{"id":"https://openalex.org/W2095200684","doi":"https://doi.org/10.1186/1471-2105-10-359","title":"Analysis and comparison of very large metagenomes with fast clustering and functional annotation","display_name":"Analysis and comparison of very large metagenomes with fast clustering and functional annotation","publication_year":2009,"publication_date":"2009-10-28","ids":{"openalex":"https://openalex.org/W2095200684","doi":"https://doi.org/10.1186/1471-2105-10-359","mag":"2095200684","pmid":"https://pubmed.ncbi.nlm.nih.gov/19863816","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/2774329"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-10-359","doi":"https://doi.org/10.1186/1471-2105-10-359","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-359","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-359","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,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-2","oarl","poland-100","russia-white-list-1","vabb-shw"],"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"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-359","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027145422","display_name":"Weizhong Li","orcid":"https://orcid.org/0000-0003-1804-9403","observed_orcids":["https://orcid.org/0000-0003-1804-9403"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Weizhong Li","raw_affiliation_strings":["California Institute for Telecommunications and Information Technology, University of California, San Diego, La Jolla, California 92093, USA. liwz@sdsc.edu","California Institute for Telecommunications and Information Technology, University of California San Diego, La Jolla, California 92093, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute for Telecommunications and Information Technology, University of California, San Diego, La Jolla, California 92093, USA. liwz@sdsc.edu","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"California Institute for Telecommunications and Information Technology, University of California San Diego, La Jolla, California 92093, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5027145422"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":4.9603,"has_fulltext":true,"cited_by_count":132,"citation_normalized_percentile":{"value":0.96405368,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"10","issue":"1","first_page":"359","last_page":"359"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994999766349792,"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":0.9994999766349792,"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/T11791","display_name":"Microbial Community Ecology and Physiology","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12640","display_name":"Environmental DNA in Biodiversity Studies","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metagenomics","display_name":"metagenomics","score":0.8479999899864197},{"id":"https://openalex.org/keywords/metagenome-comparison","display_name":"metagenome comparison","score":0.9739999771118164},{"id":"https://openalex.org/keywords/sequence-clustering","display_name":"sequence clustering","score":0.9620000123977661},{"id":"https://openalex.org/keywords/functional-annotation","display_name":"functional annotation","score":0.847000002861023},{"id":"https://openalex.org/keywords/protein-family-annotation","display_name":"protein family annotation","score":0.878000020980835},{"id":"https://openalex.org/keywords/novel-gene-families","display_name":"novel gene families","score":0.8759999871253967}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.942197859287262},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6890882849693298},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6329563856124878},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5707823038101196},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5368706583976746},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5142473578453064},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4892902076244354},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3756738305091858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18166720867156982},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1689704954624176},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1292831003665924},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","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":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-10-359","doi":"https://doi.org/10.1186/1471-2105-10-359","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-359","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-359","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,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-2","oarl","poland-100","russia-white-list-1","vabb-shw"],"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":"pmh:oai:pubmedcentral.nih.gov:2774329","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2774329","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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmid:19863816","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19863816","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,"listed_in":[],"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":"Comparative Study"},{"id":"pmh:oai:doaj.org/article:25a5adc6691446d084036531b8010a0e","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/25a5adc6691446d084036531b8010a0e","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,"listed_in":[],"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 