{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T07:50:20Z","timestamp":1776325820055,"version":"3.50.1"},"reference-count":7,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2016,10,2]],"date-time":"2016-10-02T00:00:00Z","timestamp":1475366400000},"content-version":"vor","delay-in-days":2074,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/2.0\/uk\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,3,15]]},"abstract":"Abstract<\/jats:title>\n Summary: Here, we present PRINSEQ for easy and rapid quality control and data preprocessing of genomic and metagenomic datasets. Summary statistics of FASTA (and QUAL) or FASTQ files are generated in tabular and graphical form and sequences can be filtered, reformatted and trimmed by a variety of options to improve downstream analysis.<\/jats:p>\n Availability and Implementation: This open-source application was implemented in Perl and can be used as a stand alone version or accessed online through a user-friendly web interface. The source code, user help and additional information are available at http:\/\/prinseq.sourceforge.net\/.<\/jats:p>\n Contact: \u00a0rschmied@sciences.sdsu.edu; redwards@cs.sdsu.edu<\/jats:p>","DOI":"10.1093\/bioinformatics\/btr026","type":"journal-article","created":{"date-parts":[[2011,1,29]],"date-time":"2011-01-29T02:52:41Z","timestamp":1296269561000},"page":"863-864","source":"Crossref","is-referenced-by-count":4552,"title":["Quality control and preprocessing of metagenomic datasets"],"prefix":"10.1093","volume":"27","author":[{"given":"Robert","family":"Schmieder","sequence":"first","affiliation":[{"name":"1 Department of Computer Science, 2Computational Science Research Center, San Diego State University, San Diego, CA 92182 and 3Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, IL 60439, USA"},{"name":"1 Department of Computer Science, 2Computational Science Research Center, San Diego State University, San Diego, CA 92182 and 3Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, IL 60439, USA"}]},{"given":"Robert","family":"Edwards","sequence":"additional","affiliation":[{"name":"1 Department of Computer Science, 2Computational Science Research Center, San Diego State University, San Diego, CA 92182 and 3Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, IL 60439, USA"},{"name":"1 Department of Computer Science, 2Computational Science Research Center, San Diego State University, San Diego, CA 92182 and 3Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, IL 60439, USA"}]}],"member":"286","published-online":{"date-parts":[[2011,1,28]]},"reference":[{"key":"2023012511540334800_B1","doi-asserted-by":"crossref","first-page":"1783","DOI":"10.1093\/bioinformatics\/btq281","article-title":"Manipulation of FASTQ data with Galaxy","volume":"26","author":"Blankenberg","year":"2010","journal-title":"Bioinformatics"},{"key":"2023012511540334800_B2","doi-asserted-by":"crossref","first-page":"1358","DOI":"10.1073\/pnas.89.4.1358","article-title":"Over- and under-representation of short oligonucleotides in DNA sequences","volume":"89","author":"Burge","year":"1992","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"2023012511540334800_B3","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1186\/1471-2105-11-485","article-title":"SolexaQA: at-a-glance quality assessment of Illumina second-generation sequencing data","volume":"11","author":"Cox","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2023012511540334800_B4","doi-asserted-by":"crossref","first-page":"1314","DOI":"10.1038\/ismej.2009.72","article-title":"Systematic artifacts in metagenomes from complex microbial communities","volume":"3","author":"Gomez-Alvarez","year":"2009","journal-title":"ISME J."},{"key":"2023012511540334800_B5","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":"2023012511540334800_B6","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1186\/1471-2105-11-341","article-title":"TagCleaner: identification and removal of tag sequences from genomic and metagenomic datasets","volume":"11","author":"Schmieder","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2023012511540334800_B7","doi-asserted-by":"crossref","first-page":"1752","DOI":"10.1111\/j.1462-2920.2009.01901.x","article-title":"Metagenomic signatures of 86 microbial and viral metagenomes","volume":"11","author":"Willner","year":"2009","journal-title":"Envir. Microbiol."}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/27\/6\/863\/48863248\/bioinformatics_27_6_863.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/27\/6\/863\/48863248\/bioinformatics_27_6_863.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,25]],"date-time":"2023-01-25T11:54:55Z","timestamp":1674647695000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/27\/6\/863\/236283"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,1,28]]},"references-count":7,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2011,3,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btr026","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2011,3,15]]},"published":{"date-parts":[[2011,1,28]]}}}