{"id":"https://openalex.org/W2095256334","doi":"https://doi.org/10.1186/1471-2105-13-286","title":"Identifying structural domains of proteins using clustering","display_name":"Identifying structural domains of proteins using clustering","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W2095256334","doi":"https://doi.org/10.1186/1471-2105-13-286","mag":"2095256334","pmid":"https://pubmed.ncbi.nlm.nih.gov/23116496"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-13-286","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-286","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-286","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/10.1186/1471-2105-13-286","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111967615","display_name":"Howard J. Feldman","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Howard J Feldman","raw_affiliation_strings":["Chemical Computing Group, Inc., Montreal, Quebec, Canada. feldman@chemcomp.com","Chemical Computing Group, Inc., Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chemical Computing Group, Inc., Montreal, Quebec, Canada. feldman@chemcomp.com","institution_ids":[]},{"raw_affiliation_string":"Chemical Computing Group, Inc., Montreal, Canada","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5111967615"],"corresponding_institution_ids":[],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.5375,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.66103603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"13","issue":"1","first_page":"286","last_page":"286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.8586999773979187,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.8586999773979187,"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":0.029400000348687172,"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":0.02160000056028366,"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/computational-biology","display_name":"Computational biology","score":0.6775367259979248},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6352865099906921},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.5576276779174805},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4498556852340698},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.38862574100494385},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.35506701469421387},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.26730597019195557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21514472365379333},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1264764368534088},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.10030761361122131}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6775367259979248},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6352865099906921},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.5576276779174805},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4498556852340698},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.38862574100494385},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.35506701469421387},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.26730597019195557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21514472365379333},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1264764368534088},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.10030761361122131}],"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":"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":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":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017434","descriptor_name":"Protein Structure, Tertiary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017434","descriptor_name":"Protein Structure, Tertiary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017434","descriptor_name":"Protein Structure, Tertiary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","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":"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":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/1471-2105-13-286","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-286","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-286","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:23116496","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23116496","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:doaj.org/article:7c9d630a49ff4550911b532c1f643547","is_oa":true,"landing_page_url":"https://doaj.org/article/7c9d630a49ff4550911b532c1f643547","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 13, Iss 1, p 286 (2012)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:2537051","is_oa":true,"landing_page_url":"http://europepmc.org/articles/PMC3534501","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":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:3534501","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3534501","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-13-286","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-286","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-286","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":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2095256334.pdf","grobid_xml":"https://content.openalex.org/works/W2095256334.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1553258895","https://openalex.org/W1965910641","https://openalex.org/W1969692838","https://openalex.org/W1978012062","https://openalex.org/W2008708467","https://openalex.org/W2043530041","https://openalex.org/W2049355199","https://openalex.org/W2052002049","https://openalex.org/W2052895859","https://openalex.org/W2055043387","https://openalex.org/W2055118532","https://openalex.org/W2055227231","https://openalex.org/W2062732178","https://openalex.org/W2063627598","https://openalex.org/W2085277871","https://openalex.org/W2108067237","https://openalex.org/W2116423958","https://openalex.org/W2119902292","https://openalex.org/W2133062651","https://openalex.org/W2135621733","https://openalex.org/W2138116388","https://openalex.org/W2141885858","https://openalex.org/W2147805410","https://openalex.org/W2164045406","https://openalex.org/W2167308484","https://openalex.org/W2515184929","https://openalex.org/W4320301318"],"related_works":["https://openalex.org/W2082860237","https://openalex.org/W2119695867","https://openalex.org/W2130076355","https://openalex.org/W1990804418","https://openalex.org/W1993764875","https://openalex.org/W2046158694","https://openalex.org/W2788277189","https://openalex.org/W2013243191","https://openalex.org/W2117258802","https://openalex.org/W4234157524"],"abstract_inverted_index":{"BACKGROUND:":[0],"Protein":[1],"structures":[2],"are":[3,13,73,216],"comprised":[4],"of":[5,43,79,150,225,231,247,259],"modular":[6],"elements":[7],"known":[8],"as":[9,197,201,244],"domains.":[10],"These":[11],"units":[12],"used":[14],"and":[15,18,22,71,87,117,126,170,185],"re-used":[16],"over":[17,19],"in":[20,28,178,251],"nature,":[21],"usually":[23],"serve":[24],"some":[25,206],"particular":[26],"function":[27],"the":[29,82,151,219,242],"structure.":[30,152],"Thus":[31],"it":[32,253],"is":[33,115,155,190],"useful":[34],"to":[35,38,50,75,81,100,124,147,256],"be":[36],"able":[37],"break":[39,257],"up":[40],"a":[41,67,77,96,121,148,165,173,193,228,245],"protein":[42,69,214],"interest":[44],"into":[45],"its":[46],"component":[47],"domains,":[48],"prior":[49],"similarity":[51],"searching":[52],"for":[53,59,218],"example.":[54],"Numerous":[55],"computational":[56],"methods":[57],"exist":[58],"doing":[60],"so,":[61],"but":[62],"most":[63,220],"operate":[64],"only":[65,120],"on":[66,107,164,172,181],"single":[68],"chain":[70],"many":[72],"limited":[74],"making":[76],"series":[78],"cuts":[80],"sequence,":[83],"while":[84],"domains":[85,215],"can":[86],"do":[88],"span":[89],"multiple":[90],"chains.":[91],"RESULTS:":[92],"This":[93,211],"study":[94],"presents":[95],"novel":[97],"clustering-based":[98],"approach":[99],"domain":[101,149],"identification,":[102],"which":[103,182],"works":[104,127],"equally":[105],"well":[106,202],"individual":[108],"chains":[109],"or":[110,136,203,249],"entire":[111],"complexes.":[112],"The":[113,153],"method":[114,154,195],"simple":[116],"fast,":[118],"taking":[119],"few":[122],"milliseconds":[123],"run,":[125],"by":[128],"clustering":[129],"either":[130],"vectors":[131,250],"representing":[132,241],"secondary":[133],"structure":[134,226,243],"elements,":[135],"buried":[137,232],"alpha-carbon":[138],"positions,":[139],"using":[140],"average-linkage":[141],"clustering.":[142],"Each":[143],"resulting":[144],"cluster":[145],"corresponds":[146],"competitive":[156],"with":[157,162,227],"others,":[158],"achieving":[159],"70%":[160],"agreement":[161],"SCOP":[163,184],"large":[166],"non-redundant":[167],"data":[168],"set,":[169],"80%":[171],"set":[174,246],"more":[175,208],"heavily":[176],"weighted":[177],"multi-domain":[179],"proteins":[180],"both":[183],"CATH":[186],"agree.":[187],"CONCLUSIONS:":[188],"It":[189],"encouraging":[191],"that":[192,213,263],"basic":[194],"such":[196],"this":[198],"performs":[199],"nearly":[200],"better":[204],"than":[205,236],"far":[207],"complex":[209],"approaches.":[210],"suggests":[212],"indeed":[217],"part":[221],"simply":[222],"compact":[223],"regions":[224],"higher":[229],"density":[230],"contacts":[233],"within":[234],"themselves":[235],"between":[237],"each":[238],"other.":[239],"By":[240],"points":[248],"space,":[252],"allows":[254],"us":[255],"free":[258],"any":[260],"artificial":[261],"limitations":[262],"other":[264],"approaches":[265],"may":[266],"depend":[267],"upon.":[268]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}