{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:34:44Z","timestamp":1772138084804,"version":"3.50.1"},"reference-count":25,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2017,10,26]],"date-time":"2017-10-26T00:00:00Z","timestamp":1508976000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/about_us\/legal\/notices"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["DGE-1144245"],"award-info":[{"award-number":["DGE-1144245"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,3,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Chromatin immunoprecipitation sequencing (ChIP-seq) experiments are inexpensive and time-efficient, and result in massive datasets that introduce significant storage and maintenance challenges. To address the resulting Big Data problems, we propose a lossless and lossy compression framework specifically designed for ChIP-seq Wig data, termed ChIPWig. ChIPWig enables random access, summary statistics lookups and it is based on the asymptotic theory of optimal point density design for nonuniform quantizers.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We tested the ChIPWig compressor on 10 ChIP-seq datasets generated by the ENCODE consortium. On average, lossless ChIPWig reduced the file sizes to merely 6% of the original, and offered 6-fold compression rate improvement compared to bigWig. The lossy feature further reduced file sizes 2-fold compared to the lossless mode, with little or no effects on peak calling and motif discovery using specialized NarrowPeaks methods. The compression and decompression speed rates are of the order of 0.2 sec\/MB using general purpose computers.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The source code and binaries are freely available for download at https:\/\/github.com\/vidarmehr\/ChIPWig-v2, implemented in C\u2009++.<\/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\/btx685","type":"journal-article","created":{"date-parts":[[2017,10,25]],"date-time":"2017-10-25T23:13:31Z","timestamp":1508973211000},"page":"911-919","source":"Crossref","is-referenced-by-count":5,"title":["ChIPWig: a random access-enabling lossless and lossy compression method for ChIP-seq data"],"prefix":"10.1093","volume":"34","author":[{"given":"Vida","family":"Ravanmehr","sequence":"first","affiliation":[{"name":"Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7282-8224","authenticated-orcid":false,"given":"Minji","family":"Kim","sequence":"additional","affiliation":[{"name":"Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiying","family":"Wang","sequence":"additional","affiliation":[{"name":"The Henry Samueli School of Engineering, Center for Pervasive Communications and Computing (CPCC), University of California, Irvine, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olgica","family":"Milenkovi\u0107","sequence":"additional","affiliation":[{"name":"Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2017,10,26]]},"reference":[{"key":"2023012712481766100_btx685-B1","doi-asserted-by":"crossref","first-page":"W369","DOI":"10.1093\/nar\/gkl198","article-title":"MEME: discovering and analyzing DNA and protein sequence motifs","volume":"34","author":"Bailey","year":"2006","journal-title":"Nucleic Acids Res"},{"key":"2023012712481766100_btx685-B2","doi-asserted-by":"crossref","first-page":"e1003326.","DOI":"10.1371\/journal.pcbi.1003326","article-title":"Practical guidelines for the comprehensive analysis of Chip-seq data","volume":"9","author":"Bailey","year":"2013","journal-title":"PLoS Comput Biol"},{"key":"2023012712481766100_btx685-B3","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1038\/nbt1010-1045","article-title":"The NIH roadmap epigenomics mapping consortium","volume":"28","author":"Bernstein","year":"2010","journal-title":"Nat. Biotechnol"},{"key":"2023012712481766100_btx685-B4","first-page":"43","author":"Cao","year":"2007"},{"key":"2023012712481766100_btx685-B5","doi-asserted-by":"crossref","first-page":"636","DOI":"10.1126\/science.1105136","article-title":"The ENCODE (ENCyclopedia of DNA elements) project","volume":"306","author":"Consortium","year":"2004","journal-title":"Science"},{"key":"2023012712481766100_btx685-B6","author":"Gallager","year":"2006"},{"key":"2023012712481766100_btx685-B7","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1007\/978-1-4615-3626-0_10","volume-title":"Vector Quantization and Signal Compression","author":"Gersho","year":"1992"},{"key":"2023012712481766100_btx685-B8","doi-asserted-by":"crossref","first-page":"2543","DOI":"10.1093\/bioinformatics\/btu330","article-title":"CWig: compressed representation of wiggle\/bedGraph