{"id":"https://openalex.org/W2158810446","doi":"https://doi.org/10.1186/1471-2105-6-s2-s3","title":"CLU: A new algorithm for EST clustering","display_name":"CLU: A new algorithm for EST clustering","publication_year":2005,"publication_date":"2005-07-01","ids":{"openalex":"https://openalex.org/W2158810446","doi":"https://doi.org/10.1186/1471-2105-6-s2-s3","mag":"2158810446","pmid":"https://pubmed.ncbi.nlm.nih.gov/16026600"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-6-s2-s3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-s2-s3","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-S2-S3","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/10.1186/1471-2105-6-S2-S3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055434163","display_name":"Andrey Ptitsyn","orcid":"https://orcid.org/0000-0003-1196-8757"},"institutions":[{"id":"https://openalex.org/I103990859","display_name":"Pennington Biomedical Research Center","ror":"https://ror.org/040cnym54","country_code":"US","type":"facility","lineage":["https://openalex.org/I103990859"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrey Ptitsyn","raw_affiliation_strings":["Pennington Biomedical Research Center, 6400 Perkins Rd, Baton Rouge LA 70808, USA. ptitsyaa@pbrc.edu","Pennington Biomedical Research Center, 6400 Perkins Rd, Baton Rouge, LA, 70808, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pennington Biomedical Research Center, 6400 Perkins Rd, Baton Rouge LA 70808, USA. ptitsyaa@pbrc.edu","institution_ids":["https://openalex.org/I103990859"]},{"raw_affiliation_string":"Pennington Biomedical Research Center, 6400 Perkins Rd, Baton Rouge, LA, 70808, USA","institution_ids":["https://openalex.org/I103990859"]}]},{"author_position":"last","author":{"id":null,"display_name":"Winston Hide","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087898","display_name":"South African National Biodiversity Institute","ror":"https://ror.org/005r3tp02","country_code":"ZA","type":"facility","lineage":["https://openalex.org/I4210087898"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Winston Hide","raw_affiliation_strings":["South African National Bioinformatics Institute, P/b X17 UWC SANBI, Bellville, 7535, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South African National Bioinformatics Institute, P/b X17 UWC SANBI, Bellville, 7535, South Africa","institution_ids":["https://openalex.org/I4210087898"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055434163"],"corresponding_institution_ids":["https://openalex.org/I103990859"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":1.0686,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.75209322,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"6","issue":"S2","first_page":"S3","last_page":"S3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.2184000015258789,"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/T10885","display_name":"Gene expression and cancer classification","score":0.2184000015258789,"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":0.18449999392032623,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.15369999408721924,"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":0.7556077241897583},{"id":"https://openalex.org/keywords/unigene","display_name":"UniGene","score":0.6672277450561523},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.5121667385101318},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5096864700317383},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5018010139465332},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4849134087562561},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4113942086696625},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37828728556632996},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3244761824607849},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.3137395977973938},{"id":"https://openalex.org/keywords/expressed-sequence-tag","display_name":"Expressed sequence tag","score":0.2419377565383911},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20922818779945374},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2074929177761078},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.19203338027000427}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7556077241897583},{"id":"https://openalex.org/C2780330800","wikidata":"https://www.wikidata.org/wiki/Q7884647","display_name":"UniGene","level":5,"score":0.6672277450561523},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.5121667385101318},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5096864700317383},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5018010139465332},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4849134087562561},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4113942086696625},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37828728556632996},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3244761824607849},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3137395977973938},{"id":"https://openalex.org/C149034497","wikidata":"https://www.wikidata.org/wiki/Q1384835","display_name":"Expressed sequence tag","level":4,"score":0.2419377565383911},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20922818779945374},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2074929177761078},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.19203338027000427}],"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":"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":"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":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/1471-2105-6-s2-s3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-s2-s3","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-S2-S3","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:16026600","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16026600","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:eprints.whiterose.ac.uk:115755","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:europepmc.org:1190960","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1637039","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:1637039","is_oa":true,"landing_page_url":"http://doi.org/10.1186/1471-2105-6-S2-S3","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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:10.1186/1471-2105-6-s2-s3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-s2-s3","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-S2-S3","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":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2158810446.pdf","grobid_xml":"https://content.openalex.org/works/W2158810446.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1968164578","https://openalex.org/W2003153830","https://openalex.org/W2020285640","https://openalex.org/W2035483212","https://openalex.org/W2041956242","https://openalex.org/W2054631442","https://openalex.org/W2068719237","https://openalex.org/W2104189907","https://openalex.org/W2117520899","https://openalex.org/W2150483253","https://openalex.org/W2164429509","https://openalex.org/W2168838971","https://openalex.org/W2782267736"],"related_works":["https://openalex.org/W2090165572","https://openalex.org/W1976590931","https://openalex.org/W2045375070","https://openalex.org/W1988866597","https://openalex.org/W1026390558","https://openalex.org/W2009988114","https://openalex.org/W2076099888","https://openalex.org/W2146014453","https://openalex.org/W1972257067","https://openalex.org/W1999647786"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,18,97,117,157],"continuous":[2],"flow":[3],"of":[4,9,33,35,77,136,168],"EST":[5,22,29,51,95,137],"data":[6,23],"remains":[7],"one":[8],"the":[10,31,102,113],"richest":[11],"sources":[12],"for":[13,93],"discoveries":[14],"in":[15,21,54,69,152],"modern":[16],"biology.":[17],"first":[19],"step":[20],"mining":[24],"is":[25,99,160],"usually":[26],"associated":[27],"with":[28,140],"clustering,":[30],"process":[32],"grouping":[34],"original":[36,103],"fragments":[37],"according":[38],"to":[39,43,66,75],"their":[40],"annotation,":[41],"similarity":[42],"known":[44],"genomic":[45],"DNA":[46],"or":[47],"each":[48],"other.":[49],"Clustered":[50],"data,":[52],"accumulated":[53],"databases":[55],"such":[56],"as":[57],"UniGene,":[58],"STACK":[59],"and":[60,90,126,154],"TIGR":[61],"Gene":[62],"Indices":[63],"have":[64,82],"proven":[65],"be":[67,150,172],"crucial":[68],"research":[70],"areas":[71],"from":[72,174],"gene":[73,78],"discovery":[74],"regulation":[76],"expression.":[79],"RESULTS:":[80],"We":[81],"developed":[83],"a":[84,133],"new":[85,134],"nucleotide":[86],"sequence":[87],"matching":[88],"algorithm":[89,119,139],"its":[91],"implementation":[92,148],"clustering":[94,138],"sequences.":[96],"program":[98,159],"based":[100],"on":[101,162],"CLU":[104,118,131,158],"match":[105],"detection":[106],"algorithm,":[107],"which":[108],"has":[109],"improved":[110,141],"performance":[111,142],"over":[112,143],"widely":[114],"used":[115],"d2_cluster.":[116],"automatically":[120],"ignores":[121],"low-complexity":[122],"regions":[123],"like":[124],"poly-tracts":[125],"short":[127],"tandem":[128],"repeats.":[129],"CONCLUSION:":[130],"represents":[132],"generation":[135],"current":[144],"approaches.":[145],"An":[146],"early":[147],"can":[149,171],"applied":[151],"small":[153],"medium-size":[155],"projects.":[156],"available":[161],"an":[163],"open":[164],"source":[165],"basis":[166],"free":[167],"charge.":[169],"It":[170],"downloaded":[173],"http://compbio.pbrc.edu/pti.":[175]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
