{"id":"https://openalex.org/W4206184519","doi":"https://doi.org/10.1186/s12859-021-04227-z","title":"MetaCRS: unsupervised clustering of contigs with the recursive strategy of reducing metagenomic dataset\u2019s complexity","display_name":"MetaCRS: unsupervised clustering of contigs with the recursive strategy of reducing metagenomic dataset\u2019s complexity","publication_year":2022,"publication_date":"2022-01-20","ids":{"openalex":"https://openalex.org/W4206184519","doi":"https://doi.org/10.1186/s12859-021-04227-z","pmid":"https://pubmed.ncbi.nlm.nih.gov/35045830"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-021-04227-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-04227-z","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-04227-z","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-04227-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055263549","display_name":"Zhongjun Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongjun Jiang","raw_affiliation_strings":["College of Information Science and Technology, Ningbo University, Ningbo, 315211, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Ningbo University, Ningbo, 315211, China","institution_ids":["https://openalex.org/I109935558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072919277","display_name":"Xiaobo Li","orcid":"https://orcid.org/0000-0003-0607-5567"},"institutions":[{"id":"https://openalex.org/I135237710","display_name":"Zhejiang Normal University","ror":"https://ror.org/01vevwk45","country_code":"CN","type":"education","lineage":["https://openalex.org/I135237710"]},{"id":"https://openalex.org/I3129496460","display_name":"Lishui University","ror":"https://ror.org/0418kp584","country_code":"CN","type":"education","lineage":["https://openalex.org/I3129496460"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaobo Li","raw_affiliation_strings":["College of Engineering, Lishui University, Lishui, 323000, China. lxb@zjnu.edu.cn","College of Mathematics and Computer Science, Zhejiang Normal University, Jinhua, 321004, China. lxb@zjnu.edu.cn","College of Mathematics and Computer Science, Zhejiang Normal University, Jinhua, 321004, China"],"raw_orcid":"https://orcid.org/0000-0003-0607-5567","affiliations":[{"raw_affiliation_string":"College of Engineering, Lishui University, Lishui, 323000, China. lxb@zjnu.edu.cn","institution_ids":["https://openalex.org/I3129496460"]},{"raw_affiliation_string":"College of Mathematics and Computer Science, Zhejiang Normal University, Jinhua, 321004, China. lxb@zjnu.edu.cn","institution_ids":["https://openalex.org/I135237710"]},{"raw_affiliation_string":"College of Mathematics and Computer Science, Zhejiang Normal University, Jinhua, 321004, China","institution_ids":["https://openalex.org/I135237710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013717269","display_name":"Lijun Guo","orcid":"https://orcid.org/0000-0002-6133-9564"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijun Guo","raw_affiliation_strings":["College of Information Science and Technology, Ningbo University, Ningbo, 315211, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Ningbo University, Ningbo, 315211, China","institution_ids":["https://openalex.org/I109935558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072919277"],"corresponding_institution_ids":["https://openalex.org/I135237710","https://openalex.org/I3129496460"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.1567,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.40693072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"22","issue":"S12","first_page":"315","last_page":"315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.49320000410079956,"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":0.49320000410079956,"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":0.2467000037431717,"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/T10066","display_name":"Gut microbiota and health","score":0.07280000299215317,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8615308403968811},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.7965612411499023},{"id":"https://openalex.org/keywords/contig","display_name":"Contig","score":0.6319102048873901},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.575742244720459},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5062936544418335},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.37720590829849243},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3578256368637085},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.29614871740341187},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.21996670961380005},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.10882392525672913}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8615308403968811},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.7965612411499023},{"id":"https://openalex.org/C59582021","wikidata":"https://www.wikidata.org/wiki/Q1128751","display_name":"Contig","level":4,"score":0.6319102048873901},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.575742244720459},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5062936544418335},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.37720590829849243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3578256368637085},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.29614871740341187},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.21996670961380005},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.10882392525672913}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-021-04227-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-04227-z","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-04227-z","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:35045830","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35045830","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:d2012f6044224a1b9e2feb05ae090f01","is_oa":true,"landing_page_url":"https://doaj.org/article/d2012f6044224a1b9e2feb05ae090f01","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 22, Iss S12, Pp 1-17 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8772042","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8772042","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-021-04227-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-021-04227-z","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-021-04227-z","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G2909670411","display_name":null,"funder_award_id":"no. 