{"id":"https://openalex.org/W2288445713","doi":"https://doi.org/10.1109/tcbb.2016.2535326","title":"hc-OTU: A Fast and Accurate Method for Clustering Operational Taxonomic Units Based on Homopolymer Compaction","display_name":"hc-OTU: A Fast and Accurate Method for Clustering Operational Taxonomic Units Based on Homopolymer Compaction","publication_year":2016,"publication_date":"2016-02-26","ids":{"openalex":"https://openalex.org/W2288445713","doi":"https://doi.org/10.1109/tcbb.2016.2535326","mag":"2288445713","pmid":"https://pubmed.ncbi.nlm.nih.gov/26930691"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2016.2535326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2016.2535326","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","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/A5048067770","display_name":"Seunghyun Park","orcid":"https://orcid.org/0000-0001-5260-1252"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seunghyun Park","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea","School of Electrical Engineering, Korea University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"School of Electrical Engineering, Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366819","display_name":"Hyun-Soo Choi","orcid":"https://orcid.org/0000-0002-3594-8948"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyun-soo Choi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070152050","display_name":"Byunghan Lee","orcid":"https://orcid.org/0000-0002-6727-0975"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byunghan Lee","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081493752","display_name":"Jongsik Chun","orcid":"https://orcid.org/0000-0003-3385-5171"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongsik Chun","raw_affiliation_strings":["Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016994398","display_name":"Joong\u2010Ho Won","orcid":"https://orcid.org/0000-0002-5597-9557"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joong-Ho Won","raw_affiliation_strings":["Department of Statistics, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086877012","display_name":"Sungroh Yoon","orcid":"https://orcid.org/0000-0002-2367-197X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungroh Yoon","raw_affiliation_strings":["ASRI, BDI, INMC, and Bioinformatics Institute, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"ASRI, BDI, INMC, and Bioinformatics Institute, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5048067770"],"corresponding_institution_ids":["https://openalex.org/I139264467","https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":0.8716,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.7579712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"15","issue":"2","first_page":"441","last_page":"451"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9976999759674072,"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":0.9976999759674072,"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":0.9962000250816345,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9847999811172485,"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":0.7459165453910828},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6409556865692139},{"id":"https://openalex.org/keywords/amplicon","display_name":"Amplicon","score":0.6113232374191284},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5774669647216797},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5699092149734497},{"id":"https://openalex.org/keywords/operational-taxonomic-unit","display_name":"Operational taxonomic unit","score":0.46634405851364136},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.4468720853328705},{"id":"https://openalex.org/keywords/rand-index","display_name":"Rand index","score":0.41779613494873047},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33176302909851074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3095371127128601},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.23735007643699646},{"id":"https://openalex.org/keywords/16s-ribosomal-rna","display_name":"16S ribosomal RNA","score":0.16594696044921875},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.12586283683776855},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.07547223567962646}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7459165453910828},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6409556865692139},{"id":"https://openalex.org/C8185291","wikidata":"https://www.wikidata.org/wiki/Q2844457","display_name":"Amplicon","level":4,"score":0.6113232374191284},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5774669647216797},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5699092149734497},{"id":"https://openalex.org/C2779825944","wikidata":"https://www.wikidata.org/wiki/Q7097792","display_name":"Operational taxonomic unit","level":4,"score":0.46634405851364136},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.4468720853328705},{"id":"https://openalex.org/C111442797","wikidata":"https://www.wikidata.org/wiki/Q7291446","display_name":"Rand index","level":3,"score":0.41779613494873047},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33176302909851074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3095371127128601},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.23735007643699646},{"id":"https://openalex.org/C42062724","wikidata":"https://www.wikidata.org/wiki/Q1209205","display_name":"16S ribosomal RNA","level":3,"score":0.16594696044921875},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.12586283683776855},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.07547223567962646},{"id":"https://openalex.org/C49105822","wikidata":"https://www.wikidata.org/wiki/Q176996","display_name":"Polymerase