{"id":"https://openalex.org/W2103947923","doi":"https://doi.org/10.1186/1471-2105-11-601","title":"A grammar-based distance metric enables fast and accurate clustering of large sets of 16S sequences","display_name":"A grammar-based distance metric enables fast and accurate clustering of large sets of 16S sequences","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2103947923","doi":"https://doi.org/10.1186/1471-2105-11-601","mag":"2103947923","pmid":"https://pubmed.ncbi.nlm.nih.gov/21167044"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-11-601","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-601","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-601","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-601","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051196368","display_name":"David J. Russell","orcid":null},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David J Russell","raw_affiliation_strings":["Department of Electrical Engineering, University of Nebraska-Lincoln, 209N WSEC, Lincoln, NE 68588-0511, USA. drussell@engr.unl.edu","Department of Electrical Engineering, University of Nebraska-Lincoln, 209N WSEC, Lincoln, NE, 68588-0511, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Nebraska-Lincoln, 209N WSEC, Lincoln, NE 68588-0511, USA. drussell@engr.unl.edu","institution_ids":["https://openalex.org/I114395901"]},{"raw_affiliation_string":"Department of Electrical Engineering, University of Nebraska-Lincoln, 209N WSEC, Lincoln, NE, 68588-0511, USA","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035489318","display_name":"Samuel F Way","orcid":null},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel F Way","raw_affiliation_strings":["Department of Electrical Engineering, University of Nebraska-Lincoln, 209N WSEC, Lincoln, NE, 68588-0511, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Nebraska-Lincoln, 209N WSEC, Lincoln, NE, 68588-0511, USA","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075744550","display_name":"Andrew K. Benson","orcid":"https://orcid.org/0000-0001-6330-0252"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew K Benson","raw_affiliation_strings":["Core for Applied Genomics and Ecology, University of Nebraska-Lincoln, 143 Filley Hall, Lincoln, NE, 68583-0919, USA","Department of Food Science and Technology, University of Nebraska-Lincoln, 143 Filley Hall, Lincoln, NE, 68583-0919, USA"],"affiliations":[{"raw_affiliation_string":"Core for Applied Genomics and Ecology, University of Nebraska-Lincoln, 143 Filley Hall, Lincoln, NE, 68583-0919, USA","institution_ids":["https://openalex.org/I114395901"]},{"raw_affiliation_string":"Department of Food Science and Technology, University of Nebraska-Lincoln, 143 Filley Hall, Lincoln, NE, 68583-0919, USA","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042195176","display_name":"Khalid Sayood","orcid":"https://orcid.org/0000-0001-8010-5272"},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khalid Sayood","raw_affiliation_strings":["Department of Electrical Engineering, University of Nebraska-Lincoln, 209N WSEC, Lincoln, NE, 68588-0511, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Nebraska-Lincoln, 209N WSEC, Lincoln, NE, 68588-0511, USA","institution_ids":["https://openalex.org/I114395901"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051196368"],"corresponding_institution_ids":["https://openalex.org/I114395901"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":5.1295,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.95266971,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"11","issue":"1","first_page":"601","last_page":"601"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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":0.9994999766349792,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9983999729156494,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9926999807357788,"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":0.8285690546035767},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6707460284233093},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.5237790942192078},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.512528657913208},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.5023517608642578},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.5018112659454346},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47648948431015015},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4409107267856598},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43699389696121216},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4239360988140106},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.4223138391971588},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41680869460105896},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3963330388069153},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3748360872268677},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0770905613899231}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8285690546035767},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6707460284233093},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.5237790942192078},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.512528657913208},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.5023517608642578},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.5018112659454346},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47648948431015015},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4409107267856598},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43699389696121216},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4239360988140106},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.4223138391971588},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41680869460105896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3963330388069153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3748360872268677},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0770905613899231},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012336","descriptor_name":"RNA, Ribosomal, 16S","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D012336","descriptor_name":"RNA, Ribosomal, 16S","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D012336","descriptor_name":"RNA, Ribosomal, 16S","qualifier_ui":"Q000032","qualifier_name":"analysis","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":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/1471-2105-11-601","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-601","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-601","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:21167044","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21167044","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:digitalcommons.unl.edu:electricalengineeringfacpub-1189","is_oa":false,"landing_page_url":"https://digitalcommons.unl.edu/electricalengineeringfacpub/190","pdf_url":null,"source":{"id":"https://openalex.org/S4306513441","display_name":"Insecta mundi","issn_l":"0749-6737","issn":["0749-6737","1942-1354","1942-1362"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310316217","host_organization_name":"Center for Systematic Entomology","host_organization_lineage":["https://openalex.org/P4310316217"],"host_organization_lineage_names":["Center for Systematic Entomology"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Department of Electrical and Computer Engineering: Faculty Publications","raw_type":"text"},{"id":"pmh:oai:doaj.org/article:4efe6a03f91a46a18813ba4c00728bab","is_oa":true,"landing_page_url":"https://doaj.org/article/4efe6a03f91a46a18813ba4c00728bab","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 11, Iss 1, p 601 (2010)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:3022630","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3022630","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-11-601","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-601","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-601","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3497591915","display_name":null,"funder_award_id":"(NIH)","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2103947923.pdf","grobid_xml":"https://content.openalex.org/works/W2103947923.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W9273873","https://openalex.org/W1979254690","https://openalex.org/W1981014117","https://openalex.org/W1989889539","https://openalex.org/W2008386840","https://openalex.org/W2048283878","https://openalex.org/W2059504991","https://openalex.org/W2059513841","https://openalex.org/W2062296203","https://openalex.org/W2072994259","https://openalex.org/W2077770566","https://openalex.org/W2092875293","https://openalex.org/W2095200684","https://openalex.org/W2106882534","https://openalex.org/W2107745473","https://openalex.org/W2108211735","https://openalex.org/W2115394533","https://openalex.org/W2121252285","https://openalex.org/W2122962290","https://openalex.org/W2124351063","https://openalex.org/W2129066856","https://openalex.org/W2135083016","https://openalex.org/W2146951308","https://openalex.org/W2149492307","https://openalex.org/W2156125289","https://openalex.org/W2158714788","https://openalex.org/W2533248932"],"related_works":["https://openalex.org/W2892323093","https://openalex.org/W2374506950","https://openalex.org/W3140018618","https://openalex.org/W2389934482","https://openalex.org/W4298005308","https://openalex.org/W4241252752","https://openalex.org/W3093293392","https://openalex.org/W2067669858","https://openalex.org/W2187812493","https://openalex.org/W4211006840"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,11],"fast":[3],"and":[4],"accurate":[5],"clustering":[6,17,22],"algorithm":[7],"that":[8],"relies":[9],"on":[10],"grammar-based":[12],"sequence":[13],"distance.":[14],"Its":[15],"statistical":[16],"quality":[18],"is":[19],"validated":[20],"by":[21],"large":[23],"datasets":[24],"containing":[25],"16S":[26],"rDNA":[27],"sequences.":[28]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
