{"id":"https://openalex.org/W2002276164","doi":"https://doi.org/10.1145/2649387.2649402","title":"Fast dendrogram-based OTU clustering using sequence embedding","display_name":"Fast dendrogram-based OTU clustering using sequence embedding","publication_year":2014,"publication_date":"2014-09-20","ids":{"openalex":"https://openalex.org/W2002276164","doi":"https://doi.org/10.1145/2649387.2649402","mag":"2002276164"},"language":"en","primary_location":{"id":"doi:10.1145/2649387.2649402","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2649387.2649402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics","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/A5063614815","display_name":"Thuy-Diem Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Thuy-Diem Nguyen","raw_affiliation_strings":["Nanyang Technological University, Singapore","Nanyang Technological University (Singapore)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University (Singapore)","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020388832","display_name":"Bertil Schmidt","orcid":"https://orcid.org/0000-0003-2597-8331"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bertil Schmidt","raw_affiliation_strings":["Johannes Gutenberg University, Mainz, Germany","Johannes Gutenberg University , Mainz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johannes Gutenberg University, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]},{"raw_affiliation_string":"Johannes Gutenberg University , Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112553040","display_name":"Chee-Keong Kwoh","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chee-Keong Kwoh","raw_affiliation_strings":["Nanyang Technological University, Singapore","Nanyang Technological University (Singapore)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University (Singapore)","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10066","display_name":"Gut microbiota and health","score":0.9988999962806702,"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/T10066","display_name":"Gut microbiota and health","score":0.9988999962806702,"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":0.9983999729156494,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9979000091552734,"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":0.9488725662231445},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6702390909194946},{"id":"https://openalex.org/keywords/dendrogram","display_name":"Dendrogram","score":0.6344720721244812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6313599348068237},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5865786075592041},{"id":"https://openalex.org/keywords/biodiversity","display_name":"Biodiversity","score":0.47190481424331665},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.44620272517204285},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41348662972450256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4023010730743408},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2394426167011261},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.17667174339294434}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.9488725662231445},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6702390909194946},{"id":"https://openalex.org/C172312944","wikidata":"https://www.wikidata.org/wiki/Q1957903","display_name":"Dendrogram","level":4,"score":0.6344720721244812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6313599348068237},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5865786075592041},{"id":"https://openalex.org/C130217890","wikidata":"https://www.wikidata.org/wiki/Q47041","display_name":"Biodiversity","level":2,"score":0.47190481424331665},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.44620272517204285},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41348662972450256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4023010730743408},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2394426167011261},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.17667174339294434},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","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},{"id":"https://openalex.org/C81977670","wikidata":"https://www.wikidata.org/wiki/Q585259","display_name":"Genetic diversity","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2649387.2649402","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2649387.2649402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1480958225","https://openalex.org/W1658221551","https://openalex.org/W1975684011","https://openalex.org/W1979813476","https://openalex.org/W1988925586","https://openalex.org/W2030782070","https://openalex.org/W2033403400","https://openalex.org/W2072970694","https://openalex.org/W2073548709","https://openalex.org/W2074231493","https://openalex.org/W2087671769","https://openalex.org/W2088833470","https://openalex.org/W2099751670","https://openalex.org/W2106308757","https://openalex.org/W2108718991","https://openalex.org/W2115394533","https://openalex.org/W2117228324","https://openalex.org/W2123009189","https://openalex.org/W2124351063","https://openalex.org/W2127322768","https://openalex.org/W2130208436","https://openalex.org/W2136552678","https://openalex.org/W2136879569","https://openalex.org/W2140264006","https://openalex.org/W2140638310","https://openalex.org/W2141793995","https://openalex.org/W2146577751","https://openalex.org/W2149573313","https://openalex.org/W2150914285","https://openalex.org/W2151370125","https://openalex.org/W2153993827","https://openalex.org/W2156858199","https://openalex.org/W2160681728","https://openalex.org/W2162833336","https://openalex.org/W2176446742","https://openalex.org/W4239035626"],"related_works":["https://openalex.org/W638577851","https://openalex.org/W2968354375","https://openalex.org/W2359440920","https://openalex.org/W2889550857","https://openalex.org/W3013372948","https://openalex.org/W3135997498","https://openalex.org/W4242417330","https://openalex.org/W4388282505","https://openalex.org/W3198631238","https://openalex.org/W4255657129"],"abstract_inverted_index":{"Biodiversity":[0],"assessment":[1],"is":[2,17],"an":[3],"important":[4],"step":[5],"in":[6],"a":[7,14],"metagenomic":[8,33],"processing":[9],"pipeline.":[10],"The":[11],"biodiversity":[12],"of":[13],"microbial":[15],"metagenome":[16],"often":[18],"estimated":[19],"by":[20],"grouping":[21],"its":[22],"16S":[23],"rRNA":[24],"reads":[25],"into":[26],"operational":[27],"taxonomic":[28],"units":[29],"or":[30],"OTUs.":[31],"These":[32],"datasets":[34],"are":[35],"typically":[36],"large":[37],"and":[38],"hence":[39],"require":[40],"effective":[41],"yet":[42],"accurate":[43],"computational":[44],"methods":[45],"for":[46],"processing.":[47]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
