{"id":"https://openalex.org/W2041117131","doi":"https://doi.org/10.1186/1471-2105-13-141","title":"The M5nr: a novel non-redundant database containing protein sequences and annotations from multiple sources and associated tools","display_name":"The M5nr: a novel non-redundant database containing protein sequences and annotations from multiple sources and associated tools","publication_year":2012,"publication_date":"2012-06-21","ids":{"openalex":"https://openalex.org/W2041117131","doi":"https://doi.org/10.1186/1471-2105-13-141","mag":"2041117131","pmid":"https://pubmed.ncbi.nlm.nih.gov/22720753"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-13-141","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-141","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-141","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/10.1186/1471-2105-13-141","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027887614","display_name":"Andreas Wilke","orcid":"https://orcid.org/0000-0002-7699-2267"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Wilke","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, IL 60439, USA","Computation Institute, University of Chicago, Chicago, USA","Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, IL 60439, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Computation Institute, University of Chicago, Chicago, USA","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041168268","display_name":"Travis Harrison","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Travis Harrison","raw_affiliation_strings":["Computation Institute, University of Chicago, 5735 South Ellis Avenue, Chicago, IL, 60637, USA","Mathematics and Computer Science Division, Argonne National Laboratory, 9700 S. Cass Ave., Argonne, IL, 60439, USA","Computation Institute, University of Chicago, Chicago, USA","Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computation Institute, University of Chicago, 5735 South Ellis Avenue, Chicago, IL, 60637, USA","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, 9700 S. Cass Ave., Argonne, IL, 60439, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Computation Institute, University of Chicago, Chicago, USA","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050332036","display_name":"Jared Wilkening","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I4210091204","display_name":"Joint Center for Structural Genomics","ror":"https://ror.org/00exr1241","country_code":"US","type":"other","lineage":["https://openalex.org/I4210091204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jared Wilkening","raw_affiliation_strings":["Institute for Genomics and Systems Biology, 900 East 57th Street, Chicago, IL, 60637, USA","Mathematics and Computer Science Division, Argonne National Laboratory, 9700 S. Cass Ave., Argonne, IL, 60439, USA","Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Genomics and Systems Biology, 900 East 57th Street, Chicago, IL, 60637, USA","institution_ids":["https://openalex.org/I4210091204"]},{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, 9700 S. Cass Ave., Argonne, IL, 60439, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068248399","display_name":"Dawn Field","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092773","display_name":"UK Centre for Ecology & Hydrology","ror":"https://ror.org/00pggkr55","country_code":"GB","type":"other","lineage":["https://openalex.org/I4210092773"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dawn Field","raw_affiliation_strings":["Centre for Ecology & Hydrology, Maclean Building, Crowmarsh Gifford, Wallingford, Oxfordshire, United Kingdom","Centre for Ecology & Hydrology, Oxfordshire, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Ecology & Hydrology, Maclean Building, Crowmarsh Gifford, Wallingford, Oxfordshire, United Kingdom","institution_ids":["https://openalex.org/I4210092773"]},{"raw_affiliation_string":"Centre for Ecology & Hydrology, Oxfordshire, United Kingdom","institution_ids":["https://openalex.org/I4210092773"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111479062","display_name":"Elizabeth M. Glass","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth M Glass","raw_affiliation_strings":["Computation Institute, University of Chicago, 5735 South Ellis Avenue, Chicago, IL, 60637, USA","Mathematics and Computer Science Division, Argonne National Laboratory, 9700 S. Cass Ave., Argonne, IL, 60439, USA","Computation Institute, University of Chicago, Chicago, USA","Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computation Institute, University of Chicago, 5735 South Ellis Avenue, Chicago, IL, 60637, USA","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, 9700 S. Cass Ave., Argonne, IL, 60439, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Computation Institute, University of Chicago, Chicago, USA","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023696415","display_name":"Nikos C. Kyrpides","orcid":"https://orcid.org/0000-0002-6131-0462"},"institutions":[{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikos Kyrpides","raw_affiliation_strings":["Department of Energy Joint Genome Institute, Walnut Creek, CA, USA","Department of Energy , Joint Genome Institute, Walnut Creek, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Energy Joint Genome Institute, Walnut Creek, CA, USA","institution_ids":["https://openalex.org/I196679689"]},{"raw_affiliation_string":"Department of Energy , Joint Genome Institute, Walnut Creek, USA","institution_ids":["https://openalex.org/I196679689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002539266","display_name":"Konstantinos Mavrommatis","orcid":"https://orcid.org/0000-0003-4549-385X"},"institutions":[{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Konstantinos Mavrommatis","raw_affiliation_strings":["Department of Energy Joint Genome Institute, Walnut