{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T03:53:14Z","timestamp":1772077994700,"version":"3.50.1"},"reference-count":5,"publisher":"Oxford University Press (OUP)","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,1,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Summary: The amount of genomic sequence data being generated and made available through public databases continues to increase at an ever-expanding rate. Downloading, copying, sharing and manipulating these large datasets are becoming difficult and time consuming for researchers. We need to consider using advanced compression techniques as part of a standard data format for genomic data. The inherent structure of genome data allows for more efficient lossless compression than can be obtained through the use of generic compression programs. We apply a series of techniques to James Watson's genome that in combination reduce it to a mere 4MB, small enough to be sent as an email attachment.<\/jats:p>\n               <jats:p>Availability: Our algorithms are implemented in C++ and are freely available from http:\/\/www.ics.uci.edu\/~xhx\/project\/DNAzip.<\/jats:p>\n               <jats:p>Contact: \u00a0chenli@ics.uci.edu; xhx@ics.uci.edu<\/jats:p>\n               <jats:p>Supplementary information: \u00a0Supplementary data are available at Bioinformatics online.<\/jats:p>","DOI":"10.1093\/bioinformatics\/btn582","type":"journal-article","created":{"date-parts":[[2008,11,8]],"date-time":"2008-11-08T01:34:41Z","timestamp":1226108081000},"page":"274-275","source":"Crossref","is-referenced-by-count":106,"title":["Human genomes as email attachments"],"prefix":"10.1093","volume":"25","author":[{"given":"Scott","family":"Christley","sequence":"first","affiliation":[{"name":"1 Department of Computer Science and 2Institute for Genomics and Bioinformatics, University of California Irvine, Irvine, CA 92697, USA"}]},{"given":"Yiming","family":"Lu","sequence":"additional","affiliation":[{"name":"1 Department of Computer Science and 2Institute for Genomics and Bioinformatics, University of California Irvine, Irvine, CA 92697, USA"}]},{"given":"Chen","family":"Li","sequence":"additional","affiliation":[{"name":"1 Department of Computer Science and 2Institute for Genomics and Bioinformatics, University of California Irvine, Irvine, CA 92697, USA"}]},{"given":"Xiaohui","family":"Xie","sequence":"additional","affiliation":[{"name":"1 Department of Computer Science and 2Institute for Genomics and Bioinformatics, University of California Irvine, Irvine, CA 92697, USA"},{"name":"1 Department of Computer Science and 2Institute for Genomics and Bioinformatics, University of California Irvine, Irvine, CA 92697, USA"}]}],"member":"286","published-online":{"date-parts":[[2008,9,30]]},"reference":[{"key":"2023013109594066200_B1","doi-asserted-by":"crossref","first-page":"1696","DOI":"10.1093\/bioinformatics\/18.12.1696","article-title":"DNACompress: fast and effective DNA sequence compression","volume":"18","author":"Chen","year":"2002","journal-title":"Bioinformatics"},{"key":"2023013109594066200_B2","doi-asserted-by":"crossref","first-page":"1098","DOI":"10.1109\/JRPROC.1952.273898","article-title":"A method for the construction of minimum-redundancy codes","volume":"40","author":"Huffman","year":"1952","journal-title":"Proc. I.R.E"},{"key":"2023013109594066200_B3","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1038\/nature02168","article-title":"The International HapMap Project","volume":"426","author":"The International HapMap Consortium","year":"2003","journal-title":"Nature"},{"key":"2023013109594066200_B4","doi-asserted-by":"crossref","first-page":"872","DOI":"10.1038\/nature06884","article-title":"The complete genome of an individual by massively parallel DNA sequencing","volume":"452","author":"Wheeler","year":"2008","journal-title":"Nature"},{"key":"2023013109594066200_B5","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1186\/1471-2105-9-242","article-title":"Compressing DNA sequence databases with coil","volume":"9","author":"White","year":"2008","journal-title":"BMC Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/25\/2\/274\/48982210\/bioinformatics_25_2_274.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/25\/2\/274\/48982210\/bioinformatics_25_2_274.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T18:25:26Z","timestamp":1675189526000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/25\/2\/274\/218156"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,9,30]]},"references-count":5,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2009,1,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btn582","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2009,1,15]]},"published":{"date-parts":[[2008,9,30]]}}}