{"id":"https://openalex.org/W2110340112","doi":"https://doi.org/10.1186/s12859-014-0445-4","title":"Evaluation and improvements of clustering algorithms for detecting remote homologous protein families","display_name":"Evaluation and improvements of clustering algorithms for detecting remote homologous protein families","publication_year":2015,"publication_date":"2015-02-04","ids":{"openalex":"https://openalex.org/W2110340112","doi":"https://doi.org/10.1186/s12859-014-0445-4","mag":"2110340112","pmid":"https://pubmed.ncbi.nlm.nih.gov/25651949"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-014-0445-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-014-0445-4","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-014-0445-4","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/s12859-014-0445-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089115213","display_name":"Juliana Bernardes","orcid":"https://orcid.org/0000-0003-1341-4256"},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210097156","display_name":"Biologie Computationnelle, Quantitative et Synth\u00e9tique","ror":"https://ror.org/00pcqj134","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210096427","https://openalex.org/I4210097156"]}],"countries":["BR","FR"],"is_corresponding":true,"raw_author_name":"Juliana S Bernardes","raw_affiliation_strings":["Programa de Engenharia de Sistemas e Computa\u00e7\u00e3o, COPPE, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil. juliana.silva_bernardes@upmc.fr","Sorbonne Universit\u00e9s, UPMC Univ Paris 06, UMR 7238, Biologie Computationnelle et Quantitative, Paris, France. juliana.silva_bernardes@upmc.fr","Sorbonne Universit\u00e9s, Paris, France","Programa de Engenharia de Sistemas e Computa\u00e7\u00e3o, COPPE, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Programa de Engenharia de Sistemas e Computa\u00e7\u00e3o, COPPE, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil. juliana.silva_bernardes@upmc.fr","institution_ids":["https://openalex.org/I122140584"]},{"raw_affiliation_string":"Sorbonne Universit\u00e9s, UPMC Univ Paris 06, UMR 7238, Biologie Computationnelle et Quantitative, Paris, France. juliana.silva_bernardes@upmc.fr","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4210097156"]},{"raw_affiliation_string":"Sorbonne Universit\u00e9s, Paris, France","institution_ids":["https://openalex.org/I39804081"]},{"raw_affiliation_string":"Programa de Engenharia de Sistemas e Computa\u00e7\u00e3o, COPPE, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I122140584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107345849","display_name":"Fabio RJ Vieira","orcid":null},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Fabio RJ Vieira","raw_affiliation_strings":["Programa de Engenharia de Sistemas e Computa\u00e7\u00e3o, COPPE, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil. fjimenez@cos.ufrj.br","Programa de Engenharia de Sistemas e Computa\u00e7\u00e3o, COPPE, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Programa de Engenharia de Sistemas e Computa\u00e7\u00e3o, COPPE, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil. fjimenez@cos.ufrj.br","institution_ids":["https://openalex.org/I122140584"]},{"raw_affiliation_string":"Programa de Engenharia de Sistemas e Computa\u00e7\u00e3o, COPPE, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I122140584"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035499392","display_name":"Lygia MM Costa","orcid":null},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lygia MM Costa","raw_affiliation_strings":["Engenharia de Computa\u00e7\u00e3o e Informa\u00e7\u00e3o, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil. lmmc@poli.ufrj.br","Engenharia de Computa\u00e7\u00e3o e Informa\u00e7\u00e3o, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engenharia de Computa\u00e7\u00e3o e Informa\u00e7\u00e3o, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil. lmmc@poli.ufrj.br","institution_ids":["https://openalex.org/I122140584"]},{"raw_affiliation_string":"Engenharia de Computa\u00e7\u00e3o e Informa\u00e7\u00e3o, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I122140584"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012291023","display_name":"Gerson Zaverucha","orcid":"https://orcid.org/0000-0002-3641-6839"},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Gerson Zaverucha","raw_affiliation_strings":["Programa de Engenharia de Sistemas e Computa\u00e7\u00e3o, COPPE, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil. gerson@cos.ufrj.br","Programa de Engenharia de Sistemas e Computa\u00e7\u00e3o, COPPE, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Programa de Engenharia de Sistemas e Computa\u00e7\u00e3o, COPPE, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil. gerson@cos.ufrj.br","institution_ids":["https://openalex.org/I122140584"]},{"raw_affiliation_string":"Programa de Engenharia de Sistemas e Computa\u00e7\u00e3o, COPPE, Universidade Federal do Rio de