blanca","year":"2022","unstructured":"Blanca A, Harris RS, Koslicki D, Medvedev P. The statistics of k-mers from a sequence undergoing a simple mutation process without spurious matches. J Comput Biol. 2022;29(2):155\u201368. https:\/\/doi.org\/10.1089\/cmb.2021.0431.","journal-title":"J Comput Biol"},{"key":"304_CR23","unstructured":"Wu H, Blanca A, Medvedev P. Repeat-Aware Substutituion Rate Estimator. https:\/\/github.com\/medvedevgroup\/Repeat-Aware_Substitution_Rate_Estimator"},{"issue":"1","key":"304_CR24","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1186\/s12864-015-1647-5","volume":"16","author":"H Fan","year":"2015","unstructured":"Fan H, Ives AR, Surget-Groba Y, Cannon CH. An assembly and alignment-free method of phylogeny reconstruction from next-generation sequencing data. BMC Genomics. 2015;16(1):522.","journal-title":"BMC Genomics"},{"issue":"1","key":"304_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-018-07641-9","volume":"9","author":"C Jain","year":"2018","unstructured":"Jain C, Rodriguez-R LM, Phillippy AM, Konstantinidis KT, Aluru S. High throughput Ani analysis of 90k prokaryotic genomes reveals clear species boundaries. Nat Commun. 2018;9(1):1\u20138.","journal-title":"Nat Commun"},{"issue":"Supplement\u20131","key":"304_CR26","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1093\/bioinformatics\/btac244","volume":"38","author":"M Belbasi","year":"2022","unstructured":"Belbasi M, Blanca A, Harris RS, Koslicki D, Medvedev P. The minimizer Jaccard estimator is biased and inconsistent. Bioinformatics. 2022;38(Supplement\u20131):169\u201376. https:\/\/doi.org\/10.1093\/bioinformatics\/btac244.","journal-title":"Bioinformatics"},{"key":"304_CR27","unstructured":"Casella G, Berger RL. Statistical Inference, 2. ed. Pacific Grove, Calif: Duxbury; 2002."},{"issue":"6588","key":"304_CR28","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1126\/science.abj6987","volume":"376","author":"S Nurk","year":"2022","unstructured":"Nurk S, Koren S, Rhie A, Rautiainen M, Bzikadze AV, Mikheenko A, et al. The complete sequence of a human genome. Science. 2022;376(6588):44\u201353.","journal-title":"Science"},{"key":"304_CR29","unstructured":"Wu H, Blanca A, Medvedev P. Reproducibility repository. https:\/\/github.com\/medvedevgroup\/kmer-stats-repeat_Reproduce"},{"issue":"7978","key":"304_CR30","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1038\/s41586-023-06457-y","volume":"621","author":"A Rhie","year":"2023","unstructured":"Rhie A, Nurk S, Cechova M, Hoyt SJ, Taylor DJ, Altemose N, et al. The complete sequence of a human y chromosome. Nature. 2023;621(7978):344\u201354.","journal-title":"Nature"},{"issue":"2","key":"304_CR31","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1093\/nar\/27.2.573","volume":"27","author":"G Benson","year":"1999","unstructured":"Benson G. Tandem repeats finder: a program to analyze DNA sequences. Nucleic Acids Res. 1999;27(2):573\u201380.","journal-title":"Nucleic Acids Res"},{"key":"304_CR32","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/s10577-018-9582-3","volume":"26","author":"SM McNulty","year":"2018","unstructured":"McNulty SM, Sullivan BA. Alpha satellite DNA biology: finding function in the recesses of the genome. Chromosome Res. 2018;26:115\u201338.","journal-title":"Chromosome Res"},{"issue":"7","key":"304_CR33","first-page":"1061","volume":"33","author":"MR Hera","year":"2023","unstructured":"Hera MR, Pierce-Ward NT, Koslicki D. Deriving confidence intervals for mutation rates across a wide range of evolutionary distances using fracminhash. Genome Res. 2023;33(7):1061\u20138.","journal-title":"Genome Res"},{"issue":"1","key":"304_CR34","doi-asserted-by":"publisher","first-page":"4340","DOI":"10.1038\/s41467-018-06545-y","volume":"9","author":"V Barra","year":"2018","unstructured":"Barra V, Fachinetti D. The dark side of centromeres: types, causes and consequences of structural abnormalities implicating centromeric DNA. Nat Commun. 2018;9(1):4340.","journal-title":"Nat Commun"},{"issue":"2","key":"304_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.yexcr.2020.112127","volume":"394","author":"KH Miga","year":"2020","unstructured":"Miga KH. Centromere studies in the era of \u2018telomere-to-telomere\u2019 genomics. Exp Cell Res. 2020;394(2):112127. https:\/\/doi.org\/10.1016\/j.yexcr.2020.112127.","journal-title":"Exp Cell Res"},{"issue":"8010","key":"304_CR36","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1038\/s41586-024-07278-3","volume":"629","author":"GA Logsdon","year":"2024","unstructured":"Logsdon GA, Rozanski AN, Ryabov F, Potapova T, Shepelev VA, Catacchio CR, et al. The variation and evolution of complete human centromeres. Nature. 2024;629(8010):136\u201345.","journal-title":"Nature"},{"key":"304_CR37","unstructured":"Yoo D, Rhie A, Hebbar P, Antonacci F, Logsdon GA, Solar SJ, et al. Complete sequencing of ape genomes. Nature. 2025;1\u201318."},{"issue":"1","key":"304_CR38","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1186\/s13059-019-1841-x","volume":"20","author":"BD Ondov","year":"2019","unstructured":"Ondov BD, Starrett GJ, Sappington A, Kostic A, Koren S, Buck CB, et al. Mash Screen: high-throughput sequence containment estimation for genome discovery. Genome Biol. 2019;20(1):232.","journal-title":"Genome Biol"},{"issue":"14","key":"304_CR39","doi-asserted-by":"publisher","first-page":"2202","DOI":"10.1093\/bioinformatics\/btx153","volume":"33","author":"GW Vurture","year":"2017","unstructured":"Vurture GW, Sedlazeck FJ, Nattestad M, Underwood CJ, Fang H, Gurtowski J, et al. Genomescope: fast reference-free genome profiling from short reads. Bioinformatics. 2017;33(14):2202\u20134. https:\/\/doi.org\/10.1093\/bioinformatics\/btx153.","journal-title":"Bioinformatics"}],"container-title":["Algorithms for Molecular Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13015-026-00304-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13015-026-00304-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13015-026-00304-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T14:02:17Z","timestamp":1790258537000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13015-026-00304-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,3]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["304"],"URL":"https:\/\/doi.org\/10.1186\/s13015-026-00304-1","relation":{},"ISSN":["1748-7188"],"issn-type":[{"value":"1748-7188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,3]]},"assertion":[{"value":"13 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"14"}}