2018A610057","funder_id":"https://openalex.org/F4320323225","funder_display_name":"Natural Science Foundation of Ningbo Municipality"},{"id":"https://openalex.org/G4153811458","display_name":"\u8bc6\u522b\u80bf\u7624\u57fa\u56e0\u6807\u5fd7\u7269\u7684\u8ba1\u7b97\u65b9\u6cd5\u53ca\u5e94\u7528","funder_award_id":"61373057","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4837079510","display_name":null,"funder_award_id":"No. LGF21F020008","funder_id":"https://openalex.org/F4320338465","funder_display_name":"Zhejiang Province Public Welfare Technology Application Research Project"},{"id":"https://openalex.org/G6817779856","display_name":null,"funder_award_id":"2019RC05","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6830319706","display_name":null,"funder_award_id":"2018A610057","funder_id":"https://openalex.org/F4320332587","funder_display_name":"Natural Science Foundation of Ningbo"},{"id":"https://openalex.org/G8771598067","display_name":null,"funder_award_id":"no. 61373057","funder_id":"https://openalex.org/F4320315254","funder_display_name":"Innovative Research Group Project of the National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320315254","display_name":"Innovative Research Group Project of the National Natural Science Foundation of China","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323225","display_name":"Natural Science Foundation of Ningbo Municipality","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320332587","display_name":"Natural Science Foundation of Ningbo","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338465","display_name":"Zhejiang Province Public Welfare Technology Application Research Project","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4206184519.pdf","grobid_xml":"https://content.openalex.org/works/W4206184519.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W176296285","https://openalex.org/W1562379206","https://openalex.org/W1584790813","https://openalex.org/W1757675837","https://openalex.org/W1878521557","https://openalex.org/W1966711026","https://openalex.org/W1973545398","https://openalex.org/W1977556410","https://openalex.org/W1997673861","https://openalex.org/W2000589358","https://openalex.org/W2001561488","https://openalex.org/W2004549986","https://openalex.org/W2033292629","https://openalex.org/W2069689025","https://openalex.org/W2081676964","https://openalex.org/W2082203850","https://openalex.org/W2082521980","https://openalex.org/W2083501377","https://openalex.org/W2089859322","https://openalex.org/W2099570444","https://openalex.org/W2103901746","https://openalex.org/W2112364185","https://openalex.org/W2112419798","https://openalex.org/W2113679889","https://openalex.org/W2115026474","https://openalex.org/W2121291798","https://openalex.org/W2124927293","https://openalex.org/W2131026689","https://openalex.org/W2134751812","https://openalex.org/W2136651963","https://openalex.org/W2138122982","https://openalex.org/W2139436782","https://openalex.org/W2140604849","https://openalex.org/W2141202455","https://openalex.org/W2143777131","https://openalex.org/W2145537580","https://openalex.org/W2150208009","https://openalex.org/W2152469342","https://openalex.org/W2337508844","https://openalex.org/W2341364667","https://openalex.org/W2588364491","https://openalex.org/W2626996263","https://openalex.org/W2773939681","https://openalex.org/W2949071062","https://openalex.org/W2950785362","https://openalex.org/W2952946307","https://openalex.org/W2965715058","https://openalex.org/W6680106728"],"related_works":["https://openalex.org/W2330186985","https://openalex.org/W2950447380","https://openalex.org/W2055448750","https://openalex.org/W2345730070","https://openalex.org/W2107854630","https://openalex.org/W4319294554","https://openalex.org/W3134563641","https://openalex.org/W1986608492","https://openalex.org/W4394186879","https://openalex.org/W4381279187"],"abstract_inverted_index":{"BACKGROUND:":[0],"Metagenomics":[1],"technology":[2],"can":[3,19,117,163,241],"directly":[4],"extract":[5],"microbial":[6],"genetic":[7],"material":[8],"from":[9,39,57,124,180,219,246],"the":[10,66,78,92,97,104,119,133,153,166,169,175,212,222],"environmental":[11,40,248],"samples":[12,170],"to":[13,35,83,90,121,151,173,177],"obtain":[14],"their":[15],"sequencing":[16],"reads,":[17],"which":[18,116,240],"be":[20,84],"further":[21],"assembled":[22],"into":[23],"contigs":[24,31,235],"through":[25],"assembly":[26,71],"tools.":[27],"Clustering":[28],"methods":[29,48,201],"of":[30,72,94,103,106,135,168,211,216],"are":[32,49,62,81,149],"subsequently":[33],"applied":[34],"recover":[36,53,122,178,242],"complete":[37],"genomes":[38],"samples.":[41,249],"The":[42,141,183],"main":[43],"problems":[44],"with":[45,198],"current":[46,107],"clustering":[47,98,108,114,139,185,236],"that":[50,162,225],"they":[51],"cannot":[52],"more":[54,230,243],"high-quality":[55,244],"genes":[56,123,179,218,245],"complex":[58,125,181,247],"environments.":[59,182],"Firstly,":[60],"there":[61],"multiple":[63],"strains":[64,76,95,137],"under":[65,77],"same":[67,79],"species,":[68],"resulting":[69],"in":[70,138],"chimeras.":[73],"Secondly,":[74],"different":[75],"species":[80],"difficult":[82,89],"classified.":[85],"Thirdly,":[86],"it":[87],"is":[88,171,229,238],"determine":[91],"number":[93,134,213],"during":[96],"process.":[99,140],"RESULTS:":[100],"In":[101,209],"view":[102],"shortcomings":[105],"methods,":[109],"we":[110],"propose":[111],"an":[112],"unsupervised":[113],"method":[115,130,161,186,228,237],"improve":[118,174],"ability":[120,176],"environments":[126],"and":[127,147,192,196,207,214],"a":[128],"new":[129,159,184,234],"for":[131,156],"selecting":[132],"sample's":[136],"sequence":[142],"composition":[143],"characteristics":[144],"(tetranucleotide":[145],"frequency)":[146],"co-abundance":[148],"combined":[150],"train":[152],"probability":[154],"model":[155],"clustering.":[157],"A":[158,233],"recursive":[160],"continuously":[164],"reduce":[165],"complexity":[167],"proposed":[172,227],"was":[187],"tested":[188],"on":[189],"both":[190],"simulated":[191],"real":[193],"metagenomic":[194,220],"datasets,":[195,221],"compared":[197],"five":[199],"state-of-the-art":[200],"including":[202],"CONCOCT,":[203],"Maxbin2.0,":[204],"MetaBAT,":[205],"MyCC":[206],"COCACOLA.":[208],"terms":[210],"quality":[215],"recovered":[217],"results":[223],"show":[224],"our":[226],"effective.":[231],"CONCLUSIONS:":[232],"proposed,":[239]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}