{"id":"https://openalex.org/W1606410455","doi":"https://doi.org/10.1186/1471-2105-7-301","title":"Improving the accuracy of protein secondary structure prediction using structural alignment","display_name":"Improving the accuracy of protein secondary structure prediction using structural alignment","publication_year":2006,"publication_date":"2006-06-14","ids":{"openalex":"https://openalex.org/W1606410455","doi":"https://doi.org/10.1186/1471-2105-7-301","mag":"1606410455","pmid":"https://pubmed.ncbi.nlm.nih.gov/16774686"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-7-301","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-301","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-301","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/10.1186/1471-2105-7-301","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082654320","display_name":"Scott Montgomerie","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Scott Montgomerie","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, AB, T6G 2E8, Canada. montgomerie@shaw.ca","Department of Computing Science, University of Alberta, Edmonton, AB, T6G 2E8, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB, T6G 2E8, Canada. montgomerie@shaw.ca","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB, T6G 2E8, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059925040","display_name":"Shan Sundararaj","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shan Sundararaj","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, AB, T6G 2E8, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB, T6G 2E8, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055826476","display_name":"Warren J. Gallin","orcid":"https://orcid.org/0000-0002-9937-3880"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Warren J Gallin","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, AB, T6G 2E8, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB, T6G 2E8, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003573061","display_name":"David S. Wishart","orcid":"https://orcid.org/0000-0002-3207-2434"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"David S Wishart","raw_affiliation_strings":["Department of Biological Sciences, University of Alberta, Edmonton, AB, T6G 2E9, Canada","Department of Computing Science, University of Alberta, Edmonton, AB, T6G 2E8, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biological Sciences, University of Alberta, Edmonton, AB, T6G 2E9, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB, T6G 2E8, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5003573061"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":4.5774,"has_fulltext":true,"cited_by_count":148,"citation_normalized_percentile":{"value":0.95433006,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"7","issue":"1","first_page":"301","last_page":"301"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.8592000007629395,"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":0.8592000007629395,"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/T11162","display_name":"Enzyme Structure and Function","score":0.0940999984741211,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.007000000216066837,"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/sequence","display_name":"Sequence (biology)","score":0.6697136163711548},{"id":"https://openalex.org/keywords/protein-secondary-structure","display_name":"Protein secondary structure","score":0.6471614837646484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6315698623657227},{"id":"https://openalex.org/keywords/structural-genomics","display_name":"Structural genomics","score":0.5609719753265381},{"id":"https://openalex.org/keywords/protein-structure-database","display_name":"Protein structure database","score":0.5260186791419983},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5258253812789917},{"id":"https://openalex.org/keywords/alignment-free-sequence-analysis","display_name":"Alignment-free sequence analysis","score":0.5024340152740479},{"id":"https://openalex.org/keywords/structural-alignment","display_name":"Structural alignment","score":0.5022435188293457},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.5009732246398926},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"Protein structure prediction","score":0.500962495803833},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.4976842701435089},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45556971430778503},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.4279370903968811},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.41955995559692383},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4037209153175354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3917635679244995},{"id":"https://openalex.org/keywords/sequence-database","display_name":"Sequence