{"id":"https://openalex.org/W2015696044","doi":"https://doi.org/10.1093/bioinformatics/btg392","title":"Comparative evaluation of word composition distances for the recognition of SCOP relationships","display_name":"Comparative evaluation of word composition distances for the recognition of SCOP relationships","publication_year":2004,"publication_date":"2004-01-20","ids":{"openalex":"https://openalex.org/W2015696044","doi":"https://doi.org/10.1093/bioinformatics/btg392","mag":"2015696044","pmid":"https://pubmed.ncbi.nlm.nih.gov/14734312"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btg392","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg392","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005271169","display_name":"Susana Vinga","orcid":"https://orcid.org/0000-0002-1954-5487"},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Susana Vinga","raw_affiliation_strings":["Biomathematics Group, ITQB, Universidade Nova de Lisboa, Rua da Quinta Grande, n. 6, 2780-156 Oeiras, Portugal. svinga@itqb.unl.pt","Biomathematics Group, ITQB, Universidade Nova de Lisboa, Rua da Quinta Grande, n. 6, 2780-156 Oeiras, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomathematics Group, ITQB, Universidade Nova de Lisboa, Rua da Quinta Grande, n. 6, 2780-156 Oeiras, Portugal. svinga@itqb.unl.pt","institution_ids":["https://openalex.org/I83558840"]},{"raw_affiliation_string":"Biomathematics Group, ITQB, Universidade Nova de Lisboa, Rua da Quinta Grande, n. 6, 2780-156 Oeiras, Portugal","institution_ids":["https://openalex.org/I83558840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060509394","display_name":"Rodrigo Gouveia\u2010Oliveira","orcid":null},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Rodrigo Gouveia-Oliveira","raw_affiliation_strings":["Biomathematics Group, ITQB, Universidade Nova de Lisboa, Rua da Quinta Grande, n. 6, 2780-156 Oeiras, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomathematics Group, ITQB, Universidade Nova de Lisboa, Rua da Quinta Grande, n. 6, 2780-156 Oeiras, Portugal","institution_ids":["https://openalex.org/I83558840"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012322429","display_name":"Jonas S. Almeida","orcid":"https://orcid.org/0000-0002-7883-7922"},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jonas S. Almeida","raw_affiliation_strings":["Biomathematics Group, ITQB, Universidade Nova de Lisboa, Rua da Quinta Grande, n. 6, 2780-156 Oeiras, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomathematics Group, ITQB, Universidade Nova de Lisboa, Rua da Quinta Grande, n. 6, 2780-156 Oeiras, Portugal","institution_ids":["https://openalex.org/I83558840"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5005271169"],"corresponding_institution_ids":["https://openalex.org/I83558840"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.1975,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.76166339,"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":"206","last_page":"215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7353000044822693,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7353000044822693,"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":0.042899999767541885,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.025499999523162842,"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/word","display_name":"Word (group theory)","score":0.7314989566802979},{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.7036142945289612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6327438950538635},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6057659983634949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49270060658454895},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4148104190826416},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3374800384044647},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.230575293302536},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1166301965713501}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7314989566802979},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.7036142945289612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6327438950538635},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6057659983634949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49270060658454895},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4148104190826416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3374800384044647},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.230575293302536},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1166301965713501},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","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":"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/btg392","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg392","pdf_url":null,"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:14734312","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/14734312","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":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G4388583276","display_name":null,"funder_award_id":"N01-HV-28181","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"}],"funders":[{"id":"https://openalex.org/F4320337338","display_name":"National