{"id":"https://openalex.org/W2773760320","doi":"https://doi.org/10.1145/3166072.3166076","title":"K-Means Clustering of Biological Sequences","display_name":"K-Means Clustering of Biological Sequences","publication_year":2017,"publication_date":"2017-12-07","ids":{"openalex":"https://openalex.org/W2773760320","doi":"https://doi.org/10.1145/3166072.3166076","mag":"2773760320"},"language":"en","primary_location":{"id":"doi:10.1145/3166072.3166076","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3166072.3166076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd Australasian Document Computing Symposium","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.qut.edu.au/116844/14/k-means-clustering.pdf","any_repository_has_fulltext":true},"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":true,"raw_author_name":"Timothy Chappell","raw_affiliation_strings":["School of Electrical Engineering and Computer Science, QUT, Brisbane, Queensland"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, QUT, 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, QUT, Brisbane, Queensland"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, QUT, Brisbane, Queensland","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","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, QUT, Brisbane, Queensland"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, QUT, Brisbane, Queensland","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013498459"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":0.449,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.64703068,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9997000098228455,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9997000098228455,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9980999827384949,"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":0.9973999857902527,"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":0.8751226663589478},{"id":"https://openalex.org/keywords/hamming-distance","display_name":"Hamming distance","score":0.6563034057617188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6119799613952637},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.5963355898857117},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5726093649864197},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.5254358649253845},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.49390608072280884},{"id":"https://openalex.org/keywords/hamming-code","display_name":"Hamming code","score":0.4674590229988098},{"id":"https://openalex.org/keywords/biological-data","display_name":"Biological data","score":0.45891106128692627},{"id":"https://openalex.org/keywords/hamming-space","display_name":"Hamming space","score":0.44916847348213196},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.4407847225666046},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.43139445781707764},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.42201608419418335},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3696897029876709},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3218751549720764},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.18116357922554016},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1381404995918274}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8751226663589478},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.6563034057617188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6119799613952637},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.5963355898857117},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5726093649864197},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.5254358649253845},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.49390608072280884},{"id":"https://openalex.org/C73150493","wikidata":"https://www.wikidata.org/wiki/Q853922","display_name":"Hamming code","level":4,"score":0.4674590229988098},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.45891106128692627},{"id":"https://openalex.org/C2779494224","wikidata":"https://www.wikidata.org/wiki/Q5645799","display_name":"Hamming space","level":5,"score":0.44916847348213196},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.4407847225666046},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.43139445781707764},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.42201608419418335},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3696897029876709},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3218751549720764},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.18116357922554016},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1381404995918274},{"id":"https://openalex.org/C157125643","wikidata":"https://www.wikidata.org/wiki/Q884707","display_name":"Block code","level":3,"score":0.0},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.0},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3166072.3166076","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3166072.3166076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd Australasian Document Computing Symposium","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:116844","is_oa":true,"landing_page_url":"https://dl.acm.org/citation.cfm?id=3166076","pdf_url":"https://eprints.qut.edu.au/116844/14/k-means-clustering.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 22nd Australasian Document Computing Symposium","raw_type":"Chapter in Book, Report or Conference volume"}],"best_oa_location":{"id":"pmh:oai:eprints.qut.edu.au:116844","is_oa":true,"landing_page_url":"https://dl.acm.org/citation.cfm?id=3166076","pdf_url":"https://eprints.qut.edu.au/116844/14/k-means-clustering.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 22nd Australasian Document Computing Symposium","raw_type":"Chapter in Book, Report or Conference volume"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2773760320.pdf","grobid_xml":"https://content.openalex.org/works/W2773760320.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2003503754","https://openalex.org/W2012833704","https://openalex.org/W2015292449","https://openalex.org/W2065347041","https://openalex.org/W2068448872","https://openalex.org/W2074231493","https://openalex.org/W2087064593","https://openalex.org/W2117608012","https://openalex.org/W2120358246","https://openalex.org/W2124351063","https://openalex.org/W2145349611","https://openalex.org/W2145853890","https://openalex.org/W2156125289","https://openalex.org/W2211193336","https://openalex.org/W2299467264","https://openalex.org/W2342204193","https://openalex.org/W2914643318"],"related_works":["https://openalex.org/W3120229345","https://openalex.org/W2607902515","https://openalex.org/W2171610853","https://openalex.org/W2103650652","https://openalex.org/W2025839902","https://openalex.org/W2160785859","https://openalex.org/W2393707058","https://openalex.org/W1999117613","https://openalex.org/W1887359504","https://openalex.org/W2060484766"],"abstract_inverted_index":{"The":[0],"unsupervised":[1],"clustering":[2,30,54,102],"of":[3,37,53,74],"biological":[4,55,101],"sequences":[5,26,56,85],"is":[6,69],"an":[7,62],"important":[8],"task":[9],"in":[10,104],"the":[11,15,35,72,80],"bioinformatics":[12],"space;":[13],"however,":[14],"high":[16],"computational":[17],"expense":[18],"associated":[19],"with":[20],"computing":[21],"pairwise":[22],"distances":[23],"between":[24],"these":[25,84],"makes":[27],"many":[28],"traditional":[29],"approaches":[31],"untenable,":[32],"leading":[33],"to":[34,86,99],"use":[36,79],"greedy":[38],"algorithms":[39,103],"that":[40,91],"are":[41],"fast":[42],"but":[43],"degrade":[44],"poorly.":[45],"In":[46],"this":[47,92],"paper":[48],"we":[49,78],"introduce":[50],"a":[51],"method":[52],"by":[57],"first":[58],"converting":[59],"them":[60],"into":[61],"intermediate":[63],"binary":[64],"format":[65],"where":[66],"Hamming":[67],"distance":[68],"used":[70],"as":[71],"metric":[73],"comparison.":[75],"Following":[76],"this,":[77],"k-means":[81],"algorithm":[82],"on":[83],"cluster":[87],"them.":[88],"We":[89],"show":[90],"approach":[93],"produces":[94],"results":[95],"equivalent":[96],"or":[97],"superior":[98],"comparable":[100],"less":[105],"time.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}