{"id":"https://openalex.org/W2147758638","doi":"https://doi.org/10.1093/bioinformatics/btg397","title":"Graph-based clustering for finding distant relationships in a large set of protein sequences","display_name":"Graph-based clustering for finding distant relationships in a large set of protein sequences","publication_year":2004,"publication_date":"2004-01-20","ids":{"openalex":"https://openalex.org/W2147758638","doi":"https://doi.org/10.1093/bioinformatics/btg397","mag":"2147758638","pmid":"https://pubmed.ncbi.nlm.nih.gov/14734316"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btg397","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg397","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/2/243/48905271/bioinformatics_20_2_243.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/20/2/243/48905271/bioinformatics_20_2_243.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051284054","display_name":"Hideya Kawaji","orcid":"https://orcid.org/0000-0002-0575-0308"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"Osaka University","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hideya Kawaji","raw_affiliation_strings":["Department of Bioinformatic Engineering, Graduate School of Information Science and Technology, Osaka University, 1-3 Machikaneyama, Toyonaka, Osaka 560-8531, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Bioinformatic Engineering, Graduate School of Information Science and Technology, Osaka University, 1-3 Machikaneyama, Toyonaka, Osaka 560-8531, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110041664","display_name":"Yoichi Takenaka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoichi Takenaka","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007909918","display_name":"Hideo Matsuda","orcid":"https://orcid.org/0000-0002-4701-3779"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hideo Matsuda","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051284054"],"corresponding_institution_ids":["https://openalex.org/I98285908"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.0525,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.74694895,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"20","issue":"2","first_page":"243","last_page":"252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9987000226974487,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9987000226974487,"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":0.996999979019165,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9958000183105469,"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":0.811303973197937},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5683503150939941},{"id":"https://openalex.org/keywords/uniprot","display_name":"UniProt","score":0.5665921568870544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5389086008071899},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4545412063598633},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3855352997779846},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3433419466018677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31699293851852417},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2157478928565979},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1845778226852417},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1705777645111084}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.811303973197937},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5683503150939941},{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.5665921568870544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5389086008071899},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4545412063598633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3855352997779846},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3433419466018677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31699293851852417},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2157478928565979},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1845778226852417},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1705777645111084}],"mesh":[{"descriptor_ui":"D000089622","descriptor_name":"Doublecortin Domain Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000089622","descriptor_name":"Doublecortin Domain Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000089622","descriptor_name":"Doublecortin Domain Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008040","descriptor_name":"Genetic Linkage","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008040","descriptor_name":"Genetic Linkage","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008040","descriptor_name":"Genetic Linkage","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D008869","descriptor_name":"Microtubule-Associated Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008869","descriptor_name":"Microtubule-Associated Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008869","descriptor_name":"Microtubule-Associated Proteins","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009479","descriptor_name":"Neuropeptides","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009479","descriptor_name":"Neuropeptides","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009479","descriptor_name":"Neuropeptides","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009479","descriptor_name":"Neuropeptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D009479","descriptor_name":"Neuropeptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D009479","descriptor_name":"Neuropeptides","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011494","descriptor_name":"Protein Kinases","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","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":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017386","descriptor_name":"Sequence Homology, Amino Acid","qualifier_ui":null,"qualifier_name":null,"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},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btg397","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg397","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/2/243/48905271/bioinformatics_20_2_243.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:14734316","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/14734316","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}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btg397","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg397","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/20/2/243/48905271/bioinformatics_20_2_243.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":[{"display_name":"Partnerships for the goals","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2147758638.pdf","grobid_xml":"https://content.openalex.org/works/W2147758638.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1480983574","https://openalex.org/W1513332069","https://openalex.org/W1514113870","https://openalex.org/W1769049279","https://openalex.org/W1870496269","https://openalex.org/W1982121407","https://openalex.org/W1997268601","https://openalex.org/W2003144438","https://openalex.org/W2015292449","https://openalex.org/W2024645073","https://openalex.org/W2076336658","https://openalex.org/W2081123379","https://openalex.org/W2087885007","https://openalex.org/W2095117703","https://openalex.org/W2100272598","https://openalex.org/W2109681892","https://openalex.org/W2110732466","https://openalex.org/W2114030927","https://openalex.org/W2121564430","https://openalex.org/W2124166542","https://openalex.org/W2125806930","https://openalex.org/W2127648442","https://openalex.org/W2129621613","https://openalex.org/W2133828198","https://openalex.org/W2140000690","https://openalex.org/W2141885858","https://openalex.org/W2146827656","https://openalex.org/W2148512362","https://openalex.org/W2158714788","https://openalex.org/W2161455936","https://openalex.org/W2163181687","https://openalex.org/W2798909945"],"related_works":["https://openalex.org/W24553703","https://openalex.org/W4211000692","https://openalex.org/W4212920271","https://openalex.org/W2612240612","https://openalex.org/W4324018414","https://openalex.org/W4211208250","https://openalex.org/W4211054902","https://openalex.org/W2170381940","https://openalex.org/W2472351724","https://openalex.org/W3145366215"],"abstract_inverted_index":{"The":[0],"complete":[1],"result":[2],"of":[3],"our":[4],"algorithm":[5],"for":[6],"all":[7],"the":[8],"human":[9],"proteins":[10],"in":[11],"SWISS-PROT":[12],"and":[13,15],"TrEMBL,":[14],"other":[16],"supplementary":[17],"information":[18],"are":[19],"available":[20],"at":[21],"http://motif.ics.es.osaka-u.ac.jp/Ncut-KL/":[22]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
