{"id":"https://openalex.org/W4200046412","doi":"https://doi.org/10.1142/s0219720021500360","title":"EdClust: A heuristic sequence clustering method with higher sensitivity","display_name":"EdClust: A heuristic sequence clustering method with higher sensitivity","publication_year":2021,"publication_date":"2021-12-23","ids":{"openalex":"https://openalex.org/W4200046412","doi":"https://doi.org/10.1142/s0219720021500360","pmid":"https://pubmed.ncbi.nlm.nih.gov/34939905"},"language":"en","primary_location":{"id":"doi:10.1142/s0219720021500360","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720021500360","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/A5102798953","display_name":"Ming Cao","orcid":"https://orcid.org/0000-0003-3405-4595"},"institutions":[{"id":"https://openalex.org/I4210104015","display_name":"Shaanxi Xueqian Normal University","ror":"https://ror.org/0146vv083","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210104015"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Cao","raw_affiliation_strings":["Faculty of Electronic and Information Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, 710049, P. R. China","School of Mathematics and Statistics, Shaanxi Xueqian Normal University, Xi\u2019an, 710100, P. R. China","Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, 710049, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electronic and Information Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, 710049, P. R. China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Mathematics and Statistics, Shaanxi Xueqian Normal University, Xi\u2019an, 710100, P. R. China","institution_ids":["https://openalex.org/I4210104015"]},{"raw_affiliation_string":"Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, 710049, P. R. China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101905916","display_name":"Qinke Peng","orcid":"https://orcid.org/0000-0002-2697-1038"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qinke Peng","raw_affiliation_strings":["Faculty of Electronic and Information Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, 710049, P. R. China","Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, 710049, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Electronic and Information Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, 710049, P. R. China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, 710049, P. R. China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071217704","display_name":"Ze\u2010Gang Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I2799293361","display_name":"Baoji University of Arts and Sciences","ror":"https://ror.org/05nx0xs09","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799293361"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ze-Gang Wei","raw_affiliation_strings":["Institute of Physics and Optoelectronics Technology, Baoji University of Arts and Sciences, Baoji, 721016, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Physics and Optoelectronics Technology, Baoji University of Arts and Sciences, Baoji, 721016, P. R. China","institution_ids":["https://openalex.org/I2799293361"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602474","display_name":"Fei Liu","orcid":"https://orcid.org/0000-0003-1175-4070"},"institutions":[{"id":"https://openalex.org/I2799293361","display_name":"Baoji University of Arts and Sciences","ror":"https://ror.org/05nx0xs09","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799293361"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Liu","raw_affiliation_strings":["Institute of Physics and Optoelectronics Technology, Baoji University of Arts and Sciences, Baoji, 721016, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Physics and Optoelectronics Technology, Baoji University of Arts and Sciences, Baoji, 721016, P. R. China","institution_ids":["https://openalex.org/I2799293361"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059522548","display_name":"Yifan Hou","orcid":"https://orcid.org/0000-0002-3197-4460"},"institutions":[{"id":"https://openalex.org/I2799293361","display_name":"Baoji University of Arts and Sciences","ror":"https://ror.org/05nx0xs09","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799293361"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi-Fan Hou","raw_affiliation_strings":["Institute of Physics and Optoelectronics Technology, Baoji University of Arts and Sciences, Baoji, 721016, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Physics and Optoelectronics Technology, Baoji University of Arts and Sciences, Baoji, 721016, P. R. China","institution_ids":["https://openalex.org/I2799293361"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071217704","https://openalex.org/A5101905916"],"corresponding_institution_ids":["https://openalex.org/I2799293361","https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.1586,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.49181455,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"20","issue":"01","first_page":"2150036","last_page":"2150036"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9955000281333923,"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/T10066","display_name":"Gut microbiota and health","score":0.9697999954223633,"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":0.9029684066772461},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6727863550186157},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6631785035133362},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6328966021537781},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5556175112724304},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.46475616097450256},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.45444804430007935},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4529021680355072},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.43332964181900024},{"id":"https://openalex.org/keywords/mit-license","display_name":"MIT