{"id":"https://openalex.org/W2562773385","doi":"https://doi.org/10.1093/database/baw139","title":"Minimizing proteome redundancy in the UniProt Knowledgebase","display_name":"Minimizing proteome redundancy in the UniProt Knowledgebase","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2562773385","doi":"https://doi.org/10.1093/database/baw139","mag":"2562773385","pmid":"https://pubmed.ncbi.nlm.nih.gov/28025334"},"language":"en","primary_location":{"id":"doi:10.1093/database/baw139","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baw139","pdf_url":null,"source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/database/baw139","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026008686","display_name":"Borisas Bursteinas","orcid":"https://orcid.org/0000-0002-0701-5518"},"institutions":[{"id":"https://openalex.org/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"funder","lineage":["https://openalex.org/I87048295"]},{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Borisas Bursteinas","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK","European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and"],"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]},{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043724107","display_name":"Ramona Britto","orcid":"https://orcid.org/0000-0003-1011-5410"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"funder","lineage":["https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ramona Britto","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK","European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and"],"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]},{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017249822","display_name":"Beno\u00eet Bely","orcid":"https://orcid.org/0000-0002-0029-9693"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"funder","lineage":["https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Benoit Bely","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK","European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and"],"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]},{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039823870","display_name":"Andrea H Auchincloss","orcid":"https://orcid.org/0000-0002-5297-5390"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"funder","lineage":["https://openalex.org/I12708293"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andrea Auchincloss","raw_affiliation_strings":["SIB Swiss Institute of Bioinformatics, Centre Medical Universitaire, 1 rue Michel Servet, Geneva 4 1211, Switzerland"],"affiliations":[{"raw_affiliation_string":"SIB Swiss Institute of Bioinformatics, Centre Medical Universitaire, 1 rue Michel Servet, Geneva 4 1211, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044580086","display_name":"Catherine Rivoire","orcid":"https://orcid.org/0000-0002-5979-8382"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"funder","lineage":["https://openalex.org/I12708293"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Catherine Rivoire","raw_affiliation_strings":["SIB Swiss Institute of Bioinformatics, Centre Medical Universitaire, 1 rue Michel Servet, Geneva 4 1211, Switzerland"],"affiliations":[{"raw_affiliation_string":"SIB Swiss Institute of Bioinformatics, Centre Medical Universitaire, 1 rue Michel Servet, Geneva 4 1211, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055073392","display_name":"Nicole Redaschi","orcid":"https://orcid.org/0000-0001-8890-2268"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"funder","lineage":["https://openalex.org/I12708293"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Nicole Redaschi","raw_affiliation_strings":["SIB Swiss Institute of Bioinformatics, Centre Medical Universitaire, 1 rue Michel Servet, Geneva 4 1211, Switzerland"],"affiliations":[{"raw_affiliation_string":"SIB Swiss Institute of Bioinformatics, Centre Medical Universitaire, 1 rue Michel Servet, Geneva 4 1211, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066278201","display_name":"Claire O\u2019Donovan","orcid":"https://orcid.org/0000-0001-8051-7429"},"institutions":[{"id":"https://openalex.org/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"funder","lineage":["https://openalex.org/I87048295"]},{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Claire O'Donovan","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK","European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and"],"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]},{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071535801","display_name":"Mar\u00eda Martin","orcid":"https://orcid.org/0000-0001-5454-2815"},"institutions":[{"id":"https://openalex.org/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"funder","lineage":["https://openalex.org/I87048295"]},{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Maria Jesus Martin","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK