{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T01:42:37Z","timestamp":1778636557663,"version":"3.51.4"},"reference-count":15,"publisher":"Oxford University Press (OUP)","issue":"18","license":[{"start":{"date-parts":[[2022,7,29]],"date-time":"2022-07-29T00:00:00Z","timestamp":1659052800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"ANR Inception","award":["ANR-16-CONV-0005"],"award-info":[{"award-number":["ANR-16-CONV-0005"]}]},{"name":"PRAIRIE","award":["ANR-19-P3IA-0001"],"award-info":[{"award-number":["ANR-19-P3IA-0001"]}]},{"DOI":"10.13039\/501100004281","name":"National Science Centre","doi-asserted-by":"publisher","award":["DEC-2019\/33\/B\/ST6\/02040"],"award-info":[{"award-number":["DEC-2019\/33\/B\/ST6\/02040"]}],"id":[{"id":"10.13039\/501100004281","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1453527"],"award-info":[{"award-number":["1453527"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1931531"],"award-info":[{"award-number":["1931531"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Union\u2019s Horizon 2020 Research and Innovation Programme"},{"name":"Marie Sk\u0142odowska-Curie","award":["956229"],"award-info":[{"award-number":["956229"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,9,15]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Summary<\/jats:title><jats:p>Bioinformatics applications increasingly rely on ad hoc disk storage of k-mer sets, e.g. for de Bruijn graphs or alignment indexes. Here, we introduce the K-mer File Format as a general lossless framework for storing and manipulating k-mer sets, realizing space savings of 3\u20135\u00d7 compared to other formats, and bringing interoperability across tools.<\/jats:p><\/jats:sec><jats:sec><jats:title>Availability and implementation<\/jats:title><jats:p>Format specification, C++\/Rust API, tools: https:\/\/github.com\/Kmer-File-Format\/.<\/jats:p><\/jats:sec><jats:sec><jats:title>Supplementary information<\/jats:title><jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p><\/jats:sec>","DOI":"10.1093\/bioinformatics\/btac528","type":"journal-article","created":{"date-parts":[[2022,7,29]],"date-time":"2022-07-29T15:09:23Z","timestamp":1659107363000},"page":"4423-4425","source":"Crossref","is-referenced-by-count":12,"title":["The K-mer File Format: a standardized and compact disk representation of sets of<i>k<\/i>-mers"],"prefix":"10.1093","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0930-8920","authenticated-orcid":false,"given":"Yoann","family":"Dufresne","sequence":"first","affiliation":[{"name":"Computational Biology Department, Institut Pasteur, Universit\u00e9 Paris Cit\u00e9 , F-75015 Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7210-3178","authenticated-orcid":false,"given":"Teo","family":"Lemane","sequence":"additional","affiliation":[{"name":"Univ Rennes, Inria, CNRS, IRISA\u2014UMR , 6074 Rennes, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pierre","family":"Marijon","sequence":"additional","affiliation":[{"name":"Heinrich Heine University D\u00fcsseldorf Medical Faculty Institute for Medical Biometry and Bioinformatic , D\u00fcsseldorf 40225, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0776-6407","authenticated-orcid":false,"given":"Pierre","family":"Peterlongo","sequence":"additional","affiliation":[{"name":"Univ Rennes, Inria, CNRS, IRISA\u2014UMR , 6074 Rennes, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amatur","family":"Rahman","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Pennsylvania State University , State College 16802, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marek","family":"Kokot","sequence":"additional","affiliation":[{"name":"Department of Algorithmics and Software, Silesian University of Technology, Gliwice , PL-44-100 Akademicka 16, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3143-594X","authenticated-orcid":false,"given":"Paul","family":"Medvedev","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Pennsylvania State University , State College 16802, USA"},{"name":"Department of Biochemistry and Molecular Biology, The Pennsylvania State University , State College 16801, USA"},{"name":"Huck Institutes of the Life Sciences, The Pennsylvania State University , State College 16802, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebastian","family":"Deorowicz","sequence":"additional","affiliation":[{"name":"Department