{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T00:45:00Z","timestamp":1740185100698,"version":"3.37.3"},"reference-count":13,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2020,8,7]],"date-time":"2020-08-07T00:00:00Z","timestamp":1596758400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"Science Technology and Innovation Commission of Shenzhen Municipality","award":["JCYJ20150831201123287"],"award-info":[{"award-number":["JCYJ20150831201123287"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,17]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>Rapid increase of the data size in metagenome researches has raised the demand for new tools to process large datasets efficiently. To accelerate the metagenome profiling process in the scenario of big data, we developed SOAPMetaS, a marker gene-based multiple-sample metagenome profiling tool built on Apache Spark. SOAPMetaS demonstrates high performance and scalability to process large datasets. It can process 80 samples of FASTQ data, summing up to 416 GiB, in around half an hour; and the accuracy of species profiling results of SOAPMetaS is similar to that of MetaPhlAn2. SOAPMetaS can deal with a large volume of metagenome data more efficiently than common-used single-machine tools.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Source code is implemented in Java and freely available at https:\/\/github.com\/BGI-flexlab\/SOAPMetaS.<\/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\/btaa697","type":"journal-article","created":{"date-parts":[[2020,8,4]],"date-time":"2020-08-04T19:31:10Z","timestamp":1596569470000},"page":"1021-1023","source":"Crossref","is-referenced-by-count":2,"title":["SOAPMetaS: profiling large metagenome datasets efficiently on distributed clusters"],"prefix":"10.1093","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8890-0844","authenticated-orcid":false,"given":"Shixu","family":"He","sequence":"first","affiliation":[{"name":"BGI Education Center, University of Chinese Academy of Sciences , Shenzhen 518083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhibo","family":"Huang","sequence":"additional","affiliation":[{"name":"BGI-Shenzhen , Shenzhen 518083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohan","family":"Wang","sequence":"additional","affiliation":[{"name":"BGI-Shenzhen , Shenzhen 518083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Fang","sequence":"additional","affiliation":[{"name":"BGI-Shenzhen , Shenzhen 518083, China"},{"name":"Department of Biology, University of Copenhagen , Copenhagen 2100, Departmentenmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengkang","family":"Li","sequence":"additional","affiliation":[{"name":"BGI-Shenzhen , Shenzhen 518083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Zhang","sequence":"additional","affiliation":[{"name":"BGI-Shenzhen , Shenzhen 518083, China"},{"name":"Department of Biology, University of Copenhagen , Copenhagen 2100, Departmentenmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gengyun","family":"Zhang","sequence":"additional","affiliation":[{"name":"BGI-Shenzhen , Shenzhen 518083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2020,8,7]]},"reference":[{"key":"2023051612144337400_btaa697-B1","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1093\/bioinformatics\/bty630","article-title":"Simulating Illumina metagenomic data with InSilicoSeq","volume":"35","author":"Gourl\u00e9","year":"2019","journal-title":"Bioinformatics"},{"key":"2023051612144337400_btaa697-B2","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":"2023051612144337400_btaa697-B3","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1038\/nbt.2942","article-title":"An integrated catalog of reference genes in the human gut microbiome","volume":"32","author":"Li","year":"2014","journal-title":"Nat. Biotechnol"},{"key":"2023051612144337400_btaa697-B4","doi-asserted-by":"crossref","first-page":"1861","DOI":"10.1101\/gr.081653.108","article-title":"Ethical, legal, and social considerations in conducting the Human Microbiome Project","volume":"18","author":"McGuire","year":"2008","journal-title":"Genome Res"},{"key":"2023051612144337400_btaa697-B5","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-019-08844-4","article-title":"Microbial abundance, activity and population genomic profiling with mOTUs2","volume":"10","author":"Milanese","year":"2019","journal-title":"Nat. Commun"},{"key":"2023051612144337400_btaa697-B6","doi-asserted-by":"crossref","first-page":"774","DOI":"10.1016\/j.jbi.2013.07.001","article-title":"Big data\u2019, Hadoop and cloud computing in genomics","volume":"46","author":"O\u2019Driscoll","year":"2013","journal-title":"J. Biomed. Inf"},{"key":"2023051612144337400_btaa697-B7","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1038\/nbt.3935","article-title":"Shotgun metagenomics, from sampling to analysis","volume":"35","author":"Quince","year":"2017","journal-title":"Nat. Biotechnol"},{"key":"2023051612144337400_btaa697-B8","doi-asserted-by":"crossref","first-page":"1063","DOI":"10.1038\/nmeth.4458","article-title":"Critical assessment of metagenome interpretation\u2014a benchmark of metagenomics software","volume":"14","author":"Sczyrba","year":"2017","journal-title":"Nat. Methods"},{"key":"2023051612144337400_btaa697-B9","doi-asserted-by":"crossref","first-page":"760","DOI":"10.1093\/bioinformatics\/bty733","article-title":"SpaRC: scalable sequence clustering using Apache Spark","volume":"35","author":"Shi","year":"2019","journal-title":"Bioinformatics"},{"key":"2023051612144337400_btaa697-B10","doi-asserted-by":"crossref","first-page":"902","DOI":"10.1038\/nmeth.3589","article-title":"MetaPhlAn2 for enhanced metagenomic taxonomic profiling","volume":"12","author":"Truong","year":"2015","journal-title":"Nat. Methods"},{"key":"2023051612144337400_btaa697-B11","doi-asserted-by":"crossref","first-page":"i13","DOI":"10.1093\/bioinformatics\/btz356","article-title":"Large scale microbiome profiling in the cloud","volume":"35","author":"Valdes","year":"2019","journal-title":"Bioinformatics"},{"first-page":"15","year":"2012","author":"Zaharia","key":"2023051612144337400_btaa697-B12"},{"key":"2023051612144337400_btaa697-B13","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btw750","article-title":"MetaSpark: a spark-based distributed processing tool to recruit metagenomic reads to reference genomes","volume":"33","author":"Zhou","year":"2017","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa697\/33717568\/btaa697.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/7\/1021\/50341082\/btaa697.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/37\/7\/1021\/50341082\/btaa697.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T12:16:43Z","timestamp":1684239403000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/37\/7\/1021\/5885080"}},"subtitle":[],"editor":[{"given":"Arne","family":"Elofsson","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2020,8,7]]},"references-count":13,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2021,5,17]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa697","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"type":"print","value":"1367-4803"},{"type":"electronic","value":"1367-4811"}],"subject":[],"published-other":{"date-parts":[[2021,4,1]]},"published":{"date-parts":[[2020,8,7]]}}}