{"id":"https://openalex.org/W2093634337","doi":"https://doi.org/10.1142/s0219720013400015","title":"LARGE-SCALE METAGENOMIC SEQUENCE CLUSTERING ON MAP-REDUCE CLUSTERS","display_name":"LARGE-SCALE METAGENOMIC SEQUENCE CLUSTERING ON MAP-REDUCE CLUSTERS","publication_year":2012,"publication_date":"2012-12-26","ids":{"openalex":"https://openalex.org/W2093634337","doi":"https://doi.org/10.1142/s0219720013400015","mag":"2093634337","pmid":"https://pubmed.ncbi.nlm.nih.gov/23427983"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720013400015","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720013400015","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/A5083812342","display_name":"Xiao Yang","orcid":"https://orcid.org/0000-0002-5429-9162"},"institutions":[{"id":"https://openalex.org/I107606265","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142","country_code":"US","type":"funder","lineage":["https://openalex.org/I107606265"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"XIAO YANG","raw_affiliation_strings":["Broad Institute of Harvard and MIT, Cambridge, Massachusetts 02142, USA"],"affiliations":[{"raw_affiliation_string":"Broad Institute of Harvard and MIT, Cambridge, Massachusetts 02142, USA","institution_ids":["https://openalex.org/I107606265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000660681","display_name":"Jaros\u0142aw \u017bola","orcid":"https://orcid.org/0000-0002-1686-9697"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"JAROSLAW ZOLA","raw_affiliation_strings":["Rutgers University, Department of Electrical and Computer Engineering, Rutgers Discovery Informatics Institute, Piscataway, New Jersey 08854, USA"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Department of Electrical and Computer Engineering, Rutgers Discovery Informatics Institute, Piscataway, New Jersey 08854, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074347913","display_name":"Srinivas Aluru","orcid":"https://orcid.org/0000-0003-4279-469X"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"SRINIVAS ALURU","raw_affiliation_strings":["Iowa State University, Department of Electrical and Computer Engineering, Ames, Iowa 50011, USA"],"affiliations":[{"raw_affiliation_string":"Iowa State University, Department of Electrical and Computer Engineering, Ames, Iowa 50011, USA","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083812342"],"corresponding_institution_ids":["https://openalex.org/I107606265"],"apc_list":null,"apc_paid":null,"fwci":2.1407,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.8875013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"11","issue":"01","first_page":"1340001","last_page":"1340001"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9929999709129333,"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":0.9905999898910522,"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":0.8480565547943115},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7745222449302673},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5521430969238281},{"id":"https://openalex.org/keywords/enumeration","display_name":"Enumeration","score":0.5183921456336975},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.48898446559906006},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4886517822742462},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4873684048652649},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4512559175491333},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.39930692315101624},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.36849159002304077},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2347320020198822},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20313146710395813},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17394375801086426},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.12776121497154236},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.12290576100349426},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.11990579962730408}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.8480565547943115},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7745222449302673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5521430969238281},{"id":"https://openalex.org/C156340839","wikidata":"https://www.wikidata.org/wiki/Q2704791","display_name":"Enumeration","level":2,"score":0.5183921456336975},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.48898446559906006},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4886517822742462},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4873684048652649},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4512559175491333},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.39930692315101624},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.36849159002304077},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2347320020198822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20313146710395813},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17394375801086426},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.12776121497154236},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.12290576100349426},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.11990579962730408},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"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":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219720013400015","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720013400015","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:23427983","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23427983","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1539662764","https://openalex.org/W1976369037","https://openalex.org/W1993524210","https://openalex.org/W2006465310","https://openalex.org/W2046270811","https://openalex.org/W2056930789","https://openalex.org/W2125826054","https://openalex.org/W2126913464","https://openalex.org/W2131804386","https://openalex.org/W2139570101","https://openalex.org/W2152565070","https://openalex.org/W2153233077","https://openalex.org/W2156125289","https://openalex.org/W2584945553","https://openalex.org/W6604186633"],"related_works":["https://openalex.org/W108845024","https://openalex.org/W4300125793","https://openalex.org/W2578985712","https://openalex.org/W2406961474","https://openalex.org/W3042106073","https://openalex.org/W2143566611","https://openalex.org/W588267724","https://openalex.org/W2057205169","https://openalex.org/W4297743441","https://openalex.org/W3200375535"],"abstract_inverted_index":{"Taxonomic":[0],"clustering":[1,32,129],"of":[2,6,33,60,78,90,102,109,130,134,136],"species":[3],"from":[4,10],"millions":[5,135],"DNA":[7],"fragments":[8],"sequenced":[9],"their":[11],"genomes":[12],"is":[13],"an":[14],"important":[15],"and":[16],"frequently":[17],"arising":[18],"problem":[19,75],"in":[20,82,138],"metagenomics.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25],"present":[26],"a":[27,115,145],"parallel":[28],"algorithm":[29],"for":[30,39,50],"taxonomic":[31],"large":[34],"metagenomic":[35,73,131],"samples":[36,132],"with":[37],"support":[38],"overlapping":[40],"clusters.":[41],"We":[42,70,99,119],"develop":[43],"sketching":[44],"techniques,":[45],"akin":[46],"to":[47,54,64,113],"those":[48],"created":[49],"web":[51],"document":[52],"clustering,":[53],"deduce":[55],"significant":[56],"similarities":[57],"between":[58],"pairs":[59],"sequences":[61],"without":[62],"resorting":[63],"expensive":[65],"all":[66,68],"vs.":[67],"comparison.":[69],"formulate":[71],"the":[72,83,91,103,110,122],"classification":[74],"as":[76,93,107],"that":[77,121],"maximal":[79],"quasi-clique":[80],"enumeration":[81],"resulting":[84,123],"similarity":[85,97],"graph,":[86],"at":[87],"multiple":[88],"levels":[89],"hierarchy":[92],"prescribed":[94],"by":[95],"different":[96],"thresholds.":[98],"cast":[100],"execution":[101],"underlying":[104],"algorithmic":[105],"steps":[106],"applications":[108],"map-reduce":[111],"framework":[112,124],"achieve":[114],"cloud":[116],"ready":[117],"implementation.":[118],"show":[120],"can":[125],"produce":[126],"high":[127],"quality":[128],"consisting":[133],"reads,":[137],"reasonable":[139],"time":[140],"limits,":[141],"when":[142],"executed":[143],"on":[144],"modest":[146],"size":[147],"cluster.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
