{"id":"https://openalex.org/W2145010684","doi":null,"title":"Clustering of database sequences for fast homology search using upper bounds on alignment score.","display_name":"Clustering of database sequences for fast homology search using upper bounds on alignment score.","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2145010684","mag":"2145010684","pmid":"https://pubmed.ncbi.nlm.nih.gov/15712113"},"language":"en","primary_location":{"id":"pmid:15712113","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15712113","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,"listed_in":[],"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":"Genome informatics. International Conference on Genome Informatics","raw_type":"Journal Article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020657282","display_name":"Masumi Itoh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I4399598384","display_name":"Kyoto University Institute for Chemical Research","ror":"https://ror.org/0349bbg69","country_code":"JP","type":"facility","lineage":["https://openalex.org/I22299242","https://openalex.org/I4399598384"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masumi Itoh","raw_affiliation_strings":["Bioinformatics Center, Institute for Chemical Research, Kyoto University, Gokasho, Uji, Kyoto 611-0011, Japan. itoh@kuicr.kyoto-u.ac.jp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Center, Institute for Chemical Research, Kyoto University, Gokasho, Uji, Kyoto 611-0011, Japan. itoh@kuicr.kyoto-u.ac.jp","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4399598384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016330265","display_name":"Tatsuya Akutsu","orcid":"https://orcid.org/0000-0001-9763-797X","observed_orcids":["https://orcid.org/0000-0001-9763-797X"]},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I4399598384","display_name":"Kyoto University Institute for Chemical Research","ror":"https://ror.org/0349bbg69","country_code":"JP","type":"facility","lineage":["https://openalex.org/I22299242","https://openalex.org/I4399598384"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Akutsu","raw_affiliation_strings":["Bioinformatics Center, Institute for Chemical Research, Kyoto University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Center, Institute for Chemical Research, Kyoto University,","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4399598384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058022821","display_name":"Minoru I. Kanehisa","orcid":"https://orcid.org/0000-0001-6123-540X","observed_orcids":["https://orcid.org/0000-0001-6123-540X"]},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I4399598384","display_name":"Kyoto University Institute for Chemical Research","ror":"https://ror.org/0349bbg69","country_code":"JP","type":"facility","lineage":["https://openalex.org/I22299242","https://openalex.org/I4399598384"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Minoru Kanehisa","raw_affiliation_strings":["Bioinformatics Center, Institute for Chemical Research, Kyoto University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioinformatics Center, Institute for Chemical Research, Kyoto University,","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4399598384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8692,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.91282051,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":"15","issue":"1","first_page":"93","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8773999810218811,"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":0.8773999810218811,"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":0.08609999716281891,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.02070000022649765,"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/homology-search","display_name":"homology search","score":0.9589999914169312},{"id":"https://openalex.org/keywords/sequence-clustering","display_name":"sequence clustering","score":0.7960000038146973},{"id":"https://openalex.org/keywords/representative-sequences","display_name":"representative sequences","score":0.7940000295639038},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"protein function prediction","score":0.7179999947547913},{"id":"https://openalex.org/keywords/closely-related-species","display_name":"closely related species","score":0.5820000171661377}],"concepts":[{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.7169013619422913},{"id":"https://openalex.org/C152724338","wikidata":"https://www.wikidata.org/wiki/Q909442","display_name":"KEGG","level":5,"score":0.6048334240913391},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5984384417533875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5827139019966125},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.5769100189208984},{"id":"https://openalex.org/C72802188","wikidata":"https://www.wikidata.org/wiki/Q1683352","display_name":"Smith\u2013Waterman