{"id":"https://openalex.org/W2762557867","doi":"https://doi.org/10.1142/s0219720017400066","title":"Metagenome sequence clustering with hash-based canopies","display_name":"Metagenome sequence clustering with hash-based canopies","publication_year":2017,"publication_date":"2017-10-10","ids":{"openalex":"https://openalex.org/W2762557867","doi":"https://doi.org/10.1142/s0219720017400066","mag":"2762557867","pmid":"https://pubmed.ncbi.nlm.nih.gov/29113561"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720017400066","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720017400066","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100639555","display_name":"Mohammad Arifur Rahman","orcid":"https://orcid.org/0000-0001-7373-6164"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Arifur Rahman","raw_affiliation_strings":["Department of Computer Science, George Mason University, Fairfax, Virginia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, George Mason University, Fairfax, Virginia, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080266778","display_name":"Nathan LaPierre","orcid":"https://orcid.org/0000-0003-2394-8868"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan LaPierre","raw_affiliation_strings":["Department of Computer Science, University of California, Los Angeles, California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Los Angeles, California, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006581225","display_name":"Huzefa Rangwala","orcid":"https://orcid.org/0000-0003-0435-0035"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huzefa Rangwala","raw_affiliation_strings":["Department of Computer Science, George Mason University, Fairfax, Virginia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, George Mason University, Fairfax, Virginia, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089029917","display_name":"Daniel Barbar\u00e1","orcid":"https://orcid.org/0000-0002-2830-1038"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Barbara","raw_affiliation_strings":["Department of Computer Science, George Mason University, Fairfax, Virginia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, George Mason University, Fairfax, Virginia, USA","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6558,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.68806936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"15","issue":"06","first_page":"1740006","last_page":"1740006"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10066","display_name":"Gut microbiota and health","score":0.998199999332428,"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/T10066","display_name":"Gut microbiota and health","score":0.998199999332428,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9975000023841858,"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":0.9876999855041504,"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/cluster-analysis","display_name":"Cluster analysis","score":0.830539345741272},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.7434691190719604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6333989500999451},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6242697834968567},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.581326961517334},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5411348938941956},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.509351372718811},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25394105911254883},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1737288534641266},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14656949043273926}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.830539345741272},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.7434691190719604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6333989500999451},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6242697834968567},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.581326961517334},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5411348938941956},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.509351372718811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25394105911254883},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1737288534641266},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14656949043273926},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069196","descriptor_name":"Gastrointestinal Microbiome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D000069196","descriptor_name":"Gastrointestinal Microbiome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D000069196","descriptor_name":"Gastrointestinal Microbiome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008103","descriptor_name":"Liver Cirrhosis","qualifier_ui":"Q000382","qualifier_name":"microbiology","is_major_topic":false},{"descriptor_ui":"D008103","descriptor_name":"Liver Cirrhosis","qualifier_ui":"Q000382","qualifier_name":"microbiology","is_major_topic":false},{"descriptor_ui":"D008103","descriptor_name":"Liver Cirrhosis","qualifier_ui":"Q000382","qualifier_name":"microbiology","is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012336","descriptor_name":"RNA, Ribosomal, 16S","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012336","descriptor_name":"RNA, Ribosomal, 16S","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012336","descriptor_name":"RNA, Ribosomal, 