{"id":"https://openalex.org/W1774262081","doi":"https://doi.org/10.1186/1471-2105-5-183","title":"Protein family comparison using statistical models and predicted structural information","display_name":"Protein family comparison using statistical models and predicted structural information","publication_year":2004,"publication_date":"2004-11-25","ids":{"openalex":"https://openalex.org/W1774262081","doi":"https://doi.org/10.1186/1471-2105-5-183","mag":"1774262081","pmid":"https://pubmed.ncbi.nlm.nih.gov/15563734"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-5-183","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-5-183","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-5-183","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/10.1186/1471-2105-5-183","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001127061","display_name":"Richard Chung","orcid":"https://orcid.org/0000-0003-2272-4969"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Chung","raw_affiliation_strings":["Department of Computer Science, Cornell University, Ithaca, NY 14850, USA. rc238@cornell.edu","Department of Computer Science, Cornell-University, Ithaca, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Cornell University, Ithaca, NY 14850, USA. rc238@cornell.edu","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Department of Computer Science, Cornell-University, Ithaca, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001926130","display_name":"Golan Yona","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Golan Yona","raw_affiliation_strings":["Department of Computer Science, Cornell University, Ithaca, NY, 14850, USA","Department of Computer Science, Cornell-University, Ithaca, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Cornell University, Ithaca, NY, 14850, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Department of Computer Science, Cornell-University, Ithaca, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5001926130"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":1.1352,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.74304146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"5","issue":"1","first_page":"183","last_page":"183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.8077999949455261,"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":0.8077999949455261,"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":0.04919999837875366,"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":0.036400001496076584,"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-secondary-structure","display_name":"Protein secondary structure","score":0.6777852773666382},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5319393277168274},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4619482159614563},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4494471549987793},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43475541472435},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33480435609817505},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3347899317741394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3156634569168091},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.21938389539718628}],"concepts":[{"id":"https://openalex.org/C62614982","wikidata":"https://www.wikidata.org/wiki/Q904984","display_name":"Protein secondary structure","level":2,"score":0.6777852773666382},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5319393277168274},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4619482159614563},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4494471549987793},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43475541472435},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33480435609817505},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3347899317741394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3156634569168091},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.21938389539718628},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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}],"mesh":[{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011237","descriptor_name":"Predictive Value of Tests","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011237","descriptor_name":"Predictive Value of Tests","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011237","descriptor_name":"Predictive Value of Tests","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":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/1471-2105-5-183","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-5-183","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-5-183","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:15563734","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15563734","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:europepmc.org:103477","is_oa":false,"landing_page_url":"http://europepmc.org/pmc/articles/PMC544344","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:544344","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/544344","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:26deb6a307a548099196b4080df79d73","is_oa":false,"landing_page_url":"https://doaj.org/article/26deb6a307a548099196b4080df79d73","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 5, Iss 1, p 183 (2004)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-5-183","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-5-183","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-5-183","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":[{"id":"https://openalex.org/G6946545560","display_name":"CAREER:   Global Self-Organization of all Known Proteins - Toward a Complete Map of the Protein Space","funder_award_id":"0133311","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1774262081.pdf","grobid_xml":"https://content.openalex.org/works/W1774262081.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W10876090","https://openalex.org/W1542067597","https://openalex.org/W1970742573","https://openalex.org/W1981276685","https://openalex.org/W1984675929","https://openalex.org/W1986825290","https://openalex.org/W1991809396","https://openalex.org/W2015292449","https://openalex.org/W2029358573","https://openalex.org/W2039330662","https://openalex.org/W2052450063","https://openalex.org/W2057157558","https://openalex.org/W2059168883","https://openalex.org/W2073739993","https://openalex.org/W2074235299","https://openalex.org/W2085277871","https://openalex.org/W2099075703","https://openalex.org/W2102677343","https://openalex.org/W2105767494","https://openalex.org/W2106241755","https://openalex.org/W2118817344","https://openalex.org/W2118848941","https://openalex.org/W2123838014","https://openalex.org/W2124919568","https://openalex.org/W2135221645","https://openalex.org/W2141920771","https://openalex.org/W2143079199","https://openalex.org/W2143210482","https://openalex.org/W2146950091","https://openalex.org/W2147667050","https://openalex.org/W2153187042","https://openalex.org/W2157975034","https://openalex.org/W2158714788","https://openalex.org/W2317912355","https://openalex.org/W2778716599","https://openalex.org/W4212774754","https://openalex.org/W4256395558"],"related_works":["https://openalex.org/W2078778136","https://openalex.org/W2933325505","https://openalex.org/W2020577335","https://openalex.org/W2117934800","https://openalex.org/W2386796734","https://openalex.org/W2083563479","https://openalex.org/W2472013057","https://openalex.org/W2375480909","https://openalex.org/W2031291218","https://openalex.org/W2353314428"],"abstract_inverted_index":{"BACKGROUND:":[0],"This":[1],"paper":[2],"presents":[3],"a":[4],"simple":[5],"method":[6,39],"to":[7],"increase":[8],"the":[9,24,73,87],"sensitivity":[10],"of":[11,69,95,105],"protein":[12,67,110],"family":[13],"comparisons":[14],"by":[15],"incorporating":[16],"secondary":[17,45,89,98],"structure":[18,46,90,99],"(SS)":[19],"information.":[20],"We":[21],"build":[22],"upon":[23],"effective":[25],"information":[26,53,100],"theory":[27],"approach":[28],"towards":[29],"profile-profile":[30],"comparison":[31],"described":[32],"in":[33,82],"[Yona":[34],"&":[35],"Levitt":[36],"2002].":[37],"Our":[38,57],"augments":[40],"profile":[41],"columns":[42],"using":[43,52],"PSIPRED":[44],"predictions":[47],"and":[48,97],"assesses":[49],"statistical":[50],"similarity":[51],"theoretical":[54],"principles.":[55],"RESULTS:":[56],"tests":[58],"show":[59],"that":[60],"this":[61],"tool":[62],"detects":[63],"more":[64],"similarities":[65],"between":[66,107],"families":[68],"distant":[70],"homology":[71],"than":[72],"previous":[74],"primary":[75,96],"sequence-based":[76],"method.":[77],"A":[78],"very":[79],"significant":[80],"improvement":[81],"performance":[83],"is":[84,91],"observed":[85],"when":[86],"real":[88],"used.":[92],"CONCLUSIONS:":[93],"Integration":[94],"can":[101],"substantially":[102],"improve":[103],"detection":[104],"relationships":[106],"remotely":[108],"related":[109],"families.":[111]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