algorithm","level":5,"score":0.5396080613136292},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5097038745880127},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.4886763393878937},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44708991050720215},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37583085894584656},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29501068592071533},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.23001539707183838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21581020951271057},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.188745379447937},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12042555212974548},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.11638256907463074},{"id":"https://openalex.org/C2987395477","wikidata":"https://www.wikidata.org/wiki/Q135085","display_name":"Gene ontology","level":4,"score":0.10705623030662537},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012475","descriptor_name":"Salmonella","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D012475","descriptor_name":"Salmonella","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D012689","descriptor_name":"Sequence Homology, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012763","descriptor_name":"Shigella flexneri","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D012763","descriptor_name":"Shigella flexneri","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D013698","descriptor_name":"Templates, Genetic","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":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"pmid:15712113","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15712113","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,"listed_in":[],"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":"Genome informatics. International Conference on Genome Informatics","raw_type":"Journal Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.141.3992","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.3992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.jsbi.org/journal/IBSB04/IBSB04F016.pdf","raw_type":"text"},{"id":"mag:2145010684","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15712113","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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":"PubMed","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W21816278","https://openalex.org/W1567829109","https://openalex.org/W2029195137","https://openalex.org/W2046042060","https://openalex.org/W2055043387","https://openalex.org/W2055666215","https://openalex.org/W2072967946","https://openalex.org/W2087064593","https://openalex.org/W2108211735","https://openalex.org/W2108317509","https://openalex.org/W2118597789","https://openalex.org/W2128591967","https://openalex.org/W2130200371","https://openalex.org/W2132967231","https://openalex.org/W2140000393","https://openalex.org/W2141885858","https://openalex.org/W2142237411","https://openalex.org/W2143210482","https://openalex.org/W2151891691","https://openalex.org/W2158714788","https://openalex.org/W2165156013","https://openalex.org/W2611804663"],"related_works":["https://openalex.org/W2151891691","https://openalex.org/W2103187775","https://openalex.org/W2770136439","https://openalex.org/W2108211735","https://openalex.org/W2171289182","https://openalex.org/W2894048249","https://openalex.org/W2572179285","https://openalex.org/W1989977771","https://openalex.org/W1976369037","https://openalex.org/W1576445761"],"abstract_inverted_index":{"Homology":[0],"data":[1],"are":[2,22,114,146,160],"among":[3],"the":[4,11,59,72,75,82,95,98,109,112,128,134,138,150,164,167,177,181,185],"most":[5],"important":[6],"information":[7],"used":[8],"to":[9,81,173],"predict":[10],"functions":[12],"of":[13,54,58,105,141,176],"unknown":[14],"proteins":[15],"and":[16,19,34,66,77,120,137],"thus":[17],"fast":[18,33],"accurate":[20,35],"methods":[21],"needed.":[23],"In":[24,84],"this":[25,85,89],"paper,":[26,86],"we":[27,92],"propose":[28],"a":[29,44,50,64,67,78,117,156],"new":[30],"approach":[31],"for":[32,52,107,124,143,162,180,195],"homology":[36],"search":[37],"using":[38,71,88,184],"pre-computed":[39],"all-against-all":[40],"similarity":[41],"scores":[42],"in":[43,97,111,166],"target":[45,99],"database.":[46],"We":[47,169],"previously":[48],"developed":[49],"method":[51,179,192],"derivation":[53],"an":[55],"upper":[56,90,103,139,151],"bound":[57,152],"Smith-Waterman":[60],"score":[61],"(SW-score)":[62],"between":[63,74],"query":[65,129],"homolog":[68],"candidate":[69,76],"sequence":[70,79,130],"SW-score":[73],"similar":[80],"query.":[83],"by":[87],"bound,":[91],"first":[93],"cluster":[94],"sequences":[96,123,136,165],"database":[100,183],"so":[101],"that":[102,190,198],"bounds":[104,140],"SW-scores":[106,142],"all":[108,163],"members":[110],"clusters":[113,145],"less":[115],"than":[116,155],"given":[118,157],"value":[119],"select":[121],"representative":[122,135],"respective":[125,144],"clusters.":[126],"Then,":[127],"is":[131,153,193],"searched":[132],"against":[133],"estimated.":[147],"Only":[148],"if":[149],"higher":[154],"threshold,":[158],"SW-alignments":[159],"computed":[161],"cluster.":[168],"performed":[170],"computational":[171],"experiments":[172],"test":[174],"efficiency":[175],"proposed":[178],"KEGG/GENES":[182],"KEGG/SSDB.":[186],"The":[187],"results":[188],"suggest":[189],"our":[191],"efficient":[194],"redundant":[196],"databases":[197],"include":[199],"multiple":[200],"closely":[201],"related":[202],"species.":[203]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}