16S","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012337","descriptor_name":"RNA, Ribosomal, 18S","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012337","descriptor_name":"RNA, Ribosomal, 18S","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012337","descriptor_name":"RNA, Ribosomal, 18S","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012988","descriptor_name":"Soil Microbiology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012988","descriptor_name":"Soil Microbiology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012988","descriptor_name":"Soil Microbiology","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":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D044822","descriptor_name":"Biodiversity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D044822","descriptor_name":"Biodiversity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D044822","descriptor_name":"Biodiversity","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},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219720017400066","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720017400066","pdf_url":null,"source":{"id":"https://openalex.org/S155349577","display_name":"Journal of Bioinformatics and Computational Biology","issn_l":"0219-7200","issn":["0219-7200","1757-6334"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311754","host_organization_name":"Imperial College Press","host_organization_lineage":["https://openalex.org/P4310311754"],"host_organization_lineage_names":["Imperial College Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Bioinformatics and Computational Biology","raw_type":"journal-article"},{"id":"pmid:29113561","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29113561","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":"Journal of bioinformatics and computational biology","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.5799999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1964027278","https://openalex.org/W1984081611","https://openalex.org/W1988925586","https://openalex.org/W1989889539","https://openalex.org/W1997673861","https://openalex.org/W1998601670","https://openalex.org/W1999713271","https://openalex.org/W2060661289","https://openalex.org/W2072970694","https://openalex.org/W2081193615","https://openalex.org/W2086865963","https://openalex.org/W2091922579","https://openalex.org/W2108718991","https://openalex.org/W2115387350","https://openalex.org/W2124351063","https://openalex.org/W2125826054","https://openalex.org/W2131186249","https://openalex.org/W2144550002","https://openalex.org/W2152766058","https://openalex.org/W2152885278","https://openalex.org/W2156125289","https://openalex.org/W2164631357","https://openalex.org/W2194764270","https://openalex.org/W2273522830","https://openalex.org/W2513506562","https://openalex.org/W2950150251"],"related_works":["https://openalex.org/W638577851","https://openalex.org/W2968354375","https://openalex.org/W2359440920","https://openalex.org/W2889550857","https://openalex.org/W3013372948","https://openalex.org/W3135997498","https://openalex.org/W4242417330","https://openalex.org/W3198631238","https://openalex.org/W4388282505","https://openalex.org/W2968048207"],"abstract_inverted_index":{"Metagenomics":[0],"is":[1],"the":[2,20,67,140],"collective":[3],"sequencing":[4],"of":[5,33,38,70,142],"co-existing":[6],"microbial":[7],"communities":[8,43],"which":[9],"are":[10,44,81],"ubiquitous":[11],"across":[12],"various":[13],"clinical":[14],"and":[15,23,36,51,108,119,131,134,153],"ecological":[16],"environments.":[17],"Due":[18],"to":[19,146,159,164],"large":[21,68],"volume":[22],"random":[24],"short":[25],"sequences":[26],"(reads)":[27],"obtained":[28],"from":[29],"community":[30],"sequences,":[31],"analysis":[32],"diversity,":[34],"abundance":[35],"functions":[37],"different":[39,165],"organisms":[40],"within":[41],"these":[42],"challenging":[45],"tasks.":[46],"We":[47,106,124,138,168],"present":[48],"a":[49,98,178],"fast":[50],"scalable":[52],"clustering":[53,88,104,122,127,166],"algorithm":[54,93,128],"for":[55,101,113],"analyzing":[56],"large-scale":[57],"metagenome":[58,136],"sequence":[59,71,87,121],"data.":[60],"Our":[61],"approach":[62,145],"achieves":[63],"efficiency":[64],"by":[65,84],"partitioning":[66],"number":[69],"reads":[72],"into":[73],"groups":[74],"(called":[75],"canopies)":[76],"using":[77,85],"hashing.":[78],"These":[79],"canopies":[80],"then":[82],"refined":[83],"state-of-the-art":[86,120],"algorithms.":[89,105,167],"This":[90],"canopy-clustering":[91],"(CC)":[92],"can":[94],"be":[95],"used":[96],"as":[97],"pre-processing":[99],"phase":[100],"computationally":[102],"expensive":[103],"use":[107],"compare":[109],"three":[110],"hashing":[111],"schemes":[112],"canopy":[114],"construction":[115],"with":[116,157],"five":[117],"popular":[118],"methods.":[123],"evaluate":[125],"our":[126,143,171],"on":[129,176],"synthetic":[130],"real-world":[132],"16S":[133],"whole":[135],"benchmarks.":[137],"demonstrate":[139],"ability":[141],"proposed":[144],"determine":[147],"meaningful":[148],"Operational":[149],"Taxonomic":[150],"Units":[151],"(OTU)":[152],"observe":[154],"significant":[155],"speedup":[156],"regards":[158],"run":[160],"time":[161],"when":[162],"compared":[163],"also":[169],"make":[170],"source":[172],"code":[173],"publicly":[174],"available":[175],"Github.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}