{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T03:04:36Z","timestamp":1793243076407,"version":"4.5.0"},"reference-count":51,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2017,12,6]],"date-time":"2017-12-06T00:00:00Z","timestamp":1512518400000},"content-version":"vor","delay-in-days":2,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,1,1]]},"DOI":"10.1093\/gigascience\/gix120","type":"journal-article","created":{"date-parts":[[2017,12,6]],"date-time":"2017-12-06T03:10:29Z","timestamp":1512529829000},"source":"Crossref","is-referenced-by-count":2161,"title":["SOAPnuke: a MapReduce acceleration-supported software for integrated quality control and preprocessing of high-throughput sequencing data"],"prefix":"10.1093","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9246-1829","authenticated-orcid":false,"given":"Yuxin","family":"Chen","sequence":"first","affiliation":[{"name":"BGI-Shenzhen, Shenzhen 518083"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongsheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Geneplus-Beijing, Beijing 102206"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunmei","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Oncology, Fujian Medical University Union Hospital, Fuzhou 350001"},{"name":"Fujian Key Laboratory of Translational Cancer Medicine, Fuzhou 350014"},{"name":"Department of Stem Cell Research Institute, Fujian Medical University Stem Cell Research Institute, Fuzhou 350000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2750-6517","authenticated-orcid":false,"given":"Zhibo","family":"Huang","sequence":"additional","affiliation":[{"name":"BGI-Shenzhen, Shenzhen 518083"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Zhang","sequence":"additional","affiliation":[{"name":"BGI-Shenzhen, Shenzhen 518083"},{"name":"Collaborative Innovation Center of High Performance Computing, National University of Defense Technology, Changsha 410073"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6864-5644","authenticated-orcid":false,"given":"Shengkang","family":"Li","sequence":"additional","affiliation":[{"name":"BGI-Shenzhen, Shenzhen 518083"},{"name":"Collaborative Innovation Center of High Performance Computing, National University of Defense Technology, Changsha 410073"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Li","sequence":"additional","affiliation":[{"name":"BGI-Shenzhen, Shenzhen 518083"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Ye","sequence":"additional","affiliation":[{"name":"BGI-Shenzhen, Shenzhen 518083"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Yu","sequence":"additional","affiliation":[{"name":"Intel China Ltd., Shanghai 200336"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuo","family":"Li","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Hospital of Chinese Medicine, Guangzhou 510120"},{"name":"Department of Surgery, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuqing","family":"Zhang","sequence":"additional","affiliation":[{"name":"BGI-Shenzhen, Shenzhen 518083"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"BGI-Shenzhen, Shenzhen 518083"},{"name":"James D. Watson Institute of Genome Sciences, Hangzhou 310058, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0858-3410","authenticated-orcid":false,"given":"Huanming","family":"Yang","sequence":"additional","affiliation":[{"name":"BGI-Shenzhen, Shenzhen 518083"},{"name":"James D. Watson Institute of Genome Sciences, Hangzhou 310058, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5954-3435","authenticated-orcid":false,"given":"Lin","family":"Fang","sequence":"additional","affiliation":[{"name":"BGI-Shenzhen, Shenzhen 518083"},{"name":"Collaborative Innovation Center of High Performance Computing, National University of Defense Technology, Changsha 410073"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Oncology, Fujian Medical University Union Hospital, Fuzhou 350001"},{"name":"Fujian Key Laboratory of Translational Cancer Medicine, Fuzhou 350014"},{"name":"Department of Stem Cell Research Institute, Fujian Medical University Stem Cell Research Institute, Fuzhou 350000"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2017,12,4]]},"reference":[{"key":"key\n\t\t\t\t20180415221413_bib1","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1007\/978-1-60327-563-7_5","article-title":"Applications of ultra-high-throughput sequencing","volume":"553","author":"Fox","year":"2009","journal-title":"Methods Mol