database","score":0.38418784737586975},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.19789046049118042},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.18181398510932922},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.12202116847038269}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6697136163711548},{"id":"https://openalex.org/C62614982","wikidata":"https://www.wikidata.org/wiki/Q904984","display_name":"Protein secondary structure","level":2,"score":0.6471614837646484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6315698623657227},{"id":"https://openalex.org/C192772702","wikidata":"https://www.wikidata.org/wiki/Q2583975","display_name":"Structural genomics","level":3,"score":0.5609719753265381},{"id":"https://openalex.org/C136475424","wikidata":"https://www.wikidata.org/wiki/Q7251500","display_name":"Protein structure database","level":4,"score":0.5260186791419983},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5258253812789917},{"id":"https://openalex.org/C180384323","wikidata":"https://www.wikidata.org/wiki/Q16335137","display_name":"Alignment-free sequence analysis","level":5,"score":0.5024340152740479},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.5022435188293457},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.5009732246398926},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.500962495803833},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.4976842701435089},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45556971430778503},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.4279370903968811},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.41955995559692383},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4037209153175354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3917635679244995},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.38418784737586975},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.19789046049118042},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18181398510932922},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12202116847038269},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","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":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","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},{"descriptor_ui":"D040681","descriptor_name":"Structural Homology, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D040681","descriptor_name":"Structural Homology, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D040681","descriptor_name":"Structural Homology, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D040901","descriptor_name":"Proteomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1186/1471-2105-7-301","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-301","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-301","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:16774686","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16774686","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:32adbf7529994babba7cb57627a0aa7b","is_oa":true,"landing_page_url":"https://doaj.org/article/32adbf7529994babba7cb57627a0aa7b","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 7, Iss 1, p 301 (2006)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:350625","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC1550433","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:1550433","is_oa":true,"landing_page_url":"http://doi.org/10.1186/1471-2105-7-301","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:10.1186/1471-2105-7-301","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-301","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-301","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":[{"id":"https://openalex.org/F4320310787","display_name":"Genome Canada","ror":"https://ror.org/029s29983"},{"id":"https://openalex.org/F4320326647","display_name":"Genome Prairie","ror":"https://ror.org/013s3gf12"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1606410455.pdf","grobid_xml":"https://content.openalex.org/works/W1606410455.grobid-xml"},"referenced_works_count":58,"referenced_works":["https://openalex.org/W64282669","https://openalex.org/W1499450468","https://openalex.org/W1513002528","https://openalex.org/W1965151258","https://openalex.org/W1966679395","https://openalex.org/W1983572327","https://openalex.org/W1988496202","https://openalex.org/W1990804602","https://openalex.org/W2008708467","https://openalex.org/W2008922668","https://openalex.org/W2011399646","https://openalex.org/W2027663250","https://openalex.org/W2033496784","https://openalex.org/W2045287375","https://openalex.org/W2046192291","https://openalex.org/W2049695588","https://openalex.org/W2053621743","https://openalex.org/W2057289558","https://openalex.org/W2060809301","https://openalex.org/W2067360567","https://openalex.org/W2068665736","https://openalex.org/W2079928393","https://