{"id":"https://openalex.org/W2096476896","doi":"https://doi.org/10.1093/database/bas003","title":"AntiFam: a tool to help identify spurious ORFs in protein annotation","display_name":"AntiFam: a tool to help identify spurious ORFs in protein annotation","publication_year":2012,"publication_date":"2012-03-20","ids":{"openalex":"https://openalex.org/W2096476896","doi":"https://doi.org/10.1093/database/bas003","mag":"2096476896","pmid":"https://pubmed.ncbi.nlm.nih.gov/22434837"},"language":"en","primary_location":{"id":"doi:10.1093/database/bas003","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bas003","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bas003/1189580/bas003.pdf","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://academic.oup.com/database/article-pdf/doi/10.1093/database/bas003/1189580/bas003.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040135675","display_name":"Ruth Y. Eberhardt","orcid":"https://orcid.org/0000-0001-6152-1369"},"institutions":[{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]},{"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/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"R. Y. Eberhardt","raw_affiliation_strings":["Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SA. UK. re3@sanger.ac.uk","Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SA. UK, 2Department of Bioinformatics, J. Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD 20850, USA and 3European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SD, UK"],"affiliations":[{"raw_affiliation_string":"Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SA. UK. re3@sanger.ac.uk","institution_ids":["https://openalex.org/I2802476451"]},{"raw_affiliation_string":"Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SA. UK, 2Department of Bioinformatics, J. Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD 20850, USA and 3European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SD, UK","institution_ids":["https://openalex.org/I2802476451","https://openalex.org/I1303153112","https://openalex.org/I1301553790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027242690","display_name":"Daniel H. Haft","orcid":"https://orcid.org/0000-0001-8101-4938"},"institutions":[{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]},{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]},{"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","US"],"is_corresponding":false,"raw_author_name":"D. H. Haft","raw_affiliation_strings":["Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SA. UK, 2Department of Bioinformatics, J. Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD 20850, USA and 3European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SD, UK"],"affiliations":[{"raw_affiliation_string":"Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SA. UK, 2Department of Bioinformatics, J. Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD 20850, USA and 3European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SD, UK","institution_ids":["https://openalex.org/I2802476451","https://openalex.org/I1303153112","https://openalex.org/I1301553790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056369160","display_name":"Marco Punta","orcid":"https://orcid.org/0000-0002-0050-0676"},"institutions":[{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]},{"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/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"M. Punta","raw_affiliation_strings":["Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SA. UK, 2Department of Bioinformatics, J. Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD 20850, USA and 3European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SD, UK"],"affiliations":[{"raw_affiliation_string":"Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SA. UK, 2Department of Bioinformatics, J. Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD 20850, USA and 3European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SD, UK","institution_ids":["https://openalex.org/I2802476451","https://openalex.org/I1303153112","https://openalex.org/I1301553790"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071535801","display_name":"Mar\u00eda Martin","orcid":"https://orcid.org/0000-0001-5454-2815"},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]},{"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/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"M. Martin","raw_affiliation_strings":["Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SA. UK, 2Department of Bioinformatics, J. Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD 20850, USA and 3European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SD, UK"],"affiliations":[{"raw_affiliation_string":"Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SA. UK, 2Department of Bioinformatics, J. Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD 20850, USA and 3European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SD, UK","institution_ids":["https://openalex.org/I2802476451","https://openalex.org/I1303153112","https://openalex.org/I1301553790"]}]},{"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/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]},{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]},{"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","US"],"is_corresponding":false,"raw_author_name":"C. O'Donovan","raw_affiliation_strings":["Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SA. UK, 2Department of Bioinformatics, J. Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD 20850, USA and 3European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SD, UK"],"affiliations":[{"raw_affiliation_string":"Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SA. UK, 2Department of Bioinformatics, J. Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD 20850, USA and 3European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SD, UK","institution_ids":["https://openalex.org/I2802476451","https://openalex.org/I1303153112","https://openalex.org/I1301553790"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059430118","display_name":"Alex Bateman","orcid":null},"institutions":[{"id":"https://openalex.org/I1301553790","display_name":"J. Craig Venter Institute","ror":"https://ror.org/049r1ts75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1301553790"]},{"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/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"A. Bateman","raw_affiliation_strings":["Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SA. UK, 2Department of Bioinformatics, J. Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD 20850, USA and 3European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SD, UK"],"affiliations":[{"raw_affiliation_string":"Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SA. UK, 2Department of Bioinformatics, J. Craig Venter Institute, 9704 Medical Center Drive, Rockville, MD 20850, USA and 3European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, CB10 1SD, UK","institution_ids":["https://openalex.org/I2802476451","https://openalex.org/I1303153112","https://openalex.org/I1301553790"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5040135675"],"corresponding_institution_ids":["https://openalex.org/I1301553790","https://openalex.org/I1303153112","https://openalex.org/I2802476451"],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1415,"currency":"GBP","value_usd":1735},"fwci":0.9379,"has_fulltext":true,"cited_by_count":67,"citation_normalized_percentile":{"value":0.74074392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"2012","issue":"0","first_page":"bas003","last_page":"bas003"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998000264167786,"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":0.9998000264167786,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9994000196456909,"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":0.9965999722480774,"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/orfs","display_name":"ORFS","score":0.9234929084777832},{"id":"https://openalex.org/keywords/uniprot","display_name":"UniProt","score":0.8192965984344482},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.7922534942626953},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6413032412528992},{"id":"https://openalex.org/keywords/open-reading-frame","display_name":"Open reading frame","score":0.6253395676612854},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5433095693588257},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.5125327110290527},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.48297157883644104},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.4664418697357178},{"id":"https://openalex.org/keywords/proteogenomics","display_name":"Proteogenomics","score":0.4300176203250885},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.38719263672828674},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.36222246289253235},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.26886415481567383},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.19233840703964233}],"concepts":[{"id":"https://openalex.org/C2780530800","wikidata":"https://www.wikidata.org/wiki/Q7072921","display_name":"ORFS","level":5,"score":0.9234929084777832},{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.8192965984344482},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.7922534942626953},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6413032412528992},{"id":"https://openalex.org/C47289529","wikidata":"https://www.wikidata.org/wiki/Q908550","display_name":"Open reading frame","level":4,"score":0.6253395676612854},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5433095693588257},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.5125327110290527},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.48297157883644104},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.4664418697357178},{"id":"https://openalex.org/C145741570","wikidata":"https://www.wikidata.org/wiki/Q7251534","display_name":"Proteogenomics","level":5,"score":0.4300176203250885},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.38719263672828674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.36222246289253235},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.26886415481567383},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.19233840703964233},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","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":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","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":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":"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":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/database/bas003","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bas003","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bas003/1189580/bas003.pdf","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:22434837","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22434837","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:pubmedcentral.nih.gov:3308159","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3308159","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Database (Oxford)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/database/bas003","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bas003","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bas003/1189580/bas003.pdf","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.800000011920929}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311904","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2096476896.pdf","grobid_xml":"https://content.openalex.org/works/W2096476896.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1513332069","https://openalex.org/W1971147414","https://openalex.org/W1975914194","https://openalex.org/W2017335389","https://openalex.org/W2060797027","https://openalex.org/W2078361370","https://openalex.org/W2082138488","https://openalex.org/W2105199251","https://openalex.org/W2124410686","https://openalex.org/W2130253098","https://openalex.org/W2137597742","https://openalex.org/W2141885858","https://openalex.org/W4210623056","https://openalex.org/W4252830634","https://openalex.org/W4320301318"],"related_works":["https://openalex.org/W2017477982","https://openalex.org/W1978801575","https://openalex.org/W2029252138","https://openalex.org/W4306784270","https://openalex.org/W2101899141","https://openalex.org/W3031046715","https://openalex.org/W2017335389","https://openalex.org/W2358544099","https://openalex.org/W1976390578","https://openalex.org/W2072439611"],"abstract_inverted_index":{"As":[0],"the":[1,8,22,27,37,73,76,104,117,199],"deluge":[2],"of":[3,10,24,40,75,83,96,163,188,198],"genomic":[4],"DNA":[5],"sequence":[6,30,68],"grows":[7],"fraction":[9],"protein":[11,78,84],"sequences":[12],"that":[13,138,172],"have":[14,59,86,151],"been":[15,87],"manually":[16],"curated":[17],"falls.":[18],"In":[19],"turn,":[20],"as":[21,93,195],"number":[23,82],"laboratories":[25],"with":[26,114,159],"ability":[28],"to":[29,43,61,116,145],"genomes":[31],"in":[32,108,133,156,177,185],"a":[33,51,81,109,142,180,186,196],"high-throughput":[34],"manner":[35],"grows,":[36],"informatics":[38],"capability":[39],"those":[41],"labs":[42],"accurately":[44],"identify":[45,146],"and":[46,128,179,204],"annotate":[47],"all":[48],"genes":[49],"within":[50],"genome":[52],"may":[53,140],"often":[54],"be":[55],"lacking.":[56],"These":[57,124],"issues":[58],"led":[60],"fears":[62],"about":[63],"transitive":[64],"annotation":[65],"errors":[66],"making":[67],"databases":[69],"less":[70],"reliable.":[71],"During":[72],"lifetime":[74],"Pfam":[77],"families":[79,85,125,154,162,171],"database":[80],"built,":[88],"which":[89],"were":[90,126],"later":[91],"identified":[92,173],"composed":[94],"solely":[95],"spurious":[97,148,164,175,183,208],"open":[98],"reading":[99,112],"frames":[100],"(ORFs)":[101],"either":[102],"on":[103],"opposite":[105],"strand":[106],"or":[107,120],"different,":[110],"overlapping":[111],"frame":[113],"respect":[115],"true":[118],"protein-coding":[119],"non-coding":[121],"RNA":[122],"gene.":[123],"deleted":[127],"are":[129],"no":[130],"longer":[131],"available":[132],"Pfam.":[134],"However,":[135],"we":[136],"realized":[137],"these":[139,153,207],"perform":[141],"useful":[143],"function":[144],"new":[147],"ORFs.":[149,165],"We":[150],"collected":[152],"together":[155],"AntiFam":[157,194],"along":[158],"additional":[160],"custom-made":[161],"This":[166],"resource":[167],"currently":[168],"contains":[169],"23":[170],"1310":[174],"proteins":[176,184,209],"UniProtKB":[178,200],"further":[181],"4119":[182],"collection":[187],"metagenomic":[189],"sequences.":[190],"UniProt":[191],"has":[192],"adopted":[193],"part":[197],"quality":[201],"control":[202],"process":[203],"will":[205],"investigate":[206],"for":[210],"exclusion.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}