Biol"},{"issue":"1","key":"key\n\t\t\t\t20180415221413_bib2","doi-asserted-by":"crossref","first-page":"640-","DOI":"10.1038\/msb.2012.61","article-title":"High-throughput sequencing for biology and medicine","volume":"9","author":"Soon","year":"2014","journal-title":"Mol Syst Biol"},{"issue":"7","key":"key\n\t\t\t\t20180415221413_bib3","doi-asserted-by":"crossref","first-page":"e1002195","DOI":"10.1371\/journal.pbio.1002195","article-title":"Big data: astronomical or genomical?","volume":"13","author":"Stephens","year":"2015","journal-title":"PLoS Biol"},{"issue":"6","key":"key\n\t\t\t\t20180415221413_bib4","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1093\/bib\/bbt069","article-title":"Three-stage quality control strategies for DNA re-sequencing data","volume":"15","author":"Guo","year":"2014","journal-title":"Brief Bioinformatics"},{"issue":"7","key":"key\n\t\t\t\t20180415221413_bib5","doi-asserted-by":"crossref","first-page":"1679","DOI":"10.1111\/mec.12680","article-title":"Prevention, diagnosis and treatment of high-throughput sequencing data pathologies","volume":"23","author":"Zhou","year":"2014","journal-title":"Mol Ecol"},{"issue":"6","key":"key\n\t\t\t\t20180415221413_bib6","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1093\/bioinformatics\/btr026","article-title":"Quality control and preprocessing of metagenomic datasets","volume":"27","author":"Schmieder","year":"2011","journal-title":"Bioinformatics"},{"issue":"19","key":"key\n\t\t\t\t20180415221413_bib7","doi-asserted-by":"crossref","first-page":"2252","DOI":"10.1093\/bioinformatics\/btn428","article-title":"A toolkit for analysing large-scale plant small RNA datasets","volume":"24","author":"Moxon","year":"2008","journal-title":"Bioinformatics"},{"key":"key\n\t\t\t\t20180415221413_bib8","author":"Gordon"},{"issue":"1","key":"key\n\t\t\t\t20180415221413_bib9","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"},{"issue":"6","key":"key\n\t\t\t\t20180415221413_bib10","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1016\/S1672-0229(11)60027-2","article-title":"BIGpre: a quality assessment package for next-generation sequencing data","volume":"9","author":"Zhang","year":"2011","journal-title":"Genomics Proteomics Bioinformatics"},{"key":"key\n\t\t\t\t20180415221413_bib11","volume-title":"ea-utils: Command-Line Tools for Processing Biological Sequencing Data","author":"Aronesty","year":"2011"},{"issue":"1","key":"key\n\t\t\t\t20180415221413_bib12","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/1471-2105-14-33","article-title":"HTQC: a fast quality control toolkit for Illumina sequencing data","volume":"14","author":"Yang","year":"2013","journal-title":"BMC Bioinformatics"},{"key":"key\n\t\t\t\t20180415221413_bib13","article-title":"seqtk: toolkit for processing sequences in FASTA\/Q formats","author":"Li"},{"issue":"4","key":"key\n\t\t\t\t20180415221413_bib14","doi-asserted-by":"crossref","first-page":"e60234","DOI":"10.1371\/journal.pone.0060234","article-title":"QC-Chain: fast and holistic quality control method for next-generation sequencing data","volume":"8","author":"Zhou","year":"2013","journal-title":"PLoS One"},{"issue":"1","key":"key\n\t\t\t\t20180415221413_bib15","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.gpb.2014.01.002","article-title":"Meta-QC-Chain: comprehensive and fast quality control method for metagenomic data","volume":"12","author":"Zhou","year":"2014","journal-title":"Genomics Proteomics Bioinformatics"},{"issue":"2","key":"key\n\t\t\t\t20180415221413_bib16","doi-asserted-by":"crossref","first-page":"e30619","DOI":"10.1371\/journal.pone.0030619","article-title":"NGS QC Toolkit: a toolkit for quality control of next generation sequencing data","volume":"7","author":"Patel","year":"2012","journal-title":"PLoS One"},{"key":"key\n\t\t\t\t20180415221413_bib17","volume-title":"FastQC: a quality control tool for high throughput sequence data","author":"Simon"},{"issue":"1","key":"key\n\t\t\t\t20180415221413_bib18","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"},{"issue":"1","key":"key\n\t\t\t\t20180415221413_bib19","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1186\/1471-2105-11-38","article-title":"SeqTrim: a high-throughput pipeline for preprocessing any type of sequence reads","volume":"11","author":"Falgueras","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"key\n\t\t\t\t20180415221413_bib20","volume-title":"SeqPrep: tool for stripping adaptors and\/or merging paired reads with overlap