{"id":"https://openalex.org/W3047746238","doi":"https://doi.org/10.1093/bioinformatics/btaa697","title":"SOAPMetaS: profiling large metagenome datasets efficiently on distributed clusters","display_name":"SOAPMetaS: profiling large metagenome datasets efficiently on distributed clusters","publication_year":2020,"publication_date":"2020-08-04","ids":{"openalex":"https://openalex.org/W3047746238","doi":"https://doi.org/10.1093/bioinformatics/btaa697","mag":"3047746238","pmid":"https://pubmed.ncbi.nlm.nih.gov/32766813"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaa697","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa697","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/7/1021/37947470/btaa697.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/37/7/1021/37947470/btaa697.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103102516","display_name":"Shixu He","orcid":"https://orcid.org/0000-0001-8890-0844"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shixu He","raw_affiliation_strings":["BGI Education Center, University of Chinese Academy of Sciences , Shenzhen 518083, China"],"raw_orcid":"https://orcid.org/0000-0001-8890-0844","affiliations":[{"raw_affiliation_string":"BGI Education Center, University of Chinese Academy of Sciences , Shenzhen 518083, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072904831","display_name":"Zhibo Huang","orcid":"https://orcid.org/0000-0002-2750-6517"},"institutions":[{"id":"https://openalex.org/I100135526","display_name":"BGI Group (China)","ror":"https://ror.org/045pn2j94","country_code":"CN","type":"company","lineage":["https://openalex.org/I100135526"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibo Huang","raw_affiliation_strings":["BGI-Shenzhen , Shenzhen 518083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BGI-Shenzhen , Shenzhen 518083, China","institution_ids":["https://openalex.org/I100135526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354392","display_name":"Xiaohan Wang","orcid":"https://orcid.org/0000-0003-4658-4171"},"institutions":[{"id":"https://openalex.org/I100135526","display_name":"BGI Group (China)","ror":"https://ror.org/045pn2j94","country_code":"CN","type":"company","lineage":["https://openalex.org/I100135526"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohan Wang","raw_affiliation_strings":["BGI-Shenzhen , Shenzhen 518083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BGI-Shenzhen , Shenzhen 518083, China","institution_ids":["https://openalex.org/I100135526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101738424","display_name":"Lin Fang","orcid":"https://orcid.org/0000-0002-5954-3435"},"institutions":[{"id":"https://openalex.org/I100135526","display_name":"BGI Group (China)","ror":"https://ror.org/045pn2j94","country_code":"CN","type":"company","lineage":["https://openalex.org/I100135526"]},{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["CN","DK"],"is_corresponding":false,"raw_author_name":"Lin Fang","raw_affiliation_strings":["BGI-Shenzhen , Shenzhen 518083, China","Department of Biology, University of Copenhagen , Copenhagen 2100, Departmentenmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BGI-Shenzhen , Shenzhen 518083, China","institution_ids":["https://openalex.org/I100135526"]},{"raw_affiliation_string":"Department of Biology, University of Copenhagen , Copenhagen 2100, Departmentenmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103145930","display_name":"Shengkang Li","orcid":"https://orcid.org/0000-0002-6864-5644"},"institutions":[{"id":"https://openalex.org/I100135526","display_name":"BGI Group (China)","ror":"https://ror.org/045pn2j94","country_code":"CN","type":"company","lineage":["https://openalex.org/I100135526"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengkang Li","raw_affiliation_strings":["BGI-Shenzhen , Shenzhen 518083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BGI-Shenzhen , Shenzhen 518083, China","institution_ids":["https://openalex.org/I100135526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100419755","display_name":"Yong Zhang","orcid":"https://orcid.org/0000-0001-9950-1793"},"institutions":[{"id":"https://openalex.org/I100135526","display_name":"BGI Group (China)","ror":"https://ror.org/045pn2j94","country_code":"CN","type":"company","lineage":["https://openalex.org/I100135526"]},{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["CN","DK"],"is_corresponding":true,"raw_author_name":"Yong Zhang","raw_affiliation_strings":["BGI-Shenzhen , Shenzhen 518083, China","Department of Biology, University of Copenhagen , Copenhagen 2100, Departmentenmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BGI-Shenzhen , Shenzhen 518083, China","institution_ids":["https://openalex.org/I100135526"]},{"raw_affiliation_string":"Department of Biology, University of Copenhagen , Copenhagen 2100, Departmentenmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048952229","display_name":"Gengyun Zhang","orcid":"https://orcid.org/0000-0003-2638-7859"},"institutions":[{"id":"https://openalex.org/I100135526","display_name":"BGI Group (China)","ror":"https://ror.org/045pn2j94","country_code":"CN","type":"company","lineage":["https://openalex.org/I100135526"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gengyun Zhang","raw_affiliation_strings":["BGI-Shenzhen , Shenzhen 518083, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BGI-Shenzhen , Shenzhen 