of Algorithmics and Software, Silesian University of Technology, Gliwice , PL-44-100 Akademicka 16, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rayan","family":"Chikhi","sequence":"additional","affiliation":[{"name":"Computational Biology Department, Institut Pasteur, Universit\u00e9 Paris Cit\u00e9 , F-75015 Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2022,7,29]]},"reference":[{"key":"2023041408375678800_","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1089\/cmb.2012.0021","article-title":"SPAdes: a new genome assembly algorithm and its applications to single-cell sequencing","volume":"19","author":"Bankevich","year":"2012","journal-title":"J. Comput. Biol"},{"key":"2023041408375678800_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13059-021-02297-z","article-title":"Simplitigs as an efficient and scalable representation of de Bruijn graphs","volume":"22","author":"B\u0159inda","year":"2021","journal-title":"Genome Biol"},{"key":"2023041408375678800_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3445967","article-title":"Data structures to represent a set of k-long DNA sequences","volume":"54","author":"Chikhi","year":"2021","journal-title":"ACM Comput. Surv"},{"key":"2023041408375678800_","first-page":"020024","author":"Cock","year":"2015"},{"key":"2023041408375678800_","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1186\/1471-2105-14-160","article-title":"Disk-based k-mer counting on a PC","volume":"14","author":"Deorowicz","year":"2013","journal-title":"BMC Bioinformatics"},{"key":"2023041408375678800_","first-page":"36","author":"Folk","year":"2011"},{"key":"2023041408375678800_","doi-asserted-by":"crossref","first-page":"2759","DOI":"10.1093\/bioinformatics\/btx304","article-title":"KMC 3: counting and manipulating k-mer statistics","volume":"33","author":"Kokot","year":"2017","journal-title":"Bioinformatics"},{"key":"2023041408375678800_","author":"Lemane","year":"2022"},{"key":"2023041408375678800_","doi-asserted-by":"crossref","first-page":"3094","DOI":"10.1093\/bioinformatics\/bty191","article-title":"Minimap2: pairwise alignment for nucleotide sequences","volume":"34","author":"Li","year":"2018","journal-title":"Bioinformatics"},{"key":"2023041408375678800_","doi-asserted-by":"crossref","first-page":"764","DOI":"10.1093\/bioinformatics\/btr011","article-title":"A fast, lock-free approach for efficient parallel counting of occurrences of k-mers","volume":"27","author":"Mar\u00e7ais","year":"2011","journal-title":"Bioinformatics"},{"key":"2023041408375678800_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1101\/gr.260604.119","article-title":"Data structures based on k-mers for querying large collections of sequencing data sets","volume":"31","author":"Marchet","year":"2021","journal-title":"Genome Res"},{"key":"2023041408375678800_","doi-asserted-by":"crossref","first-page":"1006","DOI":"10.12688\/f1000research.19675.1","article-title":"Large-scale sequence comparisons with sourmash","volume":"8","author":"Pierce","year":"2019","journal-title":"F1000Res"},{"key":"2023041408375678800_","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1089\/cmb.2020.0431","article-title":"Representation of k-mer sets using Spectrum-Preserving string sets","volume":"28","author":"Rahman","year":"2021","journal-title":"J. Comput. Biol"},{"key":"2023041408375678800_","author":"Rahman","year":"2020"},{"key":"2023041408375678800_","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1093\/bioinformatics\/btt020","article-title":"DSK: k-mer counting with very low memory usage","volume":"29","author":"Rizk","year":"2013","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac528\/45290957\/btac528.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/18\/4423\/49885747\/btac528.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/18\/4423\/49885747\/btac528.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T03:52:50Z","timestamp":1700884370000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/38\/18\/4423\/6651834"}},"subtitle":[],"editor":[{"given":"Inanc","family":"Birol","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2022,7,29]]},"references-count":15,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2022,9,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac528","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,9,15]]},"published":{"date-parts":[[2022,7,29]]}}}