into single reads","author":"St John"},{"issue":"2","key":"key\n\t\t\t\t20180415221413_bib21","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.ygeno.2011.05.009","article-title":"Btrim: a fast, lightweight adapter and quality trimming program for next-generation sequencing technologies","volume":"98","author":"Kong","year":"2011","journal-title":"Genomics"},{"issue":"W1","key":"key\n\t\t\t\t20180415221413_bib22","doi-asserted-by":"crossref","first-page":"W622","DOI":"10.1093\/nar\/gks540","article-title":"RobiNA: a user-friendly, integrated software solution for RNA-seq-based transcriptomics","volume":"40","author":"Lohse","year":"2012","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"key\n\t\t\t\t20180415221413_bib23","doi-asserted-by":"crossref","first-page":"pp","DOI":"10.14806\/ej.17.1.200","article-title":"Cutadapt removes adapter sequences from high-throughput sequencing reads","volume":"17","author":"Martin","year":"2011","journal-title":"EMBnet J"},{"issue":"1","key":"key\n\t\t\t\t20180415221413_bib24","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1186\/s13104-016-1900-2","article-title":"AdapterRemoval v2: rapid adapter trimming, identification, and read merging","volume":"9","author":"Schubert","year":"2016","journal-title":"BMC Res Notes"},{"issue":"3","key":"key\n\t\t\t\t20180415221413_bib25","first-page":"895","article-title":"FLEXBAR-flexible barcode and adapter processing for next-generation sequencing platforms","volume":"1","author":"Dodt","year":"2012","journal-title":"Biology (Basel)"},{"issue":"Suppl 1","key":"key\n\t\t\t\t20180415221413_bib26","doi-asserted-by":"crossref","first-page":"S2","DOI":"10.1186\/1471-2105-16-S1-S2","article-title":"PEAT: an intelligent and efficient paired-end sequencing adapter trimming algorithm","volume":"16","author":"Li","year":"2015","journal-title":"BMC Bioinformatics"},{"issue":"15","key":"key\n\t\t\t\t20180415221413_bib27","doi-asserted-by":"crossref","first-page":"2114","DOI":"10.1093\/bioinformatics\/btu170","article-title":"Trimmomatic: a flexible trimmer for Illumina sequence data","volume":"30","author":"Bolger","year":"2014","journal-title":"Bioinformatics"},{"issue":"1","key":"key\n\t\t\t\t20180415221413_bib28","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1186\/s12859-016-1069-7","article-title":"SeqPurge: highly-sensitive adapter trimming for paired-end NGS data","volume":"17","author":"Sturm","year":"2016","journal-title":"BMC Bioinformatics"},{"issue":"1","key":"key\n\t\t\t\t20180415221413_bib29","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1186\/1471-2105-15-182","article-title":"Skewer: a fast and accurate adapter trimmer for next-generation sequencing paired-end reads","volume":"15","author":"Jiang","year":"2014","journal-title":"BMC Bioinformatics"},{"issue":"S3","key":"key\n\t\t\t\t20180415221413_bib30","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1186\/s12859-017-1469-3","article-title":"AfterQC: automatic filtering, trimming, error removing and quality control for fastq data","volume":"18","author":"Chen","year":"2017","journal-title":"BMC Bioinformatics"},{"key":"key\n\t\t\t\t20180415221413_bib31","volume-title":"BBMap: A Fast, Accurate, Splice-Aware Aligner","author":"BUSHNELL","year":"2014"},{"key":"key\n\t\t\t\t20180415221413_bib32","volume-title":"Sickle: A sliding-window, adaptive, quality-based trimming tool for FastQ files","author":"Joshi"},{"key":"key\n\t\t\t\t20180415221413_bib33","volume-title":"fqtrim: trimming&filtering of next-gen reads","author":"Pertea"},{"key":"key\n\t\t\t\t20180415221413_bib34","volume-title":"Scythe: a Bayesian adapter trimmer","author":"Vince"},{"issue":"4","key":"key\n\t\t\t\t20180415221413_bib35","doi-asserted-by":"crossref","first-page":"566","DOI":"10.1093\/bioinformatics\/btt702","article-title":"NextClip: an analysis and read preparation tool for Nextera long mate pair libraries","volume":"30","author":"Leggett","year":"2014","journal-title":"Bioinformatics"},{"issue":"5\u20136","key":"key\n\t\t\t\t20180415221413_bib36","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1016\/j.ygeno.2013.07.011","article-title":"AlienTrimmer: a tool to quickly and accurately trim off multiple short contaminant sequences from high-throughput sequencing reads","volume":"102","author":"Criscuolo","year":"2013","journal-title":"Genomics"},{"issue":"8","key":"key\n\t\t\t\t20180415221413_bib37","doi-asserted-by":"crossref","first-page":"R86","DOI":"10.1186\/gb-2010-11-8-r86","article-title":"Galaxy: a comprehensive approach for supporting accessible, reproducible, and transparent computational research in the life sciences","volume":"11","author":"Goecks","year":"2010","journal-title":"Genome Biol"},{"key":"key\n\t\t\t\t20180415221413_bib38","volume-title":"R: A Language and Environment for Statistical Computing","author":"Team","year":"2013"},{"key":"key\n\t\t\t\t20180415221413_bib39","volume-title":"NextSeq 500 system overview","author":"Illumina"},{"issue":"5","key":"key\n\t\t\t\t20180415221413_bib40","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/gigascience\/gix024","article-title":"A reference human genome dataset of the BGISEQ-500 sequencer","volume":"6","author":"Huang","year":"2017","journal-title":"Gigascience"},{"issue":"3","key":"key\n\t\t\t\t20180415221413_bib41","doi-asserted-by":"crossref","first-page":"e58680","DOI":"10.1371\/journal.pone.0058680","article-title":"Digital gene expression tag profiling analysis of the gene expression patterns regulating the early stage of mouse spermatogenesis","volume":"8","author":"Zhang","year":"2013","journal-title":"PLoS One"},{"issue":"6","key":"key\n\t\t\t\t20180415221413_bib42","doi-asserted-by":"crossref","first-page":"950","DOI":"10.1093\/bib\/bbv019","article-title":"Optimization of miRNA-seq data preprocessing","volume":"16","author":"Tam","year":"2015","journal-title":"Brief Bioinformatics"},{"key":"key\n\t\t\t\t20180415221413_bib43","doi-asserted-by":"crossref","first-page":"160025","DOI":"10.1038\/sdata.2016.25","article-title":"Extensive sequencing of seven human genomes to characterize benchmark reference materials","volume":"3","author":"Zook","year":"2016","journal-title":"Sci Data"},{"key":"key\n\t\t\t\t20180415221413_bib44","author":"GATK best practices"},{"key":"key\n\t\t\t\t20180415221413_bib45","volume-title":"GIAB","author":"NISTv3.3.2","year":"2017"},{"issue":"3","key":"key\n\t\t\t\t20180415221413_bib46","doi-asserted-by":"crossref","first-page":"e58680","DOI":"10.1371\/journal.pone.0058680","article-title":"Digital gene expression tag profiling analysis of the gene expression patterns regulating the early stage of mouse spermatogenesis","volume":"8","author":"Zhang","year":"2013","journal-title":"PLoS One"},{"issue":"12","key":"key\n\t\t\t\t20180415221413_bib47","doi-asserted-by":"crossref","first-page":"e15224","DOI":"10.1371\/journal.pone.0015224","article-title":"Integrated profiling of microRNAs and mRNAs: microRNAs located on Xq27.3 associate with clear cell renal cell carcinoma","volume":"5","author":"Zhou","year":"2010","journal-title":"PLoS One"},{"issue":"11","key":"key\n\t\t\t\t20180415221413_bib48","doi-asserted-by":"crossref","first-page":"e73541","DOI":"10.1371\/journal.pone.0073541","article-title":"The suppression of WRKY44 by GIGANTEA-miR172 pathway is involved in drought response of Arabidopsis thaliana","volume":"8","author":"Han","year":"2013","journal-title":"PLoS One"},{"issue":"4","key":"key\n\t\t\t\t20180415221413_bib49","doi-asserted-by":"crossref","first-page":"e2184","DOI":"10.1038\/cddis.2016.91","article-title":"The cytoskeleton adaptor protein ankyrin-1 is upregulated by p53 following DNA damage and alters cell migration","volume":"7","author":"Hall","year":"2016","journal-title":"Cell Death Dis"},{"issue":"1","key":"key\n\t\t\t\t20180415221413_bib50","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1111\/tpj.13090","article-title":"A highly specific microRNA-mediated mechanism silences LTR retrotransposons of strawberry","volume":"85","author":"Surbanovski","year":"2016","journal-title":"Plant J"},{"key":"key\n\t\t\t\t20180415221413_bib51","author":"Chen","year":"2017"}],"container-title":["GigaScience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/gigascience\/article-pdf\/7\/1\/gix120\/24620478\/gix120.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,4,15]],"date-time":"2018-04-15T22:14:43Z","timestamp":1523830483000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/gigascience\/article\/doi\/10.1093\/gigascience\/gix120\/4689118"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12,4]]},"references-count":51,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2017,12,4]]},"published-print":{"date-parts":[[2018,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/gigascience\/gix120","relation":{},"ISSN":["2047-217X"],"issn-type":[{"value":"2047-217X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,1]]},"published":{"date-parts":[[2017,12,4]]}}}