{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T17:06:08Z","timestamp":1763744768671,"version":"3.37.3"},"reference-count":27,"publisher":"Oxford University Press (OUP)","issue":"17","license":[{"start":{"date-parts":[[2016,11,10]],"date-time":"2016-11-10T00:00:00Z","timestamp":1478736000000},"content-version":"vor","delay-in-days":73,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003484","name":"Heinrich Heine University D\u00fcsseldorf","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003484","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003246","name":"NWO","doi-asserted-by":"publisher","award":["639.072.039"],"award-info":[{"award-number":["639.072.039"]}],"id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Gene assembly is an important step in functional analysis of shotgun metagenomic data. Nonetheless, strain aware assembly remains a challenging task, as current assembly tools often fail to distinguish among strain variants or require closely related reference genomes of the studied species to be available.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We have developed Snowball, a novel strain aware gene assembler for shotgun metagenomic data that does not require closely related reference genomes to be available. It uses profile hidden Markov models (HMMs) of gene domains of interest to guide the assembly. Our assembler performs gene assembly of individual gene domains based on read overlaps and error correction using read quality scores at the same time, which results in very low per-base error rates.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and Implementation<\/jats:title>\n                  <jats:p>The software runs on a user-defined number of processor cores in parallel, runs on a standard laptop and is available under the GPL 3.0 license for installation under Linux or OS X at https:\/\/github.com\/hzi-bifo\/snowball.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Contact<\/jats:title>\n                  <jats:p>AMC14@helmholtz-hzi.de,a.schoenhuth@cwi.nl<\/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\/btw426","type":"journal-article","created":{"date-parts":[[2016,9,1]],"date-time":"2016-09-01T07:53:39Z","timestamp":1472716419000},"page":"i649-i657","source":"Crossref","is-referenced-by-count":19,"title":["<i>Snowball<\/i>: strain aware gene assembly of metagenomes"],"prefix":"10.1093","volume":"32","author":[{"given":"I.","family":"Gregor","sequence":"first","affiliation":[{"name":"Department of Algorithmic Bioinformatics, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf 40225, Germany"},{"name":"Computational Biology of Infection Research, Helmholtz Center for Infection Research, Braunschweig 38124, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A.","family":"Sch\u00f6nhuth","sequence":"additional","affiliation":[{"name":"Centrum Wiskunde & Informatica, Amsterdam, XG 1098, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. C.","family":"McHardy","sequence":"additional","affiliation":[{"name":"Department of Algorithmic Bioinformatics, Heinrich-Heine-University D\u00fcsseldorf, D\u00fcsseldorf 40225, Germany"},{"name":"Computational Biology of Infection Research, Helmholtz Center for Infection Research, Braunschweig 38124, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2016,8,29]]},"reference":[{"key":"2023020113313251700_btw426-B1","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1093\/bioinformatics\/btu641","article-title":"Sigma: strain-level inference of genomes from metagenomic analysis for biosurveillance","volume":"31","author":"Ahn","year":"2015","journal-title":"Bioinformatics"},{"key":"2023020113313251700_btw426-B2","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1038\/nature16192","article-title":"Functional overlap of the Arabidopsis leaf and root microbiota","volume":"528","author":"Bai","year":"2015","journal-title":"Nature"},{"key":"2023020113313251700_btw426-B3","doi-asserted-by":"crossref","first-page":"R122","DOI":"10.1186\/gb-2012-13-12-r122","article-title":"Ray Meta: scalable de novo metagenome assembly and profiling","volume":"13","author":"Boisvert","year":"2012","journal-title":"Genome Biol"},{"key":"2023020113313251700_btw426-B4","doi-asserted-by":"crossref","first-page":"810","DOI":"10.1101\/gr.7337908","article-title":"ALLPATHS: de novo assembly of whole-genome shotgun microreads","volume":"18","author":"Butler","year":"2008","journal-title":"Genome Res"},{"key":"2023020113313251700_btw426-B5","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1038\/nbt.3329","article-title":"Detection of low-abundance bacterial strains in metagenomic datasets by eigengenome partitioning","volume":"33","author":"Cleary","year":"2015","journal-title":"Nat. Biotechnol"},{"key":"2023020113313251700_btw426-B6","first-page":"35","volume-title":"Organization of the Prokaryotic Genome","author":"Cole","year":"1999"},{"key":"2023020113313251700_btw426-B7","doi-asserted-by":"crossref","first-page":"e1002195.","DOI":"10.1371\/journal.pcbi.1002195","article-title":"Accelerated profile HMM searches","volume":"7","author":"Eddy","year":"2011","journal-title":"PLoS Comput. Biol"},{"key":"2023020113313251700_btw426-B8","doi-asserted-by":"crossref","first-page":"D222","DOI":"10.1093\/nar\/gkt1223","article-title":"Pfam: the protein families database","volume":"42","author":"Finn","year":"2014","journal-title":"Nucleic Acids Res"},{"key":"2023020113313251700_btw426-B9","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1093\/bioinformatics\/btr708","article-title":"ART: a next-generation sequencing read simulator","volume":"28","author":"Huang","year":"2012","journal-title":"Bioinformatics"},{"key":"2023020113313251700_btw426-B10","doi-asserted-by":"crossref","DOI":"10.1186\/1471-2105-11-21","article-title":"Assembly