{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:40:31Z","timestamp":1784076031050,"version":"3.55.0"},"reference-count":10,"publisher":"Oxford University Press (OUP)","issue":"19","license":[{"start":{"date-parts":[[2021,3,31]],"date-time":"2021-03-31T00:00:00Z","timestamp":1617148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100004281","name":"National Science Centre","doi-asserted-by":"publisher","award":["DEC-2017\/25\/B\/ST6\/01525"],"award-info":[{"award-number":["DEC-2017\/25\/B\/ST6\/01525"]}],"id":[{"id":"10.13039\/501100004281","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004281","name":"National Science Centre","doi-asserted-by":"publisher","award":["POIG.02.03.01-24-099\/13"],"award-info":[{"award-number":["POIG.02.03.01-24-099\/13"]}],"id":[{"id":"10.13039\/501100004281","id-type":"DOI","asserted-by":"publisher"}]},{"name":"GeCONiI\u2014Upper Silesian Center for Computational Science and Engineering"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Summary<\/jats:title>\n                    <jats:p>Variant Call Format (VCF) files with results of sequencing projects take a lot of space. We propose the VCFShark, which is able to compress VCF files up to an order of magnitude better than the de facto standards (gzipped VCF and BCF). The advantage over competitors is the greatest when compressing VCF files containing large amounts of genotype data. The processing speeds up to 100 MB\/s and main memory requirements lower than 30 GB allow to use our tool at typical workstations even for large datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>https:\/\/github.com\/refresh-bio\/vcfshark.<\/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\/btab211","type":"journal-article","created":{"date-parts":[[2021,3,30]],"date-time":"2021-03-30T15:13:57Z","timestamp":1617117237000},"page":"3358-3360","source":"Crossref","is-referenced-by-count":7,"title":["VCFShark: how to squeeze a VCF file"],"prefix":"10.1093","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9496-733X","authenticated-orcid":false,"given":"Sebastian","family":"Deorowicz","sequence":"first","affiliation":[{"name":"Faculty of Automatic Control, Electronics and Computer Science, Department of Algorithmics and Software, Silesian University of Technology , Gliwice PL-44100, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Agnieszka","family":"Danek","sequence":"additional","affiliation":[{"name":"Faculty of Automatic Control, Electronics and Computer Science, Department of Algorithmics and Software, Silesian University of Technology , Gliwice PL-44100, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marek","family":"Kokot","sequence":"additional","affiliation":[{"name":"Faculty of Automatic Control, Electronics and Computer Science, Department of Algorithmics and Software, Silesian University of Technology , Gliwice PL-44100, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2021,3,31]]},"reference":[{"key":"2023051608270139300_btab211-B1","doi-asserted-by":"crossref","first-page":"7251","DOI":"10.1093\/nar\/12.18.7251","article-title":"Similarity in gene organization and homology between proteins of animal picornaviruses and a plant comovirus suggest common ancestry of these virus families","volume":"12","author":"Argos","year":"1984","journal-title":"Nucleic Acids Res"},{"key":"2023051608270139300_btab211-B2","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41586-018-0579-z","article-title":"The UK Biobank resource with deep phenotyping and genomic data","volume":"562","author":"Bycroft","year":"2018","journal-title":"Nature"},{"key":"2023051608270139300_btab211-B3","doi-asserted-by":"crossref","first-page":"2156","DOI":"10.1093\/bioinformatics\/btr330","article-title":"The variant call format and VCFtools","volume":"27","author":"Danecek","year":"2011","journal-title":"Bioinformatics"},{"key":"2023051608270139300_btab211-B4","doi-asserted-by":"crossref","first-page":"1834","DOI":"10.1093\/bioinformatics\/bty023","article-title":"GTC: how to maintain huge genotype collections in a compressed form","volume":"34","author":"Danek","year":"2018","journal-title":"Bioinformatics"},{"key":"2023051608270139300_btab211-B5","doi-asserted-by":"crossref","first-page":"4791","DOI":"10.1093\/bioinformatics\/btz508","article-title":"GTShark: genotype compression in large projects","volume":"35","author":"Deorowicz","year":"2019","journal-title":"Bioinformatics"},{"key":"2023051608270139300_btab211-B6","doi-asserted-by":"crossref","first-page":"1266","DOI":"10.1093\/bioinformatics\/btu014","article-title":"Efficient haplotype matching and storage using the positional Burrows\u2013Wheeler transform (PBWT)","volume":"30","author":"Durbin","year":"2014","journal-title":"Bioinformatics"},{"key":"2023051608270139300_btab211-B7","doi-asserted-by":"crossref","first-page":"4091","DOI":"10.1093\/bioinformatics\/btaa290","article-title":"genozip: a fast and efficient compression tool for VCF files","volume":"36","author":"Lan","year":"2020","journal-title":"Bioinformatics"},{"key":"2023051608270139300_btab211-B8","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1093\/bioinformatics\/btv613","article-title":"BGT: efficient and flexible genotype query across many samples","volume":"32","author":"Li","year":"2016","journal-title":"Bioinformatics"},{"key":"2023051608270139300_btab211-B9","doi-asserted-by":"crossref","first-page":"1279","DOI":"10.1038\/ng.3643","article-title":"A reference panel of 64,976 haplotypes for genotype imputation","volume":"48","author":"McCarthy","year":"2016","journal-title":"Nat. Genet"},{"key":"2023051608270139300_btab211-B10","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1038\/nature15394","article-title":"An integrated map of structural variation in 2,504 human genomes","volume":"526","author":"Sudmant","year":"2015","journal-title":"Nature"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btab211\/36890526\/btab211.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/19\/3358\/50338115\/btab211.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/19\/3358\/50338115\/btab211.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T04:40:08Z","timestamp":1684212008000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/19\/3358\/6206359"}},"subtitle":[],"editor":[{"given":"Jinbo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,3,31]]},"references-count":10,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2021,10,11]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab211","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.12.18.423437","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":[[2021,10,1]]},"published":{"date-parts":[[2021,3,31]]}}}