Heart, Lung, and Blood Institute","ror":"https://ror.org/012pb6c26"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W21816278","https://openalex.org/W154905459","https://openalex.org/W1480577415","https://openalex.org/W1502621331","https://openalex.org/W1536719366","https://openalex.org/W1996357466","https://openalex.org/W2015292449","https://openalex.org/W2015328208","https://openalex.org/W2037430361","https://openalex.org/W2042084565","https://openalex.org/W2053392780","https://openalex.org/W2055043387","https://openalex.org/W2061029680","https://openalex.org/W2080336769","https://openalex.org/W2085277871","https://openalex.org/W2089499735","https://openalex.org/W2107432340","https://openalex.org/W2118475569","https://openalex.org/W2126377763","https://openalex.org/W2138422173","https://openalex.org/W2141262207","https://openalex.org/W2143210482","https://openalex.org/W2145358391","https://openalex.org/W2155480785","https://openalex.org/W2155653793","https://openalex.org/W2157975034","https://openalex.org/W2171963266","https://openalex.org/W2954364924","https://openalex.org/W3142026388"],"related_works":["https://openalex.org/W1499958165","https://openalex.org/W2380193321","https://openalex.org/W2041489351","https://openalex.org/W2367936492","https://openalex.org/W2588831577","https://openalex.org/W2749776132","https://openalex.org/W4229073194","https://openalex.org/W3130838260","https://openalex.org/W2047062245","https://openalex.org/W2390217813"],"abstract_inverted_index":{"MOTIVATION:":[0],"Alignment-free":[1],"metrics":[2,29],"were":[3],"recently":[4],"reviewed":[5],"by":[6,53,94],"the":[7,23,42,54,78,86,98,163,173,180],"authors,":[8],"but":[9],"have":[10],"not":[11],"until":[12],"now":[13],"been":[14],"object":[15],"of":[16,26,89,139],"a":[17,35],"comparative":[18,73],"study.":[19],"This":[20,144],"paper":[21],"compares":[22],"classification":[24,110],"accuracy":[25,111],"word":[27,155],"composition":[28],"therein":[30],"reviewed.":[31],"It":[32],"also":[33],"presents":[34],"new":[36],"distance":[37,67],"definition":[38],"between":[39,46],"protein":[40,80],"sequences,":[41],"W-metric,":[43],"which":[44],"bridges":[45],"alignment":[47,104,128,164],"metrics,":[48],"such":[49,64,135],"as":[50,65,125,127,136],"scores":[51],"produced":[52],"Smith-Waterman":[55],"algorithm,":[56],"and":[57,68,84,114],"methods":[58,105],"based":[59],"solely":[60],"in":[61,107,119],"L-tuple":[62],"composition,":[63],"Euclidean":[66,122],"Information":[69],"content.":[70],"RESULTS:":[71],"The":[72],"study":[74],"reported":[75],"here":[76],"used":[77,170],"SCOP/ASTRAL":[79],"structure":[81],"hierarchical":[82],"database":[83],"accessed":[85],"discriminant":[87],"value":[88],"alternative":[90],"sequence":[91,131],"dissimilarity":[92],"measures":[93],"calculating":[95],"areas":[96],"under":[97],"Receiver":[99],"Operating":[100],"Characteristic":[101],"curves.":[102],"Although":[103],"resulted":[106],"very":[108],"good":[109,126],"at":[112,185],"family":[113],"superfamily":[115],"levels,":[116],"alignment-free":[117],"distances,":[118],"particular":[120],"Standard":[121],"Distance,":[123],"are":[124,158],"algorithms":[129],"when":[130],"similarity":[132],"is":[133,175],"smaller,":[134],"for":[137],"recognition":[138],"fold":[140],"or":[141],"class":[142],"relationships.":[143],"observation":[145],"justifies":[146],"its":[147],"advantageous":[148],"use":[149],"to":[150,171,179],"pre-filter":[151],"homologous":[152],"proteins":[153],"since":[154],"statistics":[156],"techniques":[157],"computed":[159],"much":[160],"faster":[161],"than":[162],"methods.":[165],"AVAILABILITY:":[166],"All":[167],"MATLAB":[168],"code":[169],"generate":[172],"data":[174],"available":[176,184],"upon":[177],"request":[178],"authors.":[181],"Additional":[182],"material":[183],"http://bioinformatics.musc.edu/wmetric":[186]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-16T07:32:37.131356","created_date":"2025-10-10T00:00:00"}