martin@ebi.ac.uk","European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and"],"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK martin@ebi.ac.uk","institution_ids":[]},{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK and","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5071535801"],"corresponding_institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1415,"currency":"GBP","value_usd":1735},"fwci":2.0886,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.87585828,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2016","issue":null,"first_page":"baw139","last_page":"baw139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9973000288009644,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9973000288009644,"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":0.9973000288009644,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/uniprot","display_name":"UniProt","score":0.9123369455337524},{"id":"https://openalex.org/keywords/proteome","display_name":"Proteome","score":0.7291468381881714},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5986586809158325},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5824829339981079},{"id":"https://openalex.org/keywords/human-proteome-project","display_name":"Human proteome project","score":0.4963544011116028},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4271897077560425},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4178629219532013},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4144071936607361},{"id":"https://openalex.org/keywords/proteomics","display_name":"Proteomics","score":0.38970938324928284},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2251925766468048},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.20507100224494934},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.08116191625595093}],"concepts":[{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.9123369455337524},{"id":"https://openalex.org/C104397665","wikidata":"https://www.wikidata.org/wiki/Q860947","display_name":"Proteome","level":2,"score":0.7291468381881714},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5986586809158325},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5824829339981079},{"id":"https://openalex.org/C94795543","wikidata":"https://www.wikidata.org/wiki/Q3813754","display_name":"Human proteome project","level":4,"score":0.4963544011116028},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4271897077560425},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4178629219532013},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4144071936607361},{"id":"https://openalex.org/C46111723","wikidata":"https://www.wikidata.org/wiki/Q471857","display_name":"Proteomics","level":3,"score":0.38970938324928284},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2251925766468048},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.20507100224494934},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08116191625595093},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D001426","descriptor_name":"Bacterial Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","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":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D020543","descriptor_name":"Proteome","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/database/baw139","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baw139","pdf_url":null,"source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},{"id":"pmid:28025334","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28025334","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":"Database : the journal of biological databases and curation","raw_type":null},{"id":"pmh:oai:open-archive.highwire.org:databa:2016/0/baw139","is_oa":false,"landing_page_url":"http://database.oxfordjournals.org/cgi/content/short/2016/0/baw139","pdf_url":null,"source":{"id":"https://openalex.org/S4406923041","display_name":"HighWire Press Open Archive","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":"","raw_type":"TEXT"},{"id":"pmh:oai:pubmedcentral.nih.gov:5199198","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5199198","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Database (Oxford)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/database/baw139","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/baw139","pdf_url":null,"source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1311907592","display_name":null,"funder_award_id":"U01GM120953","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G1331145985","display_name":null,"funder_award_id":"R01GM080646","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3401731667","display_name":null,"funder_award_id":"U41HG002273","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3611247453","display_name":null,"funder_award_id":"R01GM","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4971142927","display_name":null,"funder_award_id":"U41HG007822","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6414905909","display_name":null,"funder_award_id":"HG0022","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7089253139","display_name":null,"funder_award_id":"GM103446","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G7195913738","display_name":null,"funder_award_id":"HG007822","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G785190151","display_name":null,"funder_award_id":"P20GM103446","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G839285823","display_name":null,"funder_award_id":"HG002273","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G8742587250","display_name":null,"funder_award_id":"GM120953","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320314023","display_name":"European