{"id":"https://openalex.org/W2041944280","doi":"https://doi.org/10.1186/1471-2105-8-294","title":"Quantitative sequence-function relationships in proteins based on gene ontology","display_name":"Quantitative sequence-function relationships in proteins based on gene ontology","publication_year":2007,"publication_date":"2007-08-08","ids":{"openalex":"https://openalex.org/W2041944280","doi":"https://doi.org/10.1186/1471-2105-8-294","mag":"2041944280","pmid":"https://pubmed.ncbi.nlm.nih.gov/17686158"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-8-294","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-8-294","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-8-294","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/10.1186/1471-2105-8-294","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051188171","display_name":"Vineet Sangar","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vineet Sangar","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, Center of Computational Biology and Genomics, The Huck Institute for Genomics, Proteomics and Bioinformatics, The Pennsylvania State University, University Park, PA 16802, USA. vus102@psu.edu","Department of Biochemistry and Molecular Biology, Center of Computational Biology and Genomics, The Huck Institute for Genomics, Proteomics and Bioinformatics, The Pennsylvania State University, , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, Center of Computational Biology and Genomics, The Huck Institute for Genomics, Proteomics and Bioinformatics, The Pennsylvania State University, University Park, PA 16802, USA. vus102@psu.edu","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, Center of Computational Biology and Genomics, The Huck Institute for Genomics, Proteomics and Bioinformatics, The Pennsylvania State University, , USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075101770","display_name":"Daniel Blankenberg","orcid":"https://orcid.org/0000-0002-6833-9049"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel J Blankenberg","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, Center of Computational Biology and Genomics, The Huck Institute for Genomics, Proteomics and Bioinformatics, The Pennsylvania State University, University Park, PA, 16802, USA","Department of Biochemistry and Molecular Biology, Center of Computational Biology and Genomics, The Huck Institute for Genomics, Proteomics and Bioinformatics, The Pennsylvania State University, , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, Center of Computational Biology and Genomics, The Huck Institute for Genomics, Proteomics and Bioinformatics, The Pennsylvania State University, University Park, PA, 16802, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, Center of Computational Biology and Genomics, The Huck Institute for Genomics, Proteomics and Bioinformatics, The Pennsylvania State University, , USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043659174","display_name":"Naomi Altman","orcid":"https://orcid.org/0000-0002-3970-2152"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naomi Altman","raw_affiliation_strings":["Department of Statistics, The Pennsylvania State University, University Park, PA, 16802, USA","Department of Statistics, The Pennsylvania State University, , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, The Pennsylvania State University, University Park, PA, 16802, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Statistics, The Pennsylvania State University, , USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057325979","display_name":"Arthur M. Lesk","orcid":"https://orcid.org/0000-0002-2596-0601"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arthur M Lesk","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, Center of Computational Biology and Genomics, The Huck Institute for Genomics, Proteomics and Bioinformatics, The Pennsylvania State University, University Park, PA, 16802, USA","Department of Biochemistry and Molecular Biology, Center of Computational Biology and Genomics, The Huck Institute for Genomics, Proteomics and Bioinformatics, The Pennsylvania State University, , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, Center of Computational Biology and Genomics, The Huck Institute for Genomics, Proteomics and Bioinformatics, The Pennsylvania State University, University Park, PA, 16802, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, Center of Computational Biology and Genomics, The Huck Institute for Genomics, Proteomics and Bioinformatics, The Pennsylvania State University, , USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051188171"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":1.888,"has_fulltext":true,"cited_by_count":116,"citation_normalized_percentile":{"value":0.84931203,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"8","issue":"1","first_page":"294","last_page":"294"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.7542999982833862,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.7542999982833862,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.1298999935388565,"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":0.04820000007748604,"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/biology","display_name":"Biology","score":0.561124861240387},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.526648759841919},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.49682310223579407},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46128907799720764},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.46051326394081116},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.45975232124328613},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.4489816129207611},{"id":"https://openalex.org/keywords/homology","display_name":"Homology (biology)","score":0.4381648302078247},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.4354897737503052},{"id":"https://openalex.org/keywords/protein-superfamily","display_name":"Protein superfamily","score":0.4313696622848511},{"id":"https://openalex.org/keywords/sequence-analysis","display_name":"Sequence analysis","score":0.4136032164096832},{"id":"https://openalex.org/keywords/closeness","display_name":"Closeness","score":0.41131407022476196},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4105912446975708},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.3821770250797272},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.2506982684135437},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1455899477005005}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.561124861240387},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.526648759841919},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.49682310223579407},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46128907799720764},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.46051326394081116},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.45975232124328613},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4489816129207611},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.4381648302078247},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4354897737503052},{"id":"https://openalex.org/C178180057","wikidata":"https://www.wikidata.org/wiki/Q7251477","display_name":"Protein