{"id":"https://openalex.org/W2117520899","doi":"https://doi.org/10.1093/bioinformatics/btg138","title":"Fast sequence clustering using a suffix array algorithm","display_name":"Fast sequence clustering using a suffix array algorithm","publication_year":2003,"publication_date":"2003-06-30","ids":{"openalex":"https://openalex.org/W2117520899","doi":"https://doi.org/10.1093/bioinformatics/btg138","mag":"2117520899","pmid":"https://pubmed.ncbi.nlm.nih.gov/12835265"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btg138","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg138","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/10/1221/48903790/bioinformatics_19_10_1221.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/19/10/1221/48903790/bioinformatics_19_10_1221.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061545123","display_name":"Ketil Malde","orcid":"https://orcid.org/0000-0001-7381-1849"},"institutions":[{"id":"https://openalex.org/I4432739","display_name":"University of Bergen","ror":"https://ror.org/03zga2b32","country_code":"NO","type":"education","lineage":["https://openalex.org/I4432739"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Ketil Malde","raw_affiliation_strings":["Department of Informatics, University of Bergen, HIB, N5020 Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Bergen, HIB, N5020 Norway","institution_ids":["https://openalex.org/I4432739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104962826","display_name":"Eivind Coward","orcid":null},"institutions":[{"id":"https://openalex.org/I4432739","display_name":"University of Bergen","ror":"https://ror.org/03zga2b32","country_code":"NO","type":"education","lineage":["https://openalex.org/I4432739"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Eivind Coward","raw_affiliation_strings":["Department of Informatics, University of Bergen, HIB, N5020 Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Bergen, HIB, N5020 Norway","institution_ids":["https://openalex.org/I4432739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012964587","display_name":"Inge Jonassen","orcid":"https://orcid.org/0000-0003-4110-0748"},"institutions":[{"id":"https://openalex.org/I4432739","display_name":"University of Bergen","ror":"https://ror.org/03zga2b32","country_code":"NO","type":"education","lineage":["https://openalex.org/I4432739"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Inge Jonassen","raw_affiliation_strings":["Department of Informatics, University of Bergen, HIB, N5020 Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, University of Bergen, HIB, N5020 Norway","institution_ids":["https://openalex.org/I4432739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4432739"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":7.4315,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.97115271,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"19","issue":"10","first_page":"1221","last_page":"1226"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.18310000002384186,"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":0.18310000002384186,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.09380000084638596,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.09269999712705612,"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":0.7005796432495117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7000375986099243},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.6487702131271362},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.632448673248291},{"id":"https://openalex.org/keywords/suffix-array","display_name":"Suffix array","score":0.6035387516021729},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5380567908287048},{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.47331702709198},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.34266069531440735},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3163199722766876},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.17803403735160828},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10781535506248474},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.06458517909049988}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7005796432495117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7000375986099243},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.6487702131271362},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.632448673248291},{"id":"https://openalex.org/C2779259728","wikidata":"https://www.wikidata.org/wiki/Q281472","display_name":"Suffix array","level":3,"score":0.6035387516021729},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5380567908287048},{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.47331702709198},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.34266069531440735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3163199722766876},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.17803403735160828},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10781535506248474},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.06458517909049988},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","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":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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017385","descriptor_name":"Sequence Homology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017385","descriptor_name":"Sequence Homology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017385","descriptor_name":"Sequence Homology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017421","descriptor_name":"Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020224","descriptor_name":"Expressed Sequence Tags","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020224","descriptor_name":"Expressed Sequence Tags","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020224","descriptor_name":"Expressed Sequence Tags","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btg138","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg138","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/10/1221/48903790/bioinformatics_19_10_1221.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:12835265","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12835265","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.598.9533","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.598.9533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/19/10/1221.full.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btg138","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg138","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/10/1221/48903790/bioinformatics_19_10_1221.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2117520899.pdf"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1839674003","https://openalex.org/W1968164578","https://openalex.org/W1971784203","https://openalex.org/W2015292449","https://openalex.org/W2029135821","https://openalex.org/W2055043387","https://openalex.org/W2059513841","https://openalex.org/W2062296203","https://openalex.org/W2074582967","https://openalex.org/W2121252285","https://openalex.org/W2130564474","https://openalex.org/W2150483253","https://openalex.org/W2158874082","https://openalex.org/W2533248932"],"related_works":["https://openalex.org/W2003608043","https://openalex.org/W153119118","https://openalex.org/W2583658747","https://openalex.org/W2405892617","https://openalex.org/W2158874082","https://openalex.org/W1575722140","https://openalex.org/W4293529780","https://openalex.org/W1498395615","https://openalex.org/W2073921136","https://openalex.org/W2055795184"],"abstract_inverted_index":{"MOTIVATION:":[0],"Efficient":[1],"clustering":[2,51],"is":[3,34,53,58,109],"important":[4],"for":[5,105],"handling":[6],"the":[7,40,96,106],"large":[8],"amount":[9],"of":[10,22,43],"available":[11,110],"EST":[12,44,50],"sequences.":[13],"Most":[14],"contemporary":[15],"methods":[16],"are":[17,84,98],"based":[18,64],"on":[19,65,76],"some":[20],"kind":[21],"all-against-all":[23],"comparison,":[24],"resulting":[25],"in":[26],"a":[27,77,112],"quadratic":[28],"time":[29,56],"complexity.":[30],"A":[31,47,68],"different":[32],"approach":[33],"needed":[35],"to":[36,89],"keep":[37],"up":[38],"with":[39],"rapid":[41],"growth":[42],"data.":[45],"RESULTS:":[46],"new,":[48],"fast":[49],"algorithm":[52,63],"presented.":[54],"Sub-quadratic":[55],"complexity":[57],"achieved":[59],"by":[60,86,92],"using":[61],"an":[62],"suffix":[66],"arrays.":[67],"prototype":[69,107],"implementation":[70,108],"has":[71],"been":[72],"developed":[73],"and":[74,95],"run":[75],"benchmark":[78],"data":[79],"set.":[80],"The":[81,102],"produced":[82,91],"clusterings":[83,90],"validated":[85],"comparing":[87],"them":[88],"other":[93],"methods,":[94],"results":[97],"quite":[99],"promising.":[100],"AVAILABILITY:":[101],"source":[103],"code":[104],"under":[111],"GPL":[113],"license":[114],"from":[115],"http://www.ii.uib.no/~ketil/bio/.":[116]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2025-10-10T00:00:00"}