Molecular Biology Laboratory","ror":"https://ror.org/050589e39"},{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320335238","display_name":"Staatssekretariat f\u00fcr Bildung, Forschung und Innovation","ror":"https://ror.org/01kw63t33"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W991210025","https://openalex.org/W1856729396","https://openalex.org/W1976369037","https://openalex.org/W1996423252","https://openalex.org/W2011039300","https://openalex.org/W2051872583","https://openalex.org/W2060196294","https://openalex.org/W2062296203","https://openalex.org/W2064452752","https://openalex.org/W2064795263","https://openalex.org/W2093794723","https://openalex.org/W2095222153","https://openalex.org/W2102461176","https://openalex.org/W2124351063","https://openalex.org/W2135133508","https://openalex.org/W2137450588","https://openalex.org/W2148109411","https://openalex.org/W2155358039","https://openalex.org/W2156125289","https://openalex.org/W2158149672","https://openalex.org/W2161222725","https://openalex.org/W2168267323","https://openalex.org/W2739999456","https://openalex.org/W4233928114","https://openalex.org/W4285719527","https://openalex.org/W6638958822"],"related_works":["https://openalex.org/W2288906059","https://openalex.org/W3092794487","https://openalex.org/W2093519416","https://openalex.org/W2094752534","https://openalex.org/W1982829397","https://openalex.org/W2885268310","https://openalex.org/W2106414650","https://openalex.org/W2347437365","https://openalex.org/W2025055488","https://openalex.org/W2296132555"],"abstract_inverted_index":{"Advances":[0],"in":[1,10,40,46,51,68,101,194,197,204,220],"high-throughput":[2],"sequencing":[3,21,111],"have":[4,136],"led":[5],"to":[6,15,119,124,129,140,171,214],"an":[7,66],"unprecedented":[8],"growth":[9,227],"genome":[11],"sequences":[12,161],"being":[13],"submitted":[14],"biological":[16],"databases.":[17],"In":[18],"particular,":[19],"the":[20,52,79,84,107],"of":[22,25,44,90,94,104,110,158,160,164,179,186,200,228],"large":[23,80],"numbers":[24],"nearly":[26],"identical":[27],"bacterial":[28],"genomes":[29],"during":[30],"infection":[31],"outbreaks":[32],"and":[33,49,71,142,166,224],"for":[34,87,98,162,192],"other":[35],"large-scale":[36],"studies":[37],"has":[38],"resulted":[39],"a":[41,138,177,183,198,221],"high":[42],"level":[43],"redundancy":[45,76,121],"nucleotide":[47],"databases":[48],"consequently":[50],"UniProt":[53],"Knowledgebase":[54],"(UniProtKB).":[55],"Redundancy":[56],"negatively":[57],"impacts":[58],"on":[59],"database":[60],"searches":[61],"by":[62,132,154],"causing":[63],"slower":[64],"searches,":[65],"increase":[67],"statistical":[69],"bias":[70],"cumbersome":[72],"result":[73],"analysis.":[74],"The":[75,149],"combined":[77],"with":[78,182],"data":[81,130],"volume":[82],"increases":[83],"computational":[85],"costs":[86],"most":[88],"reuses":[89],"UniProtKB":[91],"data.":[92,105],"All":[93],"this":[95,102,210],"poses":[96],"challenges":[97],"effective":[99],"discovery":[100],"wealth":[103],"With":[106,206],"continuing":[108],"development":[109],"technologies,":[112],"it":[113],"is":[114,122,212],"clear":[115],"that":[116,175],"finding":[117],"ways":[118],"minimize":[120],"crucial":[123],"maintaining":[125],"UniProt's":[126],"essential":[127],"contribution":[128],"interpretation":[131],"our":[133],"users.":[134],"We":[135],"developed":[137],"methodology":[139],"identify":[141],"remove":[143],"highly":[144],"redundant":[145,152],"proteomes":[146,153,165,181],"from":[147],"UniProtKB.":[148,205],"procedure":[150,211],"identifies":[151],"performing":[155],"pairwise":[156],"alignments":[157],"sets":[159,174],"pairs":[163],"subsequently,":[167],"applies":[168],"graph":[169],"theory":[170],"find":[172],"dominating":[173],"provide":[176],"set":[178],"non-redundant":[180],"minimal":[184],"loss":[185],"information.":[187],"This":[188],"method":[189],"was":[190],"implemented":[191],"bacteria":[193],"mid-2015,":[195],"resulting":[196,219],"removal":[199],"50":[201],"million":[202],"proteins":[203],"every":[207],"new":[208,216],"release,":[209],"used":[213],"filter":[215],"incoming":[217],"proteomes,":[218],"more":[222],"scalable":[223],"scientifically":[225],"valuable":[226],"UniProtKB.Database":[229],"URL:":[230],"http://www.uniprot.org/proteomes/.":[231]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}