{"id":"https://openalex.org/W2903178573","doi":"https://doi.org/10.1145/3291992.3291998","title":"Rapid hierarchical clustering of biological sequences","display_name":"Rapid hierarchical clustering of biological sequences","publication_year":2018,"publication_date":"2018-12-04","ids":{"openalex":"https://openalex.org/W2903178573","doi":"https://doi.org/10.1145/3291992.3291998","mag":"2903178573"},"language":"en","primary_location":{"id":"doi:10.1145/3291992.3291998","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3291992.3291998","pdf_url":"https://eprints.qut.edu.au/126085/1/126085.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd Australasian Document Computing Symposium","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://eprints.qut.edu.au/126085/1/126085.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013498459","display_name":"Timothy Chappell","orcid":"https://orcid.org/0000-0002-8862-7048"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Timothy Chappell","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Queensland University of Technology, Brisbane, Queensland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Queensland University of Technology, Brisbane, Queensland","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045420626","display_name":"Shlomo Geva","orcid":"https://orcid.org/0000-0003-1340-2802"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shlomo Geva","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Queensland University of Technology, Brisbane, Queensland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Queensland University of Technology, Brisbane, Queensland","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110256734","display_name":"James M. Hogan","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"James Hogan","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Queensland University of Technology, Brisbane, Queensland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Queensland University of Technology, Brisbane, Queensland","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089156481","display_name":"Dimitri Perrin","orcid":"https://orcid.org/0000-0002-4007-5256"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dimitri Perrin","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, Queensland University of Technology, Brisbane, Queensland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Queensland University of Technology, Brisbane, Queensland","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21038961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9993000030517578,"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":0.9993000030517578,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9919999837875366,"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":0.9915000200271606,"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":0.821536660194397},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.743141233921051},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.6604669094085693},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6022455096244812},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.5780895352363586},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5414995551109314},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.5351764559745789},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4726856052875519},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.44055458903312683},{"id":"https://openalex.org/keywords/binary-tree","display_name":"Binary tree","score":0.4105372726917267},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41002732515335083},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4093021750450134},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.2879762351512909},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2705782949924469},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.2609700858592987},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12680217623710632},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10102382302284241}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.821536660194397},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743141233921051},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.6604669094085693},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6022455096244812},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.5780895352363586},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5414995551109314},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.5351764559745789},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4726856052875519},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.44055458903312683},{"id":"https://openalex.org/C197855036","wikidata":"https://www.wikidata.org/wiki/Q380172","display_name":"Binary tree","level":2,"score":0.4105372726917267},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41002732515335083},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4093021750450134},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.2879762351512909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2705782949924469},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.2609700858592987},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12680217623710632},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10102382302284241},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3291992.3291998","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3291992.3291998","pdf_url":"https://eprints.qut.edu.au/126085/1/126085.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd Australasian Document Computing Symposium","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:126085","is_oa":false,"landing_page_url":"https://eprints.qut.edu.au/126085/1/126085.pdf","pdf_url":"https://eprints.qut.edu.au/126085/1/126085.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 23rd Australasian Document Computing Symposium","raw_type":"Chapter in Book, Report or Conference volume"}],"best_oa_location":{"id":"doi:10.1145/3291992.3291998","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3291992.3291998","pdf_url":"https://eprints.qut.edu.au/126085/1/126085.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd Australasian Document Computing Symposium","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2903178573.pdf","grobid_xml":"https://content.openalex.org/works/W2903178573.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W188912188","https://openalex.org/W2034285706","https://openalex.org/W2074231493","https://openalex.org/W2124351063","https://openalex.org/W2127218421","https://openalex.org/W2149727079","https://openalex.org/W2170747616","https://openalex.org/W2299467264"],"related_works":["https://openalex.org/W4292477917","https://openalex.org/W2034251629","https://openalex.org/W2488882714","https://openalex.org/W2592952084","https://openalex.org/W2534504385","https://openalex.org/W4237492828","https://openalex.org/W2130194910","https://openalex.org/W2189374779","https://openalex.org/W2605148547","https://openalex.org/W1602287844"],"abstract_inverted_index":{"Genomic":[0],"sequences":[1],"can":[2,30],"be":[3],"viewed":[4],"as":[5,16,32,36],"special":[6],"types":[7],"of":[8,18,40,45,84,89,131,146],"documents.":[9,20],"These":[10],"are":[11,23],"typically":[12],"organised":[13],"and":[14,51,103],"stored":[15],"collections":[17,22],"text":[19,34,149],"The":[21,42,121],"vast;":[24],"a":[25,75],"single":[26],"metagenomics":[27],"sequencing":[28],"experiment":[29],"produce":[31],"much":[33],"data":[35,65,91,119],"the":[37,46,80,117,129,135,144],"entire":[38],"contents":[39],"Wikipedia.":[41],"increasing":[43],"scale":[44],"datasets":[47],"obtained":[48],"from":[49,134],"environmental":[50],"clinical":[52],"metagenomic":[53],"studies":[54],"has":[55,124],"posed":[56],"great":[57],"difficulties":[58],"to":[59,62,128,143],"researchers":[60],"attempting":[61],"organise":[63],"this":[64,71],"with":[66,107],"traditional":[67],"clustering":[68,76,113,130,145],"techniques.":[69],"In":[70],"work":[72],"we":[73,139],"introduce":[74],"approach":[77,114,123],"that":[78],"combines":[79],"highly":[81],"effective":[82],"strategy":[83],"using":[85],"binary":[86],"signature":[87],"representations":[88,106],"sequence":[90,148],"--":[92,102],"allowing":[93],"extremely":[94],"fast":[95],"pairwise":[96],"comparison":[97],"through":[98],"hardware":[99],"level":[100],"operations":[101],"couples":[104],"these":[105],"an":[108],"O(N":[109],"log":[110],"N)":[111],"hierarchical":[112],"based":[115],"on":[116],"k-tree":[118,122],"structure.":[120],"previously":[125],"been":[126],"applied":[127],"English-language":[132],"documents":[133],"ClueWeb":[136],"collection.":[137],"Here":[138],"extend":[140],"its":[141],"use":[142],"genomic":[147],"files.":[150]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}
