{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T11:20:28Z","timestamp":1783682428792,"version":"3.55.0"},"reference-count":15,"publisher":"Oxford University Press (OUP)","issue":"24","license":[{"start":{"date-parts":[[2018,7,4]],"date-time":"2018-07-04T00:00:00Z","timestamp":1530662400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000142","name":"Avon Foundation for Women","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000142","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AIO"},{"DOI":"10.13039\/100001368","name":"V Foundation for Cancer Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100001368","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AIO"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>We present an updated version of our computational pipeline, PathSeq, for the discovery and identification of microbial sequences in genomic and transcriptomic libraries from eukaryotic hosts. This pipeline is available in the Genome Analysis Toolkit (GATK) as a suite of configurable tools that can report the microbial composition of DNA or RNA short-read sequencing samples and identify unknown sequences for downstream assembly of novel organisms. GATK PathSeq enables sample analysis in minutes at low cost. In addition, these tools are built with the GATK engine and Apache Spark framework, providing robust, rapid parallelization of read quality filtering, host subtraction and microbial alignment in workstation, cluster and cloud environments.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>These tools are available as a part of the GATK at https:\/\/github.com\/broadinstitute\/gatk.<\/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\/bty501","type":"journal-article","created":{"date-parts":[[2018,7,4]],"date-time":"2018-07-04T03:13:02Z","timestamp":1530673982000},"page":"4287-4289","source":"Crossref","is-referenced-by-count":110,"title":["GATK PathSeq: a customizable computational tool for the discovery and identification of microbial sequences in libraries from eukaryotic hosts"],"prefix":"10.1093","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6613-4560","authenticated-orcid":false,"given":"Mark A","family":"Walker","sequence":"first","affiliation":[{"name":"Broad Institute of Massachusetts Institute of Technology and Harvard, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chandra Sekhar","family":"Pedamallu","sequence":"additional","affiliation":[{"name":"Broad Institute of Massachusetts Institute of Technology and Harvard, Cambridge, MA, USA"},{"name":"Department of Medical Oncology and Center for Cancer Genome Discovery, Dana-Farber Cancer Institute, Boston, MA, USA"},{"name":"Department of Pathology, Harvard Medical School, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akinyemi I","family":"Ojesina","sequence":"additional","affiliation":[{"name":"University of Alabama at Birmingham (UAB), Birmingham, AL, USA"},{"name":"HudsonAlpha Institute for Biotechnology, Huntsville, AL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Susan","family":"Bullman","sequence":"additional","affiliation":[{"name":"Broad Institute of Massachusetts Institute of Technology and Harvard, Cambridge, MA, USA"},{"name":"Department of Medical Oncology and Center for Cancer Genome Discovery, Dana-Farber Cancer Institute, Boston, MA, USA"},{"name":"Department of Pathology, Harvard Medical School, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ted","family":"Sharpe","sequence":"additional","affiliation":[{"name":"Broad Institute of Massachusetts Institute of Technology and Harvard, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher W","family":"Whelan","sequence":"additional","affiliation":[{"name":"Broad Institute of Massachusetts Institute of Technology and Harvard, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Meyerson","sequence":"additional","affiliation":[{"name":"Broad Institute of Massachusetts Institute of Technology and Harvard, Cambridge, MA, USA"},{"name":"Department of Medical Oncology and Center for Cancer Genome Discovery, Dana-Farber Cancer Institute, Boston, MA, USA"},{"name":"Department of Pathology, Harvard Medical School, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2018,7,4]]},"reference":[{"key":"2023012712245290100_bty501-B1","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","article-title":"Basic local alignment search tool","volume":"215","author":"Altschul","year":"1990","journal-title":"J. Mol. Biol"},{"key":"2023012712245290100_bty501-B2","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1056\/NEJMoa1211115","article-title":"Sequence-based