{"id":"https://openalex.org/W2050828070","doi":"https://doi.org/10.1186/1471-2105-5-56","title":"Enhanced protein domain discovery using taxonomy","display_name":"Enhanced protein domain discovery using taxonomy","publication_year":2004,"publication_date":"2004-05-11","ids":{"openalex":"https://openalex.org/W2050828070","doi":"https://doi.org/10.1186/1471-2105-5-56","mag":"2050828070","pmid":"https://pubmed.ncbi.nlm.nih.gov/15137915"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-5-56","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-5-56","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-5-56","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":null,"license_id":null,"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/10.1186/1471-2105-5-56","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056039026","display_name":"Lachlan Coin","orcid":"https://orcid.org/0000-0002-4300-455X"},"institutions":[{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Lachlan Coin","raw_affiliation_strings":["Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SA, UK. lc1@sanger.ac.uk","Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SA, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SA, UK. lc1@sanger.ac.uk","institution_ids":["https://openalex.org/I2802476451"]},{"raw_affiliation_string":"Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SA, UK","institution_ids":["https://openalex.org/I2802476451"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059430118","display_name":"Alex Bateman","orcid":"https://orcid.org/0000-0002-6982-4660"},"institutions":[{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alex Bateman","raw_affiliation_strings":["Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SA, UK","Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SA, UK","institution_ids":["https://openalex.org/I2802476451"]},{"raw_affiliation_string":"Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton,","institution_ids":["https://openalex.org/I2802476451"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082040351","display_name":"Richard Durbin","orcid":"https://orcid.org/0000-0002-9130-1006"},"institutions":[{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Richard Durbin","raw_affiliation_strings":["Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SA, UK","Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SA, UK","institution_ids":["https://openalex.org/I2802476451"]},{"raw_affiliation_string":"Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton,","institution_ids":["https://openalex.org/I2802476451"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5056039026"],"corresponding_institution_ids":["https://openalex.org/I2802476451"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":1.1337,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.75094987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"5","issue":"1","first_page":"56","last_page":"56"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.25780001282691956,"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":0.25780001282691956,"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":0.19949999451637268,"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":0.14270000159740448,"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/protein-domain","display_name":"Protein domain","score":0.6381876468658447},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6339505910873413},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5666595697402954},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5285263061523438},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48526450991630554},{"id":"https://openalex.org/keywords/protein-family","display_name":"Protein family","score":0.48480501770973206},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.483009934425354},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48261865973472595},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4733940362930298},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3741551637649536},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.35866692662239075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2890341281890869},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.20512276887893677},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.18823027610778809},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10724997520446777},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.0951281487941742},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08203420042991638}],"concepts":[{"id":"https://openalex.org/C144292202","wikidata":"https://www.wikidata.org/wiki/Q898273","display_name":"Protein domain","level":3,"score":0.6381876468658447},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6339505910873413},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5666595697402954},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5285263061523438},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48526450991630554},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.48480501770973206},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.483009934425354},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48261865973472595},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4733940362930298},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3741551637649536},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.35866692662239075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2890341281890869},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.20512276887893677},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.18823027610778809},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10724997520446777},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0951281487941742},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08203420042991638},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"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":"Q000145","qualifier_name":"classification","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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","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":"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":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.1186/1471-2105-5-56","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-5-56","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-5-56","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:15137915","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15137915","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:9ae0e2bf0ea0415fa7d1439ee4b04677","is_oa":true,"landing_page_url":"https://doaj.org/article/9ae0e2bf0ea0415fa7d1439ee4b04677","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 5, Iss 1, p 56 (2004)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:102784","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC434490","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:jupiter.its.unimelb.edu.au:11343/269927","is_oa":false,"landing_page_url":"http://hdl.handle.net/11343/269927","pdf_url":null,"source":{"id":"https://openalex.org/S4377196259","display_name":"Minerva Access (University of Melbourne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165779595","host_organization_name":"The University of Melbourne","host_organization_lineage":["https://openalex.org/I165779595"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:434490","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/434490","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-5-56","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-5-56","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-5-56","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.4699999988079071,"display_name":"Life in Land"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311904","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2050828070.pdf","grobid_xml":"https://content.openalex.org/works/W2050828070.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1972370260","https://openalex.org/W2009570821","https://openalex.org/W2050637786","https://openalex.org/W2054439791","https://openalex.org/W2055787938","https://openalex.org/W2058336694","https://openalex.org/W2102122585","https://openalex.org/W2117077088","https://openalex.org/W2121085676","https://openalex.org/W2126377763","https://openalex.org/W2141885858","https://openalex.org/W2151831732","https://openalex.org/W2158714788","https://openalex.org/W2164836215","https://openalex.org/W4210400672","https://openalex.org/W4245668478"],"related_works":["https://openalex.org/W2102122585","https://openalex.org/W2119410807","https://openalex.org/W2111805188","https://openalex.org/W2952660917","https://openalex.org/W3165639034","https://openalex.org/W2346203657","https://openalex.org/W2584692412","https://openalex.org/W1967097205","https://openalex.org/W1514151181","https://openalex.org/W2800194647"],"abstract_inverted_index":{"BACKGROUND:":[0],"It":[1],"is":[2],"well":[3],"known":[4,124],"that":[5,15,43],"different":[6,9],"species":[7],"have":[8],"protein":[10,17,54,62,145,149,167],"domain":[11,59,101,150,159,164],"repertoires,":[12],"and":[13,92,126,166],"indeed":[14],"some":[16],"domains":[18,34,71,146],"are":[19],"kingdom":[20],"specific.":[21],"This":[22],"information":[23],"has":[24],"not":[25],"yet":[26],"been":[27],"incorporated":[28],"into":[29],"statistical":[30],"methods":[31],"for":[32],"finding":[33],"in":[35,61,72,97],"sequences":[36],"of":[37,48,52,69,89,100,121,123,144],"amino":[38],"acids.":[39],"RESULTS:":[40],"We":[41,64,103,111],"show":[42],"by":[44,85],"incorporating":[45],"our":[46,108,114],"understanding":[47],"the":[49,73,81,86,98,141],"taxonomic":[50,142],"distribution":[51,143],"specific":[53],"domains,":[55],"we":[56],"can":[57,147,154],"enhance":[58,148],"recognition":[60],"sequences.":[63],"identify":[65],"4447":[66],"new":[67,109],"instances":[68],"Pfam":[70,90],"SP-TREMBL":[74],"database":[75],"using":[76,116],"this":[77],"technique,":[78],"equivalent":[79],"to":[80,93,106,130],"coverage":[82],"increase":[83,96],"given":[84],"last":[87],"8.3%":[88],"families":[91],"a":[94,117],"0.7%":[95],"number":[99],"predictions.":[102,110],"use":[104],"PSI-BLAST":[105],"cross-validate":[107],"also":[112,155],"benchmark":[113],"approach":[115],"SCOP":[118],"test":[119],"set":[120],"proteins":[122],"structure,":[125],"demonstrate":[127],"improvements":[128],"relative":[129],"standard":[131],"Hidden":[132],"Markov":[133],"model":[134],"techniques.":[135],"CONCLUSIONS:":[136],"Explicitly":[137],"including":[138],"knowledge":[139],"about":[140],"recognition.":[151],"Our":[152],"method":[153],"incorporate":[156],"other":[157],"context-specific":[158],"distributions":[160],"-":[161],"such":[162],"as":[163],"co-occurrence":[165],"localisation.":[168]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}