format","volume":"30","author":"Hoang","year":"2014","journal-title":"Bioinformatics"},{"key":"2023012712481766100_btx685-B9","doi-asserted-by":"crossref","first-page":"2204","DOI":"10.1093\/bioinformatics\/btq351","article-title":"BigWig and bigBed: enabling browsing of large distributed datasets","volume":"26","author":"Kent","year":"2010","journal-title":"Bioinformatics"},{"key":"2023012712481766100_btx685-B10","doi-asserted-by":"crossref","first-page":"1351","DOI":"10.1038\/nbt.1508","article-title":"Design and analysis of ChIP-seq experiments for DNA-binding proteins","volume":"26","author":"Kharchenko","year":"2008","journal-title":"Nat. Biotechnol"},{"key":"2023012712481766100_btx685-B11","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1198\/jasa.2011.ap09706","article-title":"A statistical framework for the analysis of ChIP-seq data","volume":"106","author":"Kuan","year":"2011","journal-title":"J. Am. Stat. Assoc"},{"key":"2023012712481766100_btx685-B12","doi-asserted-by":"crossref","first-page":"1.","DOI":"10.1186\/gb-2011-12-8-r83","article-title":"Cistrome: an integrative platform for transcriptional regulation studies","volume":"12","author":"Liu","year":"2011","journal-title":"Genome Biol"},{"key":"2023012712481766100_btx685-B13","doi-asserted-by":"crossref","first-page":"1696","DOI":"10.1093\/bioinformatics\/btr189","article-title":"MEME-ChIP: motif analysis of large DNA datasets","volume":"27","author":"Machanick","year":"2011","journal-title":"Bioinformatics"},{"key":"2023012712481766100_btx685-B14","author":"Madrigal","year":"2016"},{"key":"2023012712481766100_btx685-B15","author":"Madrigal","year":"2016"},{"key":"2023012712481766100_btx685-B16","author":"Martin","year":"1979"},{"key":"2023012712481766100_btx685-B17","doi-asserted-by":"crossref","first-page":"31.","DOI":"10.1186\/s13059-015-0597-1","article-title":"Combinatorial activities of SHORT VEGETATIVE PHASE and FLOWERING LOCUS C define distinct modes of flowering regulation in Arabidopsis","volume":"16","author":"Mateos","year":"2015","journal-title":"Genome Biol"},{"key":"2023012712481766100_btx685-B18","first-page":"279","author":"Nakato","year":"2016"},{"key":"2023012712481766100_btx685-B19","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1038\/nrg2641","article-title":"ChIP\u2013seq: advantages and challenges of a maturing technology","volume":"10","author":"Park","year":"2009","journal-title":"Nat. Rev. Genet"},{"key":"2023012712481766100_btx685-B20","doi-asserted-by":"crossref","first-page":"e21588.","DOI":"10.1371\/journal.pone.0021588","article-title":"On the representability of complete genomes by multiple competing finite-context (Markov) models","volume":"6","author":"Pinho","year":"2011","journal-title":"PloS One"},{"key":"2023012712481766100_btx685-B21","first-page":"953","article-title":"A comprehensive comparison of tools for differential ChIP-seq analysis","volume":"17","author":"Steinhauser","year":"2016","journal-title":"Brief. Bioinf"},{"key":"2023012712481766100_btx685-B22","first-page":"261","author":"Tabus","year":"2008"},{"key":"2023012712481766100_btx685-B23","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1093\/bioinformatics\/btv561","article-title":"smallWig: parallel compression of RNA-seq WIG files","volume":"32","author":"Wang","year":"2016","journal-title":"Bioinformatics"},{"key":"2023012712481766100_btx685-B24","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.cels.2015.08.004","article-title":"Entropy-scaling search of massive biological data","volume":"1","author":"Yu","year":"2015","journal-title":"Cell Syst"},{"key":"2023012712481766100_btx685-B25","doi-asserted-by":"crossref","first-page":"R137.","DOI":"10.1186\/gb-2008-9-9-r137","article-title":"Model-based analysis of ChIP-seq (MACS)","volume":"9","author":"Zhang","year":"2008","journal-title":"Genome Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/6\/911\/48914964\/bioinformatics_34_6_911.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/6\/911\/48914964\/bioinformatics_34_6_911.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,27]],"date-time":"2023-08-27T12:10:21Z","timestamp":1693138221000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/34\/6\/911\/4566198"}},"subtitle":[],"editor":[{"given":"Bonnie","family":"Berger","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2017,10,26]]},"references-count":25,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2018,3,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btx685","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/127464","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":[[2018,3,15]]},"published":{"date-parts":[[2017,10,26]]}}}