Janeiro, Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I122140584"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089115213","https://openalex.org/A5107345849"],"corresponding_institution_ids":["https://openalex.org/I122140584","https://openalex.org/I39804081","https://openalex.org/I4210097156"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":2.6167,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.90319249,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"16","issue":"1","first_page":"34","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.3596000075340271,"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":0.3596000075340271,"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":0.2743000090122223,"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":0.156700000166893,"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":0.8430600762367249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5461635589599609},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5264763832092285},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5117930769920349},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.47791653871536255},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.47117120027542114},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.4699585437774658},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4522826671600342},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4303072690963745},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.428190678358078},{"id":"https://openalex.org/keywords/protein-superfamily","display_name":"Protein superfamily","score":0.4265443682670593},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.4241781234741211},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.42295753955841064},{"id":"https://openalex.org/keywords/structural-classification-of-proteins-database","display_name":"Structural Classification of Proteins database","score":0.42215052247047424},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.41973042488098145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33469158411026},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.30654388666152954},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.24567413330078125},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.1789579689502716},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.17121323943138123},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.15152060985565186}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8430600762367249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5461635589599609},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5264763832092285},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5117930769920349},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.47791653871536255},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.47117120027542114},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4699585437774658},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4522826671600342},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4303072690963745},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.428190678358078},{"id":"https://openalex.org/C178180057","wikidata":"https://www.wikidata.org/wiki/Q7251477","display_name":"Protein superfamily","level":3,"score":0.4265443682670593},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.4241781234741211},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.42295753955841064},{"id":"https://openalex.org/C58773245","wikidata":"https://www.wikidata.org/wiki/Q4832556","display_name":"Structural Classification of Proteins database","level":3,"score":0.42215052247047424},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.41973042488098145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33469158411026},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.30654388666152954},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.24567413330078125},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.1789579689502716},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.17121323943138123},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.15152060985565186},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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":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":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"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":"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":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019143","descriptor_name":"Evolution, Molecular","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":4,"locations":[{"id":"doi:10.1186/s12859-014-0445-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-014-0445-4","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-014-0445-4","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:25651949","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25651949","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:HAL:hal-01143450v1","is_oa":false,"landing_page_url":"https://hal.sorbonne-universite.fr/hal-01143450","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, 2015, 16 (1), pp.34. ⟨10.1186/s12859-014-0445-4⟩","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:europepmc.org:3304144","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4339679","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"}],"best_oa_location":{"id":"doi:10.1186/s12859-014-0445-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-014-0445-4","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-014-0445-4","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313934","display_name":"Institut national de recherche en informatique et en automatique (INRIA)","ror":"https://ror.org/02kvxyf05"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320322749","display_name":"Funda\u00e7\u00e3o Carlos Chagas Filho de Amparo \u00e0 Pesquisa do Estado do Rio de Janeiro","ror":"https://ror.org/03kk0s825"},{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"},{"id":"https://openalex.org/F4320323678","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Ci\u00eancia e Tecnologia do Estado de Pernambuco","ror":"https://ror.org/02te5rf52"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2110340112.pdf","grobid_xml":"https://content.openalex.org/works/W2110340112.