{"id":"https://openalex.org/W2154265303","doi":"https://doi.org/10.3233/ica-2009-0323","title":"A hybrid framework for protein sequence clustering and classification using signature motif information","display_name":"A hybrid framework for protein sequence clustering and classification using signature motif information","publication_year":2009,"publication_date":"2009-10-03","ids":{"openalex":"https://openalex.org/W2154265303","doi":"https://doi.org/10.3233/ica-2009-0323","mag":"2154265303"},"language":"en","primary_location":{"id":"doi:10.3233/ica-2009-0323","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ica-2009-0323","pdf_url":null,"source":{"id":"https://openalex.org/S107631664","display_name":"Integrated Computer-Aided Engineering","issn_l":"1069-2509","issn":["1069-2509","1875-8835"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Integrated Computer-Aided Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5072192748","display_name":"Wei-Bang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei-Bang Chen","raw_affiliation_strings":["Department of Computer and Information Sciences, University of Alabama at Birmingham, Birmingham, AL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, University of Alabama at Birmingham, Birmingham, AL, USA","institution_ids":["https://openalex.org/I32389192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061568662","display_name":"Chengcui Zhang","orcid":"https://orcid.org/0000-0002-5868-6450"},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chengcui Zhang","raw_affiliation_strings":["Department of Computer and Information Sciences, University of Alabama at Birmingham, Birmingham, AL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, University of Alabama at Birmingham, Birmingham, AL, USA","institution_ids":["https://openalex.org/I32389192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5061568662"],"corresponding_institution_ids":["https://openalex.org/I32389192"],"apc_list":null,"apc_paid":null,"fwci":0.54,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.67417632,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"16","issue":"4","first_page":"353","last_page":"365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9973000288009644,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9973000288009644,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9970999956130981,"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":0.9966999888420105,"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":0.8046931028366089},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.711905837059021},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5893893241882324},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5830132365226746},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5566439032554626},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.5054173469543457},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.503842294216156},{"id":"https://openalex.org/keywords/consensus-clustering","display_name":"Consensus clustering","score":0.4888016879558563},{"id":"https://openalex.org/keywords/structural-motif","display_name":"Structural motif","score":0.4842528998851776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4820331335067749},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4629209041595459},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4346785247325897},{"id":"https://openalex.org/keywords/motif","display_name":"Motif (music)","score":0.43112361431121826},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.38834887742996216},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.25102895498275757},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15536925196647644},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10770931839942932},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.0801522433757782}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8046931028366089},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.711905837059021},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5893893241882324},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5830132365226746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5566439032554626},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.5054173469543457},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.503842294216156},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.4888016879558563},{"id":"https://openalex.org/C132677234","wikidata":"https://www.wikidata.org/wiki/Q3273544","display_name":"Structural motif","level":2,"score":0.4842528998851776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4820331335067749},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4629209041595459},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4346785247325897},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.43112361431121826},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.38834887742996216},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.25102895498275757},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15536925196647644},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10770931839942932},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0801522433757782},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/ica-2009-0323","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ica-2009-0323","pdf_url":null,"source":{"id":"https://openalex.org/S107631664","display_name":"Integrated Computer-Aided Engineering","issn_l":"1069-2509","issn":["1069-2509","1875-8835"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Integrated Computer-Aided Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337398","display_name":"Division of Biological Infrastructure","ror":"https://ror.org/04qn9mx93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1731069122","https://openalex.org/W1969051510","https://openalex.org/W2009570821","https://openalex.org/W2094454470","https://openalex.org/W2098425296","https://openalex.org/W2099182237","https://openalex.org/W2107634512","https://openalex.org/W2109681892","https://openalex.org/W2125079066","https://openalex.org/W2133828198","https://openalex.org/W2138615112","https://openalex.org/W2140190241","https://openalex.org/W2143210482","https://openalex.org/W2151831732","https://openalex.org/W3147254695"],"related_works":["https://openalex.org/W4312222690","https://openalex.org/W4224256651","https://openalex.org/W2476489150","https://openalex.org/W2150969552","https://openalex.org/W3029084886","https://openalex.org/W3159946074","https://openalex.org/W2799087180","https://openalex.org/W4231226332","https://openalex.org/W2126459812","https://openalex.org/W4285248592"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"an":[5],"unsupervised":[6],"hybrid":[7,32,59],"framework":[8,23,150],"for":[9,119,151],"protein":[10,17,28,40],"sequence":[11,35,54,133,153],"clustering":[12,60,78,88,154],"and":[13,34,68,100,144,155],"classification":[14],"which":[15,89,123],"incorporates":[16],"structural":[18,29,41],"motif":[19,30,42],"information.":[20],"The":[21,37,56,110],"proposed":[22,57,149],"consists":[24],"of":[25,39,65,131,147],"three":[26],"stages:":[27],"scan,":[31],"clustering,":[33],"classification.":[36,156],"incorporation":[38],"detected":[43],"by":[44,126],"ScanProsite":[45],"service":[46],"provides":[47],"a":[48,132],"better":[49],"measurement":[50],"in":[51,116],"calculating":[52],"the":[53,63,66,69,75,86,95,117,128,142,145,148],"similarity.":[55],"two-phase":[58],"approach":[61],"combines":[62],"strengths":[64],"hierarchical":[67,76],"partition":[70,87,92],"clustering.":[71],"Phase":[72,83,98],"I":[73,99],"adopts":[74],"agglomerative":[77],"to":[79,107,134],"pre-cluster":[80],"multi-aligned":[81],"sequences.":[82],"II":[84],"performs":[85],"initiates":[90],"its":[91],"based":[93],"on":[94],"result":[96],"from":[97],"uses":[101],"profile":[102,111,137],"Hidden":[103],"Markov":[104],"Models":[105],"(HMMs)":[106],"represent":[108],"clusters.":[109],"HMMs":[112],"are":[113],"then":[114],"stored":[115],"database":[118],"unknown":[120],"sequences":[121],"classification,":[122],"is":[124],"done":[125],"finding":[127],"best":[129],"alignment":[130],"each":[135],"existing":[136],"HMM.":[138],"Our":[139],"experiments":[140],"demonstrate":[141],"effectiveness":[143],"efficiency":[146],"biological":[152]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-23T06:36:01.041984","created_date":"2025-10-10T00:00:00"}