complexity of prokaryotic genomes using short reads","volume":"11","author":"Kingsford","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2023020113313251700_btw426-B11","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1128\/MMBR.00009-08","article-title":"A bioinformatician's guide to metagenomics","volume":"72","author":"Kunin","year":"2008","journal-title":"Microbiol. Mol. Biol. Rev"},{"key":"2023020113313251700_btw426-B12","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1093\/bib\/bbv029","article-title":"Denoising DNA deep sequencing data-high-throughput sequencing errors and their correction","volume":"17","author":"Laehnemann","year":"2015","journal-title":"Brief. Bioinform"},{"key":"2023020113313251700_btw426-B13","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":"2023020113313251700_btw426-B14","doi-asserted-by":"crossref","first-page":"1754","DOI":"10.1093\/bioinformatics\/btp324","article-title":"Fast and accurate short read alignment with Burrows-Wheeler transform","volume":"25","author":"Li","year":"2009","journal-title":"Bioinformatics"},{"key":"2023020113313251700_btw426-B15","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1186\/2047-217X-1-18","article-title":"SOAPdenovo2: an empirically improved memory-efficient short-read de novo assembler","volume":"1","author":"Luo","year":"2012","journal-title":"GigaScience"},{"key":"2023020113313251700_btw426-B16","first-page":"043430.","article-title":"Computational pan-genomics: status, promises and challenges","author":"Marschall","year":"2016","journal-title":"BioRxiv"},{"key":"2023020113313251700_btw426-B17","doi-asserted-by":"crossref","first-page":"R112","DOI":"10.1186\/gb-2011-12-11-r112","article-title":"Evaluation of genomic high-throughput sequencing data generated on Illumina HiSeq and genome analyzer systems","volume":"12","author":"Minoche","year":"2011","journal-title":"Genome Biol"},{"key":"2023020113313251700_btw426-B18","doi-asserted-by":"crossref","first-page":"e155","DOI":"10.1093\/nar\/gks678","article-title":"MetaVelvet: an extension of Velvet assembler to de novo metagenome assembly from short sequence reads","volume":"40","author":"Namiki","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2023020113313251700_btw426-B19","doi-asserted-by":"crossref","first-page":"1420","DOI":"10.1093\/bioinformatics\/bts174","article-title":"IDBA-UD: a de novo assembler for single-cell and metagenomic sequencing data with highly uneven depth","volume":"28","author":"Peng","year":"2012","journal-title":"Bioinformatics"},{"key":"2023020113313251700_btw426-B20","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1146\/annurev.genet.38.072902.091216","article-title":"Metagenomics: genomic analysis of microbial communities","volume":"38","author":"Riesenfeld","year":"2004","journal-title":"Annu. Rev. Genet"},{"key":"2023020113313251700_btw426-B21","doi-asserted-by":"crossref","first-page":"e37","DOI":"10.1093\/nar\/gku1341","article-title":"Insight into biases and sequencing errors for amplicon sequencing with the Illumina MiSeq platform","volume":"43","author":"Schirmer","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2023020113313251700_btw426-B22","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1101\/gr.126953.111","article-title":"Efficient de novo assembly of large genomes using compressed data structures","volume":"22","author":"Simpson","year":"2012","journal-title":"Genome Res"},{"key":"2023020113313251700_btw426-B23","doi-asserted-by":"crossref","first-page":"e1003515","DOI":"10.1371\/journal.pcbi.1003515","article-title":"Viral quasispecies assembly via maximal clique enumeration","volume":"10","author":"T\u00f6pfer","year":"2014","journal-title":"PLoS Comput. Biol"},{"key":"2023020113313251700_btw426-B24","doi-asserted-by":"crossref","first-page":"1033","DOI":"10.1093\/bioinformatics\/bts079","article-title":"Phylogenomic analysis of bacterial and archaeal sequences with AMPHORA2","volume":"28","author":"Wu","year":"2012","journal-title":"Bioinformatics"},{"key":"2023020113313251700_btw426-B25","doi-asserted-by":"crossref","first-page":"i35","DOI":"10.1093\/bioinformatics\/btv231","article-title":"Reconstructing 16S rRNA genes in metagenomic data","volume":"31","author":"Yuan","year":"2015","journal-title":"Bioinformatics"},{"key":"2023020113313251700_btw426-B26","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1186\/1471-2105-12-119","article-title":"ShoRAH: estimating the genetic diversity of a mixed sample from next-generation sequencing data","volume":"12","author":"Zagordi","year":"2011","journal-title":"BMC Bioinformatics"},{"key":"2023020113313251700_btw426-B27","doi-asserted-by":"crossref","first-page":"e1003737","DOI":"10.1371\/journal.pcbi.1003737","article-title":"A scalable and accurate targeted gene assembly tool (SAT-Assembler) for next-generation sequencing data","volume":"10","author":"Zhang","year":"2014","journal-title":"PLoS Comput. Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/32\/17\/i649\/49023543\/bioinformatics_32_17_i649.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/32\/17\/i649\/49023543\/bioinformatics_32_17_i649.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T23:34:01Z","timestamp":1675294441000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/32\/17\/i649\/2450756"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,8,29]]},"references-count":27,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2016,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btw426","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"type":"print","value":"1367-4803"},{"type":"electronic","value":"1367-4811"}],"subject":[],"published-other":{"date-parts":[[2016,9,1]]},"published":{"date-parts":[[2016,8,29]]}}}