{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T01:38:26Z","timestamp":1780105106243,"version":"3.54.0"},"reference-count":16,"publisher":"Oxford University Press (OUP)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000272","name":"National Institute for Health Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Health Protection Research Unit in Healthcare Associated Infections and Antimicrobial Resistance","award":["NIHR200915"],"award-info":[{"award-number":["NIHR200915"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Microbial sequences generated from clinical samples are often contaminated with human host sequences that must be removed for ethical and legal reasons. Care must be taken to excise host sequences without inadvertently removing target microbial sequences to the detriment of downstream analyses such as variant calling and de novo assembly.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>To facilitate accurate host decontamination of both short and long sequencing reads, we developed Hostile, a tool capable of accurate host read removal using a laptop. We demonstrate that our approach removes at least 99.6% of real human reads and retains at least 99.989% of simulated bacterial reads. Using Hostile with a masked reference genome further increases bacterial read retention (\u226599.997%) with negligible (\u22640.001%) reduction in human read removal performance. Compared with an existing tool, Hostile removes 21%\u201323% more human short reads and 21\u201343 times fewer bacterial reads, typically in less time.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Hostile is implemented as an MIT-licensed Python package available from https:\/\/github.com\/bede\/hostile together with supplementary material.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad728","type":"journal-article","created":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T18:46:26Z","timestamp":1701283586000},"source":"Crossref","is-referenced-by-count":66,"title":["Hostile: accurate decontamination of microbial host sequences"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3480-3819","authenticated-orcid":false,"given":"Bede","family":"Constantinides","sequence":"first","affiliation":[{"name":"NDM Experimental Medicine, University of Oxford, John Radcliffe Hospital , Oxfordshire OX3 9DU, United Kingdom"},{"name":"The National Institute for Health Research Health Protection Research Unit in Healthcare Associated Infections and Antimicrobial Resistance, University of Oxford, John Radcliffe Hospital , Oxfordshire OX3 9DU, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Hunt","sequence":"additional","affiliation":[{"name":"NDM Experimental Medicine, University of Oxford, John Radcliffe Hospital , Oxfordshire OX3 9DU, United Kingdom"},{"name":"EMBL-EBI, Wellcome Genome Campus , Cambridgeshire CB10 1SD, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Derrick W","family":"Crook","sequence":"additional","affiliation":[{"name":"NDM Experimental Medicine, University of Oxford, John Radcliffe Hospital , Oxfordshire OX3 9DU, United Kingdom"},{"name":"The National Institute for Health Research Health Protection Research Unit in Healthcare Associated Infections and Antimicrobial Resistance, University of Oxford, John Radcliffe Hospital , Oxfordshire OX3 9DU, United Kingdom"},{"name":"The National Institute for Health Research Oxford Biomedical Research Centre, University of Oxford, John Radcliffe Hospital , Oxfordshire OX3 9DU, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,12,1]]},"reference":[{"key":"2023122523400653400_btad728-B1","first-page":"mgen000393","article-title":"Evaluation of methods for detecting human reads in microbial sequencing datasets","volume":"6","author":"Bush","year":"2020","journal-title":"Microb Genom"},{"key":"2023122523400653400_btad728-B2","author":"Bushnell","year":"2014"},{"key":"2023122523400653400_btad728-B3","doi-asserted-by":"crossref","first-page":"3426","DOI":"10.1016\/j.cell.2022.08.004","article-title":"High-coverage whole-genome sequencing of the expanded 1000 genomes project cohort including 602 trios","volume":"185","author":"Byrska-Bishop","year":"2022","journal-title":"Cell"},{"key":"2023122523400653400_btad728-B4","doi-asserted-by":"crossref","first-page":"giab008","DOI":"10.1093\/gigascience\/giab008","article-title":"Twelve years of SAMtools and BCFtools","volume":"10","author":"Danecek","year":"2021","journal-title":"Gigascience"},{"key":"2023122523400653400_btad728-B5","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1101\/gr.210500.116","article-title":"A reference data set of 5.4 million phased human variants validated by genetic inheritance from sequencing a three-generation 17-member pedigree","volume":"27","author":"Eberle","year":"2017","journal-title":"Genome Res"},{"key":"2023122523400653400_btad728-B6","author":"Homer","year":"2010"},{"key":"2023122523400653400_btad728-B7","doi-asserted-by":"crossref","first-page":"3291","DOI":"10.1093\/bioinformatics\/btac311","article-title":"ReadItAndKeep: rapid decontamination of SARS-CoV-2 sequencing reads","volume":"38","author":"Hunt","year":"2022","journal-title":"Bioinformatics"},{"key":"2023122523400653400_btad728-B8","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1038\/nbt.4060","article-title":"Nanopore sequencing and assembly of a human genome with ultra-long reads","volume":"36","author":"Jain","year":"2018","journal-title":"Nat Biotechnol"},{"key":"2023122523400653400_btad728-B9","doi-asserted-by":"crossref","first-page":"1721","DOI":"10.1101\/gr.210641.116","article-title":"Centrifuge: rapid and sensitive classification of metagenomic sequences","volume":"26","author":"Kim","year":"2016","journal-title":"Genome Res"},{"key":"2023122523400653400_btad728-B10","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/nmeth.1923","article-title":"Fast gapped-read alignment with Bowtie 2","volume":"9","author":"Langmead","year":"2012","journal-title":"Nat Methods"},{"key":"2023122523400653400_btad728-B11","doi-asserted-by":"crossref","first-page":"3094","DOI":"10.1093\/bioinformatics\/bty191","article-title":"Minimap2: pairwise alignment for nucleotide sequences","volume":"34","author":"Li","year":"2018","journal-title":"Bioinformatics"},{"key":"2023122523400653400_btad728-B12","doi-asserted-by":"crossref","first-page":"1674","DOI":"10.1093\/bioinformatics\/btv033","article-title":"MEGAHIT: an ultra-fast single-node solution for large and complex metagenomics assembly via succinct de Bruijn graph","volume":"31","author":"Li","year":"2015","journal-title":"Bioinformatics"},{"key":"2023122523400653400_btad728-B13","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1126\/science.abj6987","article-title":"The complete sequence of a human genome","volume":"376","author":"Nurk","year":"2022","journal-title":"Science"},{"key":"2023122523400653400_btad728-B14","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1093\/bioinformatics\/btaa835","article-title":"PBSIM2: a simulator for long-read sequencers with a novel generative model of quality scores","volume":"37","author":"Ono","year":"2021","journal-title":"Bioinformatics"},{"key":"2023122523400653400_btad728-B15","doi-asserted-by":"crossref","first-page":"3313","DOI":"10.1038\/s41467-019-11306-6","article-title":"FDA-ARGOS is a database with public quality-controlled reference genomes for diagnostic use and regulatory science","volume":"10","author":"Sichtig","year":"2019","journal-title":"Nat Commun"},{"key":"2023122523400653400_btad728-B16","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1186\/s13059-019-1891-0","article-title":"Improved metagenomic analysis with Kraken 2","volume":"20","author":"Wood","year":"2019","journal-title":"Genome Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad728\/53970806\/btad728.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/12\/btad728\/54850422\/btad728.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/12\/btad728\/54850422\/btad728.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T18:40:25Z","timestamp":1703529625000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad728\/7457481"}},"subtitle":[],"editor":[{"given":"Alfonso","family":"Valencia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,12,1]]},"references-count":16,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,12,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad728","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.07.04.547735","asserted-by":"object"}]},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,12,1]]},"published":{"date-parts":[[2023,12,1]]},"article-number":"btad728"}}