518083, China","institution_ids":["https://openalex.org/I100135526"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5048952229","https://openalex.org/A5100419755"],"corresponding_institution_ids":["https://openalex.org/I100135526","https://openalex.org/I124055696"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.0834,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.4489241,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"37","issue":"7","first_page":"1021","last_page":"1023"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.7260000109672546,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.7260000109672546,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.032499998807907104,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10269","display_name":"Epigenetics and DNA Methylation","score":0.024000000208616257,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.8580237030982971},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.8491643667221069},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6280160546302795},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.561783492565155},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4162408709526062},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.23723134398460388},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.12640628218650818},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.06456232070922852},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.060116320848464966}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.8580237030982971},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.8491643667221069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6280160546302795},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.561783492565155},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4162408709526062},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.23723134398460388},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12640628218650818},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.06456232070922852},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.060116320848464966}],"mesh":[{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077558","descriptor_name":"Big Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btaa697","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa697","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/7/1021/37947470/btaa697.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:32766813","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32766813","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/8eede653-1371-4487-ab46-c1b208328924","is_oa":false,"landing_page_url":"https://researchprofiles.ku.dk/da/publications/8eede653-1371-4487-ab46-c1b208328924","pdf_url":null,"source":{"id":"https://openalex.org/S4306401983","display_name":"Research at the University of Copenhagen (University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I124055696","host_organization_name":"University of Copenhagen","host_organization_lineage":["https://openalex.org/I124055696"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"He , S , Huang , Z , Wang , X , Fang , L , Li , S , Zhang , Y & Zhang , G 2021 , ' SOAPMetaS : profiling large metagenome datasets efficiently on distributed clusters ' , Bioinformatics , vol. 37 , no. 7 , pp. 1021-1023 . https://doi.org/10.1093/bioinformatics/btaa697","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaa697","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa697","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/37/7/1021/37947470/btaa697.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3047746238.pdf","grobid_xml":"https://content.openalex.org/works/W3047746238.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1703384511","https://openalex.org/W1977046764","https://openalex.org/W2097124003","https://openalex.org/W2104290137","https://openalex.org/W2170551349","https://openalex.org/W2568237575","https://openalex.org/W2754579667","https://openalex.org/W2773939681","https://openalex.org/W2884944393","https://openalex.org/W2920716817","https://openalex.org/W2950686248","https://openalex.org/W2961863736"],"related_works":["https://openalex.org/W2210738511","https://openalex.org/W2487541429","https://openalex.org/W1910109602","https://openalex.org/W2080583581","https://openalex.org/W4297131566","https://openalex.org/W2017364432","https://openalex.org/W2329606903","https://openalex.org/W3195915274","https://openalex.org/W4285082713","https://openalex.org/W2344981695"],"abstract_inverted_index":{"SUMMARY:":[0],"Rapid":[1],"increase":[2],"of":[3,31,63,79,83,89,98],"the":[4,12,24,29,77],"data":[5,100,124],"size":[6],"in":[7,28,71,114],"metagenome":[8,25,41,99],"researches":[9],"has":[10],"raised":[11],"demand":[13],"for":[14],"new":[15],"tools":[16],"to":[17,54,68,87],"process":[18,27,55,60],"large":[19,56,96],"datasets":[20],"efficiently.":[21],"To":[22],"accelerate":[23],"profiling":[26,42,81],"scenario":[30],"big":[32],"data,":[33,65],"we":[34],"developed":[35],"SOAPMetaS,":[36],"a":[37,95],"marker":[38],"gene-based":[39],"multiple-sample":[40],"tool":[43],"built":[44],"on":[45],"Apache":[46],"Spark.":[47],"SOAPMetaS":[48,84,91],"demonstrates":[49],"high":[50],"performance":[51],"and":[52,76,116],"scalability":[53],"datasets.":[57],"It":[58],"can":[59,92],"80":[61],"samples":[62],"FASTQ":[64],"summing":[66],"up":[67],"416":[69],"GiB,":[70],"around":[72],"half":[73],"an":[74],"hour;":[75],"accuracy":[78],"species":[80],"results":[82],"is":[85,112],"similar":[86],"that":[88],"MetaPhlAn2.":[90],"deal":[93],"with":[94],"volume":[97],"more":[101],"efficiently":[102],"than":[103],"common-used":[104],"single-machine":[105],"tools.":[106],"AVAILABILITY":[107],"AND":[108],"IMPLEMENTATION:":[109],"Source":[110],"code":[111],"implemented":[113],"Java":[115],"freely":[117],"available":[118,126],"at":[119,127],"https://github.com/BGI-flexlab/SOAPMetaS.":[120],"SUPPLEMENTARY":[121],"INFORMATION:":[122],"Supplementary":[123],"are":[125],"Bioinformatics":[128],"online.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