License","score":0.42084410786628723},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.4119972884654999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22824802994728088},{"id":"https://openalex.org/keywords/license","display_name":"License","score":0.12455970048904419},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11664307117462158},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.084512859582901}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.9029684066772461},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6727863550186157},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6631785035133362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6328966021537781},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5556175112724304},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.46475616097450256},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.45444804430007935},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4529021680355072},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.43332964181900024},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.42084410786628723},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.4119972884654999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22824802994728088},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.12455970048904419},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11664307117462158},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.084512859582901},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000066506","descriptor_name":"Heuristics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000066506","descriptor_name":"Heuristics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000066506","descriptor_name":"Heuristics","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":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":"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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219720021500360","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219720021500360","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:34939905","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34939905","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":[{"score":0.49000000953674316,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G4089621766","display_name":null,"funder_award_id":"2021JQ-811","funder_id":"https://openalex.org/F4320327224","funder_display_name":"Shaanxi Provincial Science and Technology Department"},{"id":"https://openalex.org/G8035653337","display_name":null,"funder_award_id":"21JK0486","funder_id":"https://openalex.org/F4320325627","funder_display_name":"Education Department of Shaanxi Province"},{"id":"https://openalex.org/G996507653","display_name":"\u57fa\u4e8e\u6df1\u5ea6\u5b66\u4e60\u7684miRNA\u3001lncRNA\u548ccircRNA\u5173\u7cfb\u5206\u6790\u53ca\u5176\u4e0e\u4eba\u7c7b\u590d\u6742\u6027\u75be\u75c5\u5173\u8054\u6027\u7814\u7a76","funder_award_id":"61872288","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320325627","display_name":"Education Department of Shaanxi Province","ror":null},{"id":"https://openalex.org/F4320327224","display_name":"Shaanxi Provincial Science and Technology Department","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1490161904","https://openalex.org/W1545338289","https://openalex.org/W1977668719","https://openalex.org/W1986908904","https://openalex.org/W2002723915","https://openalex.org/W2011084061","https://openalex.org/W2030782070","https://openalex.org/W2037532428","https://openalex.org/W2049349724","https://openalex.org/W2054698853","https://openalex.org/W2056930789","https://openalex.org/W2073548709","https://openalex.org/W2074231493","https://openalex.org/W2078958937","https://openalex.org/W2084168100","https://openalex.org/W2087544933","https://openalex.org/W2093794723","https://openalex.org/W2100761975","https://openalex.org/W2103947923","https://openalex.org/W2106399600","https://openalex.org/W2108211735","https://openalex.org/W2108718991","https://openalex.org/W2117228324","https://openalex.org/W2124351063","https://openalex.org/W2131186249","https://openalex.org/W2145853890","https://openalex.org/W2151350595","https://openalex.org/W2155066423","https://openalex.org/W2160209604","https://openalex.org/W2160444236","https://openalex.org/W2160681728","https://openalex.org/W2163681976","https://openalex.org/W2166171121","https://openalex.org/W2167519901","https://openalex.org/W2170747616","https://openalex.org/W2315831910","https://openalex.org/W2378604574","https://openalex.org/W2513506562","https://openalex.org/W2557595285","https://openalex.org/W2607937729","https://openalex.org/W2622369200","https://openalex.org/W2739999456","https://openalex.org/W2804477062","https://openalex.org/W2913097383","https://openalex.org/W2913847081","https://openalex.org/W2921129204","https://openalex.org/W2950589160","https://openalex.org/W2950609999","https://openalex.org/W2953008890","https://openalex.org/W2953174564","https://openalex.org/W3047578107","https://openalex.org/W3136918052","https://openalex.org/W4231601595"],"related_works":["https://openalex.org/W2188840951","https://openalex.org/W4241767317","https://openalex.org/W2101637161","https://openalex.org/W2171610853","https://openalex.org/W2160785859","https://openalex.org/W1999117613","https://openalex.org/W2559422900","https://openalex.org/W3092684173","https://openalex.org/W2103650652","https://openalex.org/W1887359504"],"abstract_inverted_index":{"The":[0,97,157],"development":[1],"of":[2,9,25,41,60,129,154,160],"high-throughput":[3],"technologies":[4],"has":[5],"produced":[6],"increasing":[7,14],"amounts":[8],"sequence":[10,38,75,91,106],"data":[11,27],"and":[12,63,108,122,132,146],"an":[13],"need":[15],"for":[16,28,37,87],"efficient":[17],"clustering":[18,32,39,49,65,76,116],"algorithms":[19],"that":[20,137,147,153],"can":[21,139],"process":[22],"massive":[23],"volumes":[24],"sequencing":[26],"downstream":[29],"analysis.":[30],"Heuristic":[31],"methods":[33,50,145],"are":[34,162],"widely":[35],"applied":[36],"because":[40],"their":[42],"low":[43,64],"computational":[44],"complexity.":[45],"Although":[46],"numerous":[47],"heuristic":[48,115],"have":[51],"been":[52],"developed,":[53],"they":[54],"suffer":[55],"from":[56,164],"two":[57],"limitations:":[58],"overestimation":[59],"inferred":[61],"clusters":[62,142],"sensitivity.":[66],"To":[67],"address":[68],"these":[69],"issues,":[70],"we":[71,109],"present":[72],"a":[73,82],"new":[74,98],"method":[77,99],"(edClust)":[78],"based":[79,125],"on":[80,103,126],"Edlib,":[81],"C/C[Formula:":[83],"see":[84],"text]":[85],"library":[86],"fast,":[88],"exact":[89],"semi-global":[90],"alignment":[92],"to":[93,112],"group":[94],"similar":[95],"sequences.":[96],"edClust":[100,111,138,161],"was":[101],"tested":[102],"three":[104],"large-scale":[105],"databases,":[107],"compared":[110],"several":[113],"classic":[114],"methods,":[117],"such":[118],"as":[119],"UCLUST,":[120],"CD-HIT,":[121],"VSEARCH.":[123],"Evaluations":[124],"the":[127,167],"metrics":[128],"cluster":[130],"number":[131],"seed":[133],"sensitivity":[134],"(SS)":[135],"demonstrate":[136],"produce":[140],"fewer":[141],"than":[143,152],"other":[144,155],"its":[148],"SS":[149],"is":[150],"higher":[151],"methods.":[156],"source":[158],"codes":[159],"available":[163],"https://github.com/zhang134/EdClust.git":[165],"under":[166],"GNU":[168],"GPL":[169],"license.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