superfamily","level":3,"score":0.4313696622848511},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.4136032164096832},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.41131407022476196},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4105912446975708},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.3821770250797272},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.2506982684135437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1455899477005005},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000502","qualifier_name":"physiology","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":"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":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":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":4,"locations":[{"id":"doi:10.1186/1471-2105-8-294","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-8-294","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-8-294","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:17686158","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17686158","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":"Comparative Study"},{"id":"pmh:oai:pubmedcentral.nih.gov:1976327","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1976327","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"},{"id":"pmh:oai:doaj.org/article:381c5e6e0adb4ecc979ef59b86c6c05e","is_oa":false,"landing_page_url":"https://doaj.org/article/381c5e6e0adb4ecc979ef59b86c6c05e","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 8, Iss 1, p 294 (2007)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-8-294","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-8-294","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-8-294","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/W2041944280.pdf","grobid_xml":"https://content.openalex.org/works/W2041944280.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W180785841","https://openalex.org/W1512367497","https://openalex.org/W1519266993","https://openalex.org/W1593371547","https://openalex.org/W1966852334","https://openalex.org/W1970346761","https://openalex.org/W1973481154","https://openalex.org/W1998140558","https://openalex.org/W2003788979","https://openalex.org/W2032838501","https://openalex.org/W2036792999","https://openalex.org/W2038535897","https://openalex.org/W2048102092","https://openalex.org/W2051796357","https://openalex.org/W2058567762","https://openalex.org/W2068334214","https://openalex.org/W2074231493","https://openalex.org/W2076282513","https://openalex.org/W2078866107","https://openalex.org/W2098223336","https://openalex.org/W2100018338","https://openalex.org/W2100494857","https://openalex.org/W2101595316","https://openalex.org/W2103017472","https://openalex.org/W2103150692","https://openalex.org/W2112492958","https://openalex.org/W2123858481","https://openalex.org/W2124410686","https://openalex.org/W2126975650","https://openalex.org/W2129448726","https://openalex.org/W2134789671","https://openalex.org/W2141885858","https://openalex.org/W2146389940","https://openalex.org/W2155238244","https://openalex.org/W2158714788","https://openalex.org/W2161529001","https://openalex.org/W2163105490","https://openalex.org/W2164154943","https://openalex.org/W2164565068","https://openalex.org/W2166745327","https://openalex.org/W2180356199","https://openalex.org/W2339953814","https://openalex.org/W2400915255","https://openalex.org/W4210400672","https://openalex.org/W4251257036"],"related_works":["https://openalex.org/W2159663778","https://openalex.org/W2936543792","https://openalex.org/W2789559913","https://openalex.org/W2981223346","https://openalex.org/W2056092504","https://openalex.org/W2094959732","https://openalex.org/W2318097870","https://openalex.org/W4236358448","https://openalex.org/W150090254","https://openalex.org/W2149355317"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,17],"relationship":[2,57,254],"between":[3,58,175,255],"divergence":[4,9,60,63,107,116],"of":[5,10,24,26,41,52,79,98,101,148,156,173,192,208,216,219,231,234,245,252],"amino-acid":[6],"sequence":[7,42,59,80,157],"and":[8,43,61,114,237,259],"function":[11,44,62,118,187],"among":[12,143],"homologous":[13,144],"proteins":[14,94,135,165,200],"is":[15,75,212,222],"complex.":[16],"assumption":[18],"that":[19,133,196],"homologs":[20,176],"share":[21],"function--the":[22],"basis":[23],"transfer":[25,172],"annotations":[27],"in":[28,64,89,108,117,123,188],"databases--must":[29],"therefore":[30],"be":[31],"regarded":[32],"with":[33,166,183],"caution.":[34],"Here,":[35],"we":[36],"present":[37],"a":[38,76,154,184,240,256],"quantitative":[39],"study":[40],"divergence,":[45],"based":[46,248],"on":[47,249],"the":[48,56,69,96,106,115,124,131,146,206,217,232,243,250,253],"Gene":[49,125],"Ontology":[50,126],"classification":[51],"function.":[53],"We":[54,104],"determined":[55,110,119],"6828":[65],"protein":[66,235,258],"families":[67,73],"from":[68,82,111],"PFAM":[70],"database.":[71],"Within":[72],"there":[74],"broad":[77],"range":[78],"similarity":[81,158],"very":[83,92,198],"closely":[84],"related":[85],"proteins--for":[86],"instance,":[87],"orthologs":[88],"different":[90],"mammals--to":[91],"distantly-related":[93],"at":[95,159],"limit":[97],"reliable":[99],"recognition":[100],"homology.":[102],"RESULTS:":[103],"correlated":[105],"sequences":[109],"pairwise":[112],"alignments,":[113],"by":[120],"path":[121],"lengths":[122],"graph,":[127],"taking":[128],"into":[129],"account":[130],"fact":[132],"many":[134],"have":[136],"multiple":[137],"functions.":[138],"Our":[139,226],"results":[140,227],"show":[141],"that,":[142],"proteins,":[145],"proportion":[147],"divergent":[149],"functions":[150],"decreases":[151],"dramatically":[152],"above":[153],"threshold":[155],"about":[160],"50%":[161,169],"residue":[162,170],"identity.":[163],"For":[164],"more":[167],"than":[168,190],"identity,":[171],"annotation":[174,211,246],"will":[177],"lead":[178],"to":[179,242],"an":[180],"erroneous":[181],"attribution":[182],"totally":[185],"dissimilar":[186],"fewer":[189],"6%":[191],"cases.":[193],"This":[194],"means":[195],"for":[197],"similar":[199],"(about":[201],"50":[202],"%":[203],"identical":[204],"residues)":[205],"chance":[207],"completely":[209],"incorrect":[210],"low;":[213],"however,":[214],"because":[215],"phenomenon":[218],"recruitment,":[220],"it":[221],"still":[223],"non-zero.":[224],"CONCLUSION:":[225],"describe":[228],"general":[229],"features":[230],"evolution":[233],"function,":[236],"serve":[238],"as":[239],"guide":[241],"reliability":[244],"transfer,":[247],"closeness":[251],"new":[257],"its":[260],"nearest":[261],"annotated":[262],"relative.":[263]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":6}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}