chain reaction","level":3,"score":0.0}],"mesh":[{"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":"D012336","descriptor_name":"RNA, Ribosomal, 16S","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012336","descriptor_name":"RNA, Ribosomal, 16S","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012336","descriptor_name":"RNA, Ribosomal, 16S","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","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":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"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":4,"locations":[{"id":"doi:10.1109/tcbb.2016.2535326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2016.2535326","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:26930691","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26930691","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":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null},{"id":"pmh:oai:s-space.snu.ac.kr:10371/165726","is_oa":false,"landing_page_url":"https://hdl.handle.net/10371/165726","pdf_url":null,"source":{"id":"https://openalex.org/S4306401345","display_name":"Seoul National University Open Repository (Seoul National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139264467","host_organization_name":"Seoul National University","host_organization_lineage":["https://openalex.org/I139264467"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:s-space.snu.ac.kr:10371/187211","is_oa":false,"landing_page_url":"https://hdl.handle.net/10371/187211","pdf_url":null,"source":{"id":"https://openalex.org/S4306401345","display_name":"Seoul National University Open Repository (Seoul National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139264467","host_organization_name":"Seoul National University","host_organization_lineage":["https://openalex.org/I139264467"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.41999998688697815}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1515226261","https://openalex.org/W1738124305","https://openalex.org/W1967843471","https://openalex.org/W1971784203","https://openalex.org/W1980355960","https://openalex.org/W1988925586","https://openalex.org/W1989889539","https://openalex.org/W1991517254","https://openalex.org/W2010829655","https://openalex.org/W2026808573","https://openalex.org/W2033829415","https://openalex.org/W2034285706","https://openalex.org/W2040888993","https://openalex.org/W2048719649","https://openalex.org/W2059237622","https://openalex.org/W2073548709","https://openalex.org/W2087671769","https://openalex.org/W2095006983","https://openalex.org/W2102813808","https://openalex.org/W2106308757","https://openalex.org/W2108718991","https://openalex.org/W2118526609","https://openalex.org/W2124135641","https://openalex.org/W2124351063","https://openalex.org/W2129070834","https://openalex.org/W2130208436","https://openalex.org/W2132598047","https://openalex.org/W2136879569","https://openalex.org/W2140638310","https://openalex.org/W2153562609","https://openalex.org/W2156125289","https://openalex.org/W2158714788","https://openalex.org/W2160681728","https://openalex.org/W2162315106","https://openalex.org/W2166661751","https://openalex.org/W2168408208","https://openalex.org/W2171963266","https://openalex.org/W2319660501","https://openalex.org/W4235169531","https://openalex.org/W6630786662","https://openalex.org/W6662703138"],"related_works":["https://openalex.org/W638577851","https://openalex.org/W2968354375","https://openalex.org/W2359440920","https://openalex.org/W4242417330","https://openalex.org/W2889550857","https://openalex.org/W3013372948","https://openalex.org/W3135997498","https://openalex.org/W2010421806","https://openalex.org/W2051814207","https://openalex.org/W4221125478"],"abstract_inverted_index":{"To":[0],"assess":[1],"the":[2,12,66,77,120,130],"genetic":[3],"diversity":[4],"of":[5,15,72,112,126,134],"an":[6],"environmental":[7],"sample":[8],"in":[9],"metagenomics":[10],"studies,":[11],"amplicon":[13,73],"sequences":[14],"16s":[16],"rRNA":[17],"genes":[18],"need":[19],"to":[20,63,129],"be":[21],"clustered":[22],"into":[23],"operational":[24],"taxonomic":[25],"units":[26],"(OTUs).":[27],"Many":[28],"existing":[29],"tools":[30],"for":[31,69],"OTU":[32,45,141],"clustering":[33,46,142],"trade":[34],"off":[35],"between":[36],"accuracy":[37,52,127,132],"and":[38,53,60,91,99,114,136],"computational":[39],"efficiency.":[40],"We":[41,75],"propose":[42],"a":[43,124],"novel":[44],"algorithm,":[47],"hc-OTU,":[48],"which":[49],"achieves":[50,123],"high":[51],"fast":[54],"runtime":[55],"by":[56],"exploiting":[57],"homopolymer":[58],"compaction":[59],"k-mer":[61],"profiling":[62],"significantly":[64],"reduce":[65],"computing":[67],"time":[68],"pairwise":[70],"distances":[71],"sequences.":[74],"compare":[76],"proposed":[78,121],"method":[79,122],"with":[80],"other":[81],"widely":[82,139],"used":[83,140],"methods,":[84,143],"including":[85],"UCLUST,":[86],"CD-HIT,":[87],"MOTHUR,":[88],"ESPRIT,":[89],"ESPRIT-TREE,":[90,137],"CLUSTOM,":[92],"comprehensively,":[93],"using":[94],"nine":[95],"different":[96],"experimental":[97],"datasets":[98],"many":[100],"evaluation":[101,117],"metrics,":[102],"such":[103],"as":[104],"normalized":[105],"mutual":[106],"information,":[107],"adjusted":[108],"Rand":[109],"index,":[110],"measure":[111],"concordance,":[113],"F-score.":[115],"Our":[116],"reveals":[118],"that":[119],"level":[125],"comparable":[128],"respective":[131],"levels":[133],"MOTHUR":[135],"two":[138],"while":[144],"delivering":[145],"orders-of-magnitude":[146],"speedups.":[147]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}