{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T07:16:21Z","timestamp":1779002181288,"version":"3.51.4"},"reference-count":8,"publisher":"Oxford University Press (OUP)","issue":"19","license":[{"start":{"date-parts":[[2019,2,25]],"date-time":"2019-02-25T00:00:00Z","timestamp":1551052800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Summary<\/jats:title>\n                    <jats:p>DNA sequence databases use compression such as gzip to reduce the required storage space and network transmission time. We describe Nucleotide Archival Format (NAF)\u2014a new file format for lossless reference-free compression of FASTA and FASTQ-formatted nucleotide sequences. Nucleotide Archival Format compression ratio is comparable to the best DNA compressors, while providing dramatically faster decompression. We compared our format with DNA compressors: DELIMINATE and MFCompress, and with general purpose compressors: gzip, bzip2, xz, brotli and zstd.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>NAF compressor and decompressor, as well as format specification are available at https:\/\/github.com\/KirillKryukov\/naf. Format specification is in public domain. Compressor and decompressor are open source under the zlib\/libpng license, free for nearly any use.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary information<\/jats:title>\n                    <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btz144","type":"journal-article","created":{"date-parts":[[2019,2,22]],"date-time":"2019-02-22T07:41:13Z","timestamp":1550821273000},"page":"3826-3828","source":"Crossref","is-referenced-by-count":53,"title":["Nucleotide Archival Format (NAF) enables efficient lossless reference-free compression of DNA sequences"],"prefix":"10.1093","volume":"35","author":[{"given":"Kirill","family":"Kryukov","sequence":"first","affiliation":[{"name":"Department of Molecular Life Science, Tokai University School of Medicine , Isehara, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahoko Takahashi","family":"Ueda","sequence":"additional","affiliation":[{"name":"Micro\/Nano Technology Center, Tokai University , Hiratsuka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"So","family":"Nakagawa","sequence":"additional","affiliation":[{"name":"Department of Molecular Life Science, Tokai University School of Medicine , Isehara, Japan"},{"name":"Micro\/Nano Technology Center, Tokai University , Hiratsuka, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tadashi","family":"Imanishi","sequence":"additional","affiliation":[{"name":"Department of Molecular Life Science, Tokai University School of Medicine , Isehara, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2019,2,25]]},"reference":[{"key":"2023013108193437500_btz144-B1","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1089\/cmb.2016.0151","article-title":"Toward a better compression for DNA sequences using Huffman encoding","volume":"24","author":"Al-Okaily","year":"2017","journal-title":"J. Comput. Biol"},{"key":"2023013108193437500_btz144-B2","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1186\/s12859-015-0709-7","article-title":"Reference-free compression of high throughput sequencing data with a probabilistic de Bruijn graph","volume":"16","author":"Benoit","year":"2015","journal-title":"BMC Bioinformatics"},{"key":"2023013108193437500_btz144-B3","first-page":"43","volume-title":"DCC-2007 Data Compression Conference, Snowbird, Utah","author":"Cao","year":"2007"},{"key":"2023013108193437500_btz144-B4","first-page":"340","volume-title":"DCC '93 Data Compression Conference, Snowbird, Utah","author":"Grumbach","year":"1993"},{"key":"2023013108193437500_btz144-B5","doi-asserted-by":"crossref","first-page":"e80377","DOI":"10.1371\/journal.pone.0080377","article-title":"DNA-COMPACT: DNA COMpression based on a pattern-aware contextual modeling technique","volume":"8","author":"Li","year":"2013","journal-title":"PLoS One"},{"key":"2023013108193437500_btz144-B6","doi-asserted-by":"crossref","first-page":"2527","DOI":"10.1093\/bioinformatics\/bts467","article-title":"DELIMINATE\u2014a fast and efficient method for loss-less compression of genomic sequences","volume":"28","author":"Mohammed","year":"2012","journal-title":"Bioinformatics"},{"key":"2023013108193437500_btz144-B7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.1432-1033.1985.tb08977.x","article-title":"Nomenclature for incompletely specified bases in nucleic acid sequences","volume":"150","year":"1985","journal-title":"Eur. J. Biochem"},{"key":"2023013108193437500_btz144-B8","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1093\/bioinformatics\/btt594","article-title":"MFCompress: a compression tool for FASTA and multi-FASTA data","volume":"30","author":"Pinho","year":"2014","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/19\/3826\/48977341\/bioinformatics_35_19_3826.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/19\/3826\/48977341\/bioinformatics_35_19_3826.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T10:08:49Z","timestamp":1675159729000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/35\/19\/3826\/5364265"}},"subtitle":[],"editor":[{"given":"John","family":"Hancock","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2019,2,25]]},"references-count":8,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2019,10,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btz144","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/501130","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,10,1]]},"published":{"date-parts":[[2019,2,25]]}}}