{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T16:44:18Z","timestamp":1775925858383,"version":"3.50.1"},"reference-count":11,"publisher":"Oxford University Press (OUP)","issue":"22","license":[{"start":{"date-parts":[[2019,6,24]],"date-time":"2019-06-24T00:00:00Z","timestamp":1561334400000},"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":"\u2018GeCONiI\u2014Upper Silesian Center for Computational Science and Engineering\u2019"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Summary<\/jats:title>\n                    <jats:p>Nowadays large sequencing projects handle tens of thousands of individuals. The huge files summarizing the findings definitely require compression. We propose a tool able to compress large collections of genotypes almost 30% better than the best tool to date, i.e. squeezing human genotype to less than 62 KB. Moreover, it can also compress single samples in reference to the existing database achieving comparable results.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>https:\/\/github.com\/refresh-bio\/GTShark.<\/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\/btz508","type":"journal-article","created":{"date-parts":[[2019,6,14]],"date-time":"2019-06-14T08:33:35Z","timestamp":1560501215000},"page":"4791-4793","source":"Crossref","is-referenced-by-count":21,"title":["GTShark: genotype compression in large projects"],"prefix":"10.1093","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9496-733X","authenticated-orcid":false,"given":"Sebastian","family":"Deorowicz","sequence":"first","affiliation":[{"name":"Institute of Informatics, Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology , Gliwice, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1953-0880","authenticated-orcid":false,"given":"Agnieszka","family":"Danek","sequence":"additional","affiliation":[{"name":"Institute of Informatics, Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology , Gliwice, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2019,6,24]]},"reference":[{"key":"2023013108334414700_btz508-B1","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":"2023013108334414700_btz508-B2","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":"2023013108334414700_btz508-B3","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":"2023013108334414700_btz508-B4","doi-asserted-by":"crossref","first-page":"2572","DOI":"10.1093\/bioinformatics\/btt460","article-title":"Genome compression: a novel approach for large collections","volume":"29","author":"Deorowicz","year":"2013","journal-title":"Bioinformatics"},{"key":"2023013108334414700_btz508-B5","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1093\/bioinformatics\/bty619","article-title":"CoMSA: compression of protein multiple sequence alignment files","volume":"35","author":"Deorowicz","year":"2019","journal-title":"Bioinformatics"},{"key":"2023013108334414700_btz508-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":"2023013108334414700_btz508-B7","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1038\/nature19057","article-title":"Analysis of protein-coding genetic variation in 60,706 humans","volume":"536","author":"Lek","year":"2016","journal-title":"Nature"},{"key":"2023013108334414700_btz508-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":"2023013108334414700_btz508-B9","doi-asserted-by":"crossref","first-page":"1279","DOI":"10.1038\/ng.3643","article-title":"A reference panel of 64,976 haplotypes for genome imputation","volume":"48","author":"McCarthy","year":"2016","journal-title":"Nat. Genet"},{"key":"2023013108334414700_btz508-B10","doi-asserted-by":"crossref","first-page":"2199","DOI":"10.1093\/bioinformatics\/btt362","article-title":"The human genome contracts again","volume":"29","author":"Pavlichin","year":"2013","journal-title":"Bioinformatics"},{"key":"2023013108334414700_btz508-B11","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\/btz508\/28894215\/btz508.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/22\/4791\/48977768\/bioinformatics_35_22_4791.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/22\/4791\/48977768\/bioinformatics_35_22_4791.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T12:44:06Z","timestamp":1675169046000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/35\/22\/4791\/5521623"}},"subtitle":[],"editor":[{"given":"John","family":"Hancock","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2019,6,24]]},"references-count":11,"journal-issue":{"issue":"22","published-print":{"date-parts":[[2019,11,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btz508","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/494104","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":[[2019,11,15]]},"published":{"date-parts":[[2019,6,24]]}}}