discovery of Bradyrhizobium enterica within cord colitis syndrome","volume":"369","author":"Bhatt","year":"2013","journal-title":"N. Engl. J. Med"},{"key":"2023012712245290100_bty501-B3","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1145\/362686.362692","article-title":"Space\/time trade-offs in hash coding with allowable errors","volume":"13","author":"Bloom","year":"1970","journal-title":"Commun. ACM"},{"key":"2023012712245290100_bty501-B4","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1093\/bioinformatics\/bts665","article-title":"VirusSeq: software to identify viruses and their integration sites using next-generation sequencing of human cancer tissue","volume":"29","author":"Chen","year":"2013","journal-title":"Bioinformatics"},{"key":"2023012712245290100_bty501-B5","doi-asserted-by":"crossref","first-page":"11332","DOI":"10.1128\/JVI.00875-07","article-title":"Human transcriptome subtraction by using short sequence tags to search for tumor viruses in conjunctival carcinoma","volume":"81","author":"Feng","year":"2007","journal-title":"J. Virol"},{"key":"2023012712245290100_bty501-B6","doi-asserted-by":"crossref","first-page":"1721","DOI":"10.1101\/gr.150151.112","article-title":"Pathoscope: species identification and strain attribution with unassembled sequencing data","volume":"23","author":"Francis","year":"2013","journal-title":"Genome Res"},{"key":"2023012712245290100_bty501-B7","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1038\/nbt.1868","article-title":"PathSeq: software to identify or discover microbes by deep sequencing of human tissue","volume":"29","author":"Kostic","year":"2011","journal-title":"Nat. Biotechnol"},{"key":"2023012712245290100_bty501-B8","author":"Li","year":"2013"},{"key":"2023012712245290100_bty501-B9","doi-asserted-by":"crossref","first-page":"btv440","DOI":"10.1093\/bioinformatics\/btv440","article-title":"FermiKit: assembly-based variant calling for Illumina resequencing data","volume":"31","author":"Li","year":"2015","journal-title":"Bioinformatics"},{"key":"2023012712245290100_bty501-B10","doi-asserted-by":"crossref","first-page":"1028","DOI":"10.1089\/cmb.2006.13.1028","article-title":"A fast and symmetric DUST implementation to mask low-complexity DNA sequences","volume":"13","author":"Morgulis","year":"2006","journal-title":"J. Comput. Biol"},{"key":"2023012712245290100_bty501-B11","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1101\/gr.107524.110","article-title":"The genome analysis toolkit: a mapreduce framework for analyzing next-generation DNA sequencing data","volume":"20","author":"McKenna","year":"2010","journal-title":"Genome Res"},{"key":"2023012712245290100_bty501-B12","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1101\/gr.171934.113","article-title":"A cloud-compatible bioinformatics pipeline for ultrarapid pathogen identification from next-generation sequencing of clinical samples","volume":"24","author":"Naccache","year":"2014","journal-title":"Genome Res"},{"key":"2023012712245290100_bty501-B13","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1038\/nature12881","article-title":"Landscape of genomic alterations in cervical carcinomas","volume":"506","author":"Ojesina","year":"2014","journal-title":"Nature"},{"key":"2023012712245290100_bty501-B15","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1038\/ng818","article-title":"Identification of foreign gene sequences by transcript filtering against the human genome","volume":"30","author":"Weber","year":"2002","journal-title":"Nat. Genet"},{"key":"2023012712245290100_bty501-B16","article-title":"Spark: cluster computing with working sets","volume":"10","author":"Zaharia","year":"2010","journal-title":"Proc. 2nd USENIX Conf. Hot Top. Cloud Comput"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/24\/4287\/48919919\/bioinformatics_34_24_4287.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/24\/4287\/48919919\/bioinformatics_34_24_4287.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:11:20Z","timestamp":1674825080000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/34\/24\/4287\/5048938"}},"subtitle":[],"editor":[{"given":"Bonnie","family":"Berger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2018,7,4]]},"references-count":15,"journal-issue":{"issue":"24","published-print":{"date-parts":[[2018,12,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty501","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,12,15]]},"published":{"date-parts":[[2018,7,4]]}}}