{"id":"https://openalex.org/W2579441661","doi":"https://doi.org/10.1109/bibm.2016.7822604","title":"Evaluation of CD-HIT for constructing non-redundant databases","display_name":"Evaluation of CD-HIT for constructing non-redundant databases","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2579441661","doi":"https://doi.org/10.1109/bibm.2016.7822604","mag":"2579441661"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2016.7822604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2016.7822604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042874172","display_name":"Qingyu Chen","orcid":"https://orcid.org/0000-0002-6036-1516"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Qingyu Chen","raw_affiliation_strings":["Dept. of Computing & Information Systems, University of Melbourne, Victoria, Australia"],"affiliations":[{"raw_affiliation_string":"Dept. of Computing & Information Systems, University of Melbourne, Victoria, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377279","display_name":"Yu Wan","orcid":"https://orcid.org/0000-0002-8354-7647"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yu Wan","raw_affiliation_strings":["Centre for Systems Genomics, University of Melbourne, Victoria, Australia"],"affiliations":[{"raw_affiliation_string":"Centre for Systems Genomics, University of Melbourne, Victoria, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102772304","display_name":"Yang Lei","orcid":"https://orcid.org/0000-0003-3780-6510"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang Lei","raw_affiliation_strings":["Dept. of Computing & Information Systems, University of Melbourne, Victoria, Australia"],"affiliations":[{"raw_affiliation_string":"Dept. of Computing & Information Systems, University of Melbourne, Victoria, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041495909","display_name":"Justin Zobel","orcid":"https://orcid.org/0000-0001-6622-032X"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Justin Zobel","raw_affiliation_strings":["Dept. of Computing & Information Systems, University of Melbourne, Victoria, Australia"],"affiliations":[{"raw_affiliation_string":"Dept. of Computing & Information Systems, University of Melbourne, Victoria, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067214173","display_name":"Karin Verspoor","orcid":"https://orcid.org/0000-0002-8661-1544"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Karin Verspoor","raw_affiliation_strings":["Dept. of Computing & Information Systems, University of Melbourne, Victoria, Australia"],"affiliations":[{"raw_affiliation_string":"Dept. of Computing & Information Systems, University of Melbourne, Victoria, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042874172"],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":3.1039,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93372953,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"703","last_page":"706"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9947999715805054,"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":0.9947999715805054,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9857000112533569,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.984000027179718,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/redundancy","display_name":"Redundancy (engineering)","score":0.9080281853675842},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6763310432434082},{"id":"https://openalex.org/keywords/data-redundancy","display_name":"Data redundancy","score":0.573930025100708},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.49625712633132935},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4622696340084076},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4449891746044159},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4082200825214386},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.06459015607833862}],"concepts":[{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.9080281853675842},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6763310432434082},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.573930025100708},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.49625712633132935},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4622696340084076},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4449891746044159},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4082200825214386},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06459015607833862},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bibm.2016.7822604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2016.7822604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/27592236","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27592236","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1501500081","https://openalex.org/W2097606916","https://openalex.org/W2108166985","https://openalex.org/W2108211735","https://openalex.org/W2116699248","https://openalex.org/W2124351063","https://openalex.org/W2135083016","https://openalex.org/W2146341019","https://openalex.org/W2156125289","https://openalex.org/W2170747616","https://openalex.org/W2224056471","https://openalex.org/W2273522830"],"related_works":["https://openalex.org/W2002428578","https://openalex.org/W2897258045","https://openalex.org/W2018406690","https://openalex.org/W2072332896","https://openalex.org/W2951748633","https://openalex.org/W4292309272","https://openalex.org/W2057691131","https://openalex.org/W2542042335","https://openalex.org/W2952039693","https://openalex.org/W4280621979"],"abstract_inverted_index":{"CD-HIT":[0,82],"is":[1,13,77],"one":[2],"of":[3,38,46,52,57,81],"the":[4,17,47,50,55,66,71],"most":[5],"popular":[6],"tools":[7],"for":[8],"reducing":[9,26],"sequence":[10,39],"redundancy,":[11],"and":[12,61,75,98],"considered":[14],"to":[15,22],"be":[16],"state-of-art":[18],"method.":[19],"It":[20],"tries":[21],"minimise":[23],"redundancy":[24,48],"by":[25],"an":[27],"input":[28],"database":[29],"into":[30],"several":[31],"representative":[32],"sequences,":[33],"under":[34],"a":[35,43],"user-defined":[36],"threshold":[37,74,87],"identity.":[40],"We":[41,68],"present":[42],"comprehensive":[44],"assessment":[45],"in":[49,95],"outputs":[51],"CD-HIT,":[53],"exploring":[54],"impact":[56],"different":[58],"identity":[59,86],"thresholds":[60],"new":[62],"evaluation":[63],"data":[64],"on":[65],"redundancy.":[67],"demonstrate":[69],"that":[70,83],"relationship":[72],"between":[73],"redundancies":[76],"surprising":[78],"weak.":[79],"Applications":[80],"set":[84],"low":[85],"values":[88],"also":[89],"may":[90],"suffer":[91],"from":[92],"substantial":[93],"degradation":[94],"both":[96],"efficiency":[97],"accuracy.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