10, Iss 1, p 359 (2009)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-10-359","doi":"https://doi.org/10.1186/1471-2105-10-359","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-359","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-10-359","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,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-2","oarl","poland-100","russia-white-list-1","vabb-shw"],"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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3621401605","display_name":"CD-HIT: A Fast Program to Cluster and Compare Large Sets of Biological Sequences","funder_award_id":"R01RR025030","funder_id":"https://openalex.org/F4320337375","funder_display_name":"National Center for Research Resources"}],"funders":[{"id":"https://openalex.org/F4320306202","display_name":"Gordon and Betty Moore Foundation","ror":"https://ror.org/006wxqw41"},{"id":"https://openalex.org/F4320309507","display_name":"San Diego State University","ror":"https://ror.org/0264fdx42"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337375","display_name":"National Center for Research Resources","ror":"https://ror.org/04pw6fb54"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2095200684.pdf","grobid_xml":"https://content.openalex.org/works/W2095200684.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1562379206","https://openalex.org/W1571319209","https://openalex.org/W1791999417","https://openalex.org/W1969295076","https://openalex.org/W1986473212","https://openalex.org/W1994456450","https://openalex.org/W1995614275","https://openalex.org/W2004548026","https://openalex.org/W2009543464","https://openalex.org/W2033705779","https://openalex.org/W2042893247","https://openalex.org/W2048818637","https://openalex.org/W2056930789","https://openalex.org/W2061680337","https://openalex.org/W2081676964","https://openalex.org/W2093830129","https://openalex.org/W2108211735","https://openalex.org/W2113601822","https://openalex.org/W2114200698","https://openalex.org/W2116895571","https://openalex.org/W2124637227","https://openalex.org/W2126809954","https://openalex.org/W2131342905","https://openalex.org/W2132415967","https://openalex.org/W2135083016","https://openalex.org/W2140604849","https://openalex.org/W2145336165","https://openalex.org/W2150337627","https://openalex.org/W2151831732","https://openalex.org/W2156125289","https://openalex.org/W2156296225","https://openalex.org/W2156701707","https://openalex.org/W2158714788","https://openalex.org/W2162704968","https://openalex.org/W4298982457"],"related_works":["https://openalex.org/W2044841417","https://openalex.org/W2056930789","https://openalex.org/W2093249177","https://openalex.org/W4283371129","https://openalex.org/W2890611946","https://openalex.org/W7098251807","https://openalex.org/W2082650848","https://openalex.org/W4282964184","https://openalex.org/W2116572549","https://openalex.org/W2051443629"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,52,72],"remarkable":[2],"advance":[3],"of":[4,19,54,80,172,194],"metagenomics":[5],"presents":[6],"significant":[7],"new":[8,73],"challenges":[9],"in":[10,44,68,191],"data":[11,75],"analysis.":[12],"Metagenomic":[13],"datasets":[14,120],"(metagenomes)":[15],"are":[16,34,39,48,67],"large":[17,32,119],"collections":[18],"sequencing":[20],"reads":[21,190],"from":[22,200],"anonymous":[23],"species":[24],"within":[25],"particular":[26],"environments.":[27],"Computational":[28],"analyses":[29],"for":[30],"very":[31,179],"metagenomes":[33,46,56,142],"extremely":[35,118],"time-consuming,":[36],"and":[37,62,86,103,131,140,168,185],"there":[38],"often":[40],"many":[41],"novel":[42,105,137],"sequences":[43],"these":[45],"that":[47,110,134,182],"not":[49],"fully":[50],"utilized.":[51],"number":[53],"available":[55,161,199],"is":[57,177,198],"rapidly":[58],"increasing,":[59],"so":[60],"fast":[61,98,180],"efficient":[63],"metagenome":[64,107],"comparison":[65,108],"methods":[66],"great":[69],"demand.":[70],"RESULTS:":[71],"metagenomic":[74,162,189],"analysis":[76],"method":[77,109,181],"Rapid":[78],"Analysis":[79],"Multiple":[81],"Metagenomes":[82],"with":[83,121],"a":[84,104,112,178],"Clustering":[85],"Annotation":[87],"Pipeline":[88],"(RAMMCAP)":[89],"was":[90,155],"developed":[91],"using":[92,143],"an":[93],"ultra-fast":[94],"sequence":[95],"clustering":[96],"algorithm,":[97],"protein":[99,132],"family":[100],"annotation":[101],"tools,":[102],"statistical":[106],"employs":[111],"unique":[113],"graphic":[114],"interface.":[115],"RAMMCAP":[116,154,176],"processes":[117],"only":[122,192],"moderate":[123],"computational":[124],"effort.":[125],"It":[126,197],"identifies":[127],"raw":[128],"read":[129],"clusters":[130,133,144],"may":[135],"include":[136],"gene":[138],"families,":[139],"compares":[141],"or":[145],"functional":[146],"annotations":[147],"calculated":[148],"by":[149],"RAMMCAP.":[150],"In":[151],"this":[152],"study,":[153],"applied":[156],"to":[157],"the":[158,164,169],"two":[159],"largest":[160],"collections,":[163],"\"Global":[165],"Ocean":[166],"Sampling\"":[167],"\"Metagenomic":[170],"Profiling":[171],"Nine":[173],"Biomes\".":[174],"CONCLUSION:":[175],"can":[183],"cluster":[184],"annotate":[186],"one":[187],"million":[188],"hundreds":[193],"CPU":[195],"hours.":[196],"http://tools.camera.calit2.net/camera/rammcap/.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":16},{"year":2013,"cited_by_count":17},{"year":2012,"cited_by_count":13}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2016-06-24T00:00:00"}