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W349216298","https://openalex.org/W567708786","https://openalex.org/W1482644886","https://openalex.org/W1565377632","https://openalex.org/W1680392829","https://openalex.org/W1981029985","https://openalex.org/W1986075313","https://openalex.org/W2015530520","https://openalex.org/W2047606947","https://openalex.org/W2051210555","https://openalex.org/W2055043387","https://openalex.org/W2058720919","https://openalex.org/W2059223767","https://openalex.org/W2082819719","https://openalex.org/W2097263991","https://openalex.org/W2097555181","https://openalex.org/W2109820980","https://openalex.org/W2110734043","https://openalex.org/W2117077088","https://openalex.org/W2124166542","https://openalex.org/W2131681506","https://openalex.org/W2135152200","https://openalex.org/W2137745608","https://openalex.org/W2145268834","https://openalex.org/W2145358391","https://openalex.org/W2152219892","https://openalex.org/W2482589566","https://openalex.org/W2497532187","https://openalex.org/W2531563875","https://openalex.org/W2611831635","https://openalex.org/W3099768174","https://openalex.org/W4235848672"],"related_works":["https://openalex.org/W2075451741","https://openalex.org/W2164753093","https://openalex.org/W2139240863","https://openalex.org/W2070693796","https://openalex.org/W2121560377","https://openalex.org/W4386644018","https://openalex.org/W2053803793","https://openalex.org/W4291397982","https://openalex.org/W2138921203","https://openalex.org/W2821108685"],"abstract_inverted_index":{"BACKGROUND:":[0],"An":[1],"important":[2],"problem":[3],"in":[4],"computational":[5],"biology":[6],"is":[7,22,81,104],"the":[8,24,66,89,152,160,163,165,183,194,199,205,214,217,238,251,263],"automatic":[9],"detection":[10],"of":[11,15,26,52,68,91,97,113,125,132,142,147,162,216,266,275],"protein":[12,32,133,277],"families":[13,21],"(groups":[14],"homologous":[16,102],"sequences).":[17],"Clustering":[18,118,121,124],"sequences":[19,134],"into":[20],"at":[23,271],"heart":[25],"most":[27,255],"comparative":[28,111],"studies":[29],"dealing":[30],"with":[31,57,139],"evolution,":[33],"structure,":[34],"and":[35,45,129,172],"function.":[36],"Many":[37],"methods":[38,70,99,253,269],"have":[39],"been":[40],"developed":[41],"for":[42,62,182,193,241,254,262],"this":[43],"task,":[44],"they":[46],"perform":[47],"reasonably":[48],"well":[49],"(over":[50],"0.88":[51],"F-measure)":[53],"when":[54,198,221],"grouping":[55],"proteins":[56,65,103],"high":[58],"sequence":[59,86,143,154,224,268],"identity.":[60],"However,":[61,204],"highly":[63,195],"diverged":[64],"performance":[67,161,192,215],"these":[69],"can":[71],"be":[72],"much":[73],"lower,":[74],"mainly":[75],"because":[76],"a":[77,94,110,173,232],"common":[78],"evolutionary":[79],"origin":[80],"not":[82],"deduced":[83],"directly":[84],"from":[85,169],"similarity.":[87,144],"To":[88],"best":[90,239],"our":[92],"knowledge,":[93],"systematic":[95],"evaluation":[96],"clustering":[98,115,131,153,191,243,267],"over":[100],"distant":[101],"still":[105],"lacking.":[106],"RESULTS:":[107],"We":[108,229,245],"performed":[109,231],"assessment":[112],"four":[114,218],"algorithms:":[116,164],"Markov":[117],"(MCL),":[119],"Transitive":[120],"(TransClust),":[122],"Spectral":[123],"Protein":[126],"Sequences":[127],"(SCPS),":[128],"High-Fidelity":[130],"(HiFix),":[135],"considering":[136],"several":[137],"datasets":[138,197,226],"different":[140],"levels":[141],"Two":[145],"types":[146],"similarity":[148],"measures,":[149],"required":[150],"by":[151],"methods,":[155,219],"were":[156,227],"used":[157,180],"to":[158,236],"evaluate":[159],"standard":[166,200],"measure":[167,175,201,207],"obtained":[168],"sequence-sequence":[170],"comparisons,":[171,179],"novel":[174,206],"based":[176,208],"on":[177,209],"profile-profile":[178,210],"here":[181],"first":[184],"time.":[185],"CONCLUSIONS:":[186],"The":[187],"results":[188],"reveal":[189],"low":[190,223],"divergent":[196],"was":[202],"used.":[203],"comparisons":[211],"substantially":[212],"improved":[213],"especially":[220],"very":[222],"identity":[225],"evaluated.":[228],"also":[230,259],"parameter":[233],"optimization":[234],"step":[235],"determine":[237],"configuration":[240],"each":[242],"method.":[244],"found":[246],"that":[247],"TransClust":[248],"clearly":[249],"outperformed":[250],"other":[252],"datasets.":[256],"This":[257],"work":[258],"provides":[260],"guidelines":[261],"practical":[264],"application":[265],"aimed":[270],"detecting":[272],"accurately":[273],"groups":[274],"related":[276],"sequences.":[278]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}