openalex.org/W2084466582","https://openalex.org/W2095450147","https://openalex.org/W2095791446","https://openalex.org/W2098464924","https://openalex.org/W2106066024","https://openalex.org/W2108211735","https://openalex.org/W2108985827","https://openalex.org/W2109261827","https://openalex.org/W2110863368","https://openalex.org/W2115596146","https://openalex.org/W2122289960","https://openalex.org/W2124354935","https://openalex.org/W2130161623","https://openalex.org/W2130185698","https://openalex.org/W2133179696","https://openalex.org/W2136766277","https://openalex.org/W2137259082","https://openalex.org/W2139279375","https://openalex.org/W2139582206","https://openalex.org/W2139582672","https://openalex.org/W2139592083","https://openalex.org/W2140992384","https://openalex.org/W2141783940","https://openalex.org/W2144112248","https://openalex.org/W2144482798","https://openalex.org/W2147905080","https://openalex.org/W2150408357","https://openalex.org/W2153100136","https://openalex.org/W2153187042","https://openalex.org/W2153582608","https://openalex.org/W2153717161","https://openalex.org/W2158714788","https://openalex.org/W2159136327","https://openalex.org/W2160072419","https://openalex.org/W2161210482","https://openalex.org/W2165206687"],"related_works":["https://openalex.org/W2015399150","https://openalex.org/W2092691595","https://openalex.org/W408054492","https://openalex.org/W2084052949","https://openalex.org/W1983625232","https://openalex.org/W1971429173","https://openalex.org/W2130060890","https://openalex.org/W2099254366","https://openalex.org/W2036521446","https://openalex.org/W2105364679"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1],"accuracy":[2,25,33,254],"of":[3,27,49,58,67,93,103,124,169,182,205],"protein":[4,249],"secondary":[5,18,95,128,139,250,268],"structure":[6,19,40,96,102,140,232,251,269],"prediction":[7,20,51,97,162],"has":[8],"steadily":[9],"improved":[10,37],"over":[11],"the":[12,50,55,59,65,94,101,111,237,282],"past":[13],"30":[14],"years.":[15],"Now":[16],"many":[17],"methods":[21,141],"routinely":[22,247],"achieve":[23,220],"an":[24,178,253],"(Q3)":[26],"about":[28],"75%.":[29],"We":[30,81],"believe":[31],"this":[32,132,174,187,216],"could":[34],"be":[35,289],"further":[36],"by":[38,235],"including":[39],"(as":[41],"opposed":[42],"to":[43,118,150,158,246],"sequence)":[44],"database":[45],"comparisons":[46],"as":[47,91],"part":[48,92],"process.":[52,98],"Indeed,":[53],"given":[54],"large":[56],"size":[57],"Protein":[60],"Data":[61],"Bank":[62],"(>35,000":[63],"sequences),":[64],"probability":[66],"a":[68,73,84,104,122,147,152,165,221],"newly":[69],"identified":[70],"sequence":[71,89,230,280],"having":[72],"structural":[74,133,212],"homologue":[75,106],"is":[76,116,156,188,244,271],"actually":[77],"quite":[78],"high.":[79],"RESULTS:":[80],"have":[82],"developed":[83],"method":[85,176,195,218],"that":[86,125,215,265],"performs":[87,266],"structure-based":[88],"alignments":[90],"By":[99,130,227],"mapping":[100],"known":[105],"(sequence":[107],"ID":[108],">25%)":[109],"onto":[110],"query":[112,126],"protein's":[113,127],"sequence,":[114],"it":[115,145,155,243],"possible":[117,157,245],"predict":[119,248],"at":[120,273],"least":[121],"portion":[123],"structure.":[129],"integrating":[131],"alignment":[134],"approach":[135],"with":[136,146,252],"conventional":[137],"(sequence-based)":[138],"and":[142,231,234,260,291],"then":[143],"combining":[144],"\"jury-of-experts\"":[148],"system":[149],"generate":[151],"consensus":[153],"result,":[154],"attain":[159],"very":[160],"high":[161,276],"accuracy.":[163],"Using":[164],"sequence-unique":[166,201],"test":[167,202],"set":[168],"1644":[170],"proteins":[171],"from":[172],"EVA,":[173],"new":[175,217],"achieves":[177],"average":[179],"Q3":[180,222],"score":[181,223],"81.3%.":[183],"Extensive":[184],"testing":[185],"indicates":[186],"approximately":[189],"4-5%":[190],"better":[191],"than":[192],"any":[193],"other":[194],"currently":[196],"available.":[197],"Assessments":[198],"using":[199,228],"non":[200],"sets":[203],"(typical":[204],"those":[206],"used":[207],"in":[208,240],"proteome":[209],"annotation":[210],"or":[211,278],"genomics)":[213],"indicate":[214],"can":[219,288],"approaching":[224],"88%.":[225],"CONCLUSION:":[226],"both":[229],"databases":[233,285],"exploiting":[236],"latest":[238],"techniques":[239],"machine":[241],"learning":[242],"well":[255],"above":[256],"80%.":[257],"A":[258],"program":[259],"web":[261],"server,":[262],"called":[263],"PROTEUS,":[264],"these":[267],"predictions":[270],"accessible":[272],"http://wishart.biology.ualberta.ca/proteus.":[274],"For":[275],"throughput":[277],"batch":[279],"analyses,":[281],"PROTEUS":[283],"programs,":[284],"(and":[286],"server)":[287],"downloaded":[290],"run":[292],"locally.":[293]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":9}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}