{"id":"https://openalex.org/W4390991987","doi":"https://doi.org/10.1109/bibm58861.2023.10385950","title":"EdtClust: A fast homologous protein sequences clustering method based on edit distance","display_name":"EdtClust: A fast homologous protein sequences clustering method based on edit distance","publication_year":2023,"publication_date":"2023-12-05","ids":{"openalex":"https://openalex.org/W4390991987","doi":"https://doi.org/10.1109/bibm58861.2023.10385950"},"language":"en","primary_location":{"id":"doi:10.1109/bibm58861.2023.10385950","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bibm58861.2023.10385950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5100666567","display_name":"Yixin Xiang","orcid":"https://orcid.org/0009-0008-9165-1277"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixin Xiang","raw_affiliation_strings":["Nankai University,College of Software,Tianjin,China","College of Software, Nankai University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,College of Software,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"College of Software, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100583018","display_name":"Jiachang Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiachang Gu","raw_affiliation_strings":["Nankai University,College of Software,Tianjin,China","College of Software, Nankai University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,College of Software,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"College of Software, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071042348","display_name":"Jianyu Zhou","orcid":"https://orcid.org/0000-0003-4104-6091"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianyu Zhou","raw_affiliation_strings":["Nankai University,College of Software,Tianjin,China","College of Software, Nankai University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,College of Software,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"College of Software, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25785389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"99","issue":null,"first_page":"690","last_page":"697"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9990000128746033,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9990000128746033,"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":0.9983000159263611,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9926999807357788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7153282165527344},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.6924393177032471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6911178231239319},{"id":"https://openalex.org/keywords/homologous-chromosome","display_name":"Homologous chromosome","score":0.618372917175293},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3444255590438843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.282187283039093},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.16412580013275146},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.14101633429527283},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.07912254333496094}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7153282165527344},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.6924393177032471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6911178231239319},{"id":"https://openalex.org/C64894306","wikidata":"https://www.wikidata.org/wiki/Q849622","display_name":"Homologous chromosome","level":3,"score":0.618372917175293},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3444255590438843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.282187283039093},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.16412580013275146},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.14101633429527283},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.07912254333496094}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm58861.2023.10385950","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bibm58861.2023.10385950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1968570655","https://openalex.org/W1986022261","https://openalex.org/W2001496424","https://openalex.org/W2029195137","https://openalex.org/W2055043387","https://openalex.org/W2074231493","https://openalex.org/W2087064593","https://openalex.org/W2102443632","https://openalex.org/W2132069633","https://openalex.org/W2162006472","https://openalex.org/W2162663580","https://openalex.org/W2166637863","https://openalex.org/W2949342052","https://openalex.org/W2950150251","https://openalex.org/W2953008890","https://openalex.org/W2961460076","https://openalex.org/W2992400060","https://openalex.org/W3177828909","https://openalex.org/W4220791336","https://openalex.org/W4226052879","https://openalex.org/W4377011795","https://openalex.org/W6629956336"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3044917232","https://openalex.org/W1498160656","https://openalex.org/W2119149496","https://openalex.org/W2055693471","https://openalex.org/W4295101776","https://openalex.org/W2139858675","https://openalex.org/W2952580779","https://openalex.org/W1537327044"],"abstract_inverted_index":{"Homology":[0],"among":[1],"protein":[2,27,38,49,142,200],"sequences":[3,20,28,39,143,201],"plays":[4],"a":[5,14,22,30,104,118,148,159,191,212],"crucial":[6],"role":[7],"in":[8,43,120,173,211,232],"evolutionary":[9],"and":[10,144,156,186,193,225],"comparative":[11],"biology,":[12],"with":[13,215],"key":[15],"step":[16],"involving":[17],"retrieving":[18],"homologous":[19,26,48,208],"of":[21,36,85,107,235],"query":[23],"or":[24],"clustering":[25,51,114,172],"within":[29],"dataset.":[31],"However,":[32],"the":[33,82,130,137,165,233],"growing":[34],"size":[35],"known":[37],"due":[40],"to":[41,62,102,170,220],"advances":[42],"sequencing":[44],"technology":[45],"has":[46],"made":[47],"sequence":[50,68,209],"an":[52],"increasingly":[53],"challenging":[54],"task.":[55],"Current":[56],"feasible":[57],"solutions":[58],"employ":[59],"locality-sensitive":[60,108,160],"hashing":[61,78,109,161],"achieve":[63],"linear":[64],"time":[65,214],"complexity":[66],"for":[67,110],"clustering.":[69],"Nonetheless,":[70],"existing":[71],"methods":[72],"do":[73],"not":[74],"directly":[75],"apply":[76],"this":[77,94,96,174],"technique":[79,162],"based":[80,163],"on":[81,164],"foundational":[83],"concept":[84],"edit":[86,111,145],"distance,":[87,112],"which":[88,100],"precisely":[89],"defines":[90],"homology.":[91],"To":[92],"address":[93],"gap,":[95],"paper":[97],"introduces":[98],"EdtClust,":[99],"aims":[101],"design":[103],"specific":[105],"instance":[106],"enhancing":[113],"efficiency":[115],"while":[116,188],"maintaining":[117],"foundation":[119],"homology\u2019s":[121],"essence.":[122],"EdtClust":[123,182,204],"comprises":[124],"two":[125],"core":[126],"steps:":[127],"first,":[128],"utilizing":[129],"gapped":[131,153],"k-mer":[132,154],"embedding":[133],"framework,":[134],"it":[135],"transforms":[136],"metric":[138,150,176],"space":[139,151],"derived":[140],"from":[141],"distances":[146],"into":[147],"novel":[149],"containing":[152],"sets":[155],"L1distances.":[157],"Subsequently,":[158],"Cauchy":[166],"distribution":[167],"is":[168],"implemented":[169],"expedite":[171],"new":[175],"space.":[177],"Through":[178],"rigorous":[179],"theoretical":[180],"analysis,":[181],"demonstrates":[183],"enhanced":[184],"precision":[185],"efficiency,":[187],"also":[189],"ensuring":[190],"simple":[192],"swift":[194],"implementation.":[195],"Experimental":[196],"results":[197],"using":[198],"real":[199],"validate":[202],"that":[203],"can":[205],"identify":[206],"more":[207],"pairs":[210],"shorter":[213],"reduced":[216],"memory":[217],"consumption":[218],"compared":[219],"state-of-the-art":[221],"algorithms":[222],"like":[223],"Linclust":[224],"ALFATClust,":[226],"thereby":[227],"confirming":[228],"its":[229],"substantial":[230],"potential":[231],"field":[234],"computational":[236],"biology.":[237]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}