Creek, CA, USA","Department of Energy , Joint Genome Institute, Walnut Creek, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Energy Joint Genome Institute, Walnut Creek, CA, USA","institution_ids":["https://openalex.org/I196679689"]},{"raw_affiliation_string":"Department of Energy , Joint Genome Institute, Walnut Creek, USA","institution_ids":["https://openalex.org/I196679689"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086419862","display_name":"Folker Meyer","orcid":"https://orcid.org/0000-0003-1112-2284"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]},{"id":"https://openalex.org/I4210091204","display_name":"Joint Center for Structural Genomics","ror":"https://ror.org/00exr1241","country_code":"US","type":"other","lineage":["https://openalex.org/I4210091204"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Folker Meyer","raw_affiliation_strings":["Computation Institute, University of Chicago, 5735 South Ellis Avenue, Chicago, IL, 60637, USA","Institute for Genomics and Systems Biology, 900 East 57th Street, Chicago, IL, 60637, USA","Mathematics and Computer Science Division, Argonne National Laboratory, 9700 S. Cass Ave., Argonne, IL, 60439, USA","Computation Institute, University of Chicago, Chicago, USA","Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computation Institute, University of Chicago, 5735 South Ellis Avenue, Chicago, IL, 60637, USA","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"Institute for Genomics and Systems Biology, 900 East 57th Street, Chicago, IL, 60637, USA","institution_ids":["https://openalex.org/I4210091204"]},{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, 9700 S. Cass Ave., Argonne, IL, 60439, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Computation Institute, University of Chicago, Chicago, USA","institution_ids":["https://openalex.org/I40347166"]},{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5086419862"],"corresponding_institution_ids":["https://openalex.org/I1282105669","https://openalex.org/I40347166","https://openalex.org/I4210091204"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":5.8939,"has_fulltext":true,"cited_by_count":332,"citation_normalized_percentile":{"value":0.97313851,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"13","issue":"1","first_page":"141","last_page":"141"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.3765999972820282,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.3765999972820282,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.20260000228881836,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.09700000286102295,"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/computer-science","display_name":"Computer science","score":0.7387467622756958},{"id":"https://openalex.org/keywords/genbank","display_name":"GenBank","score":0.7300843000411987},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6603730320930481},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5631412267684937},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.526164710521698},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5003688335418701},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46904999017715454},{"id":"https://openalex.org/keywords/kegg","display_name":"KEGG","score":0.46654510498046875},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.39634445309638977},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.15961149334907532},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13103851675987244},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.0991719663143158}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387467622756958},{"id":"https://openalex.org/C79029880","wikidata":"https://www.wikidata.org/wiki/Q901755","display_name":"GenBank","level":3,"score":0.7300843000411987},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6603730320930481},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5631412267684937},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.526164710521698},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5003688335418701},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46904999017715454},{"id":"https://openalex.org/C152724338","wikidata":"https://www.wikidata.org/wiki/Q909442","display_name":"KEGG","level":5,"score":0.46654510498046875},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.39634445309638977},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15961149334907532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13103851675987244},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0991719663143158},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"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/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[{"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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","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":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":7,"locations":[{"id":"doi:10.1186/1471-2105-13-141","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-141","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-141","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:22720753","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22720753","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:ark:/13030/qt1h51x8jw","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:doaj.org/article:d3751400d4a545e08bc25c41b5a867d7","is_oa":true,"landing_page_url":"https://doaj.org/article/d3751400d4a545e08bc25c41b5a867d7","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 13, Iss 1, p 141 (2012)","raw_type":"article"},{"id":"pmh:oai:escholarship.org/ark:/13030/qt1h51x8jw","is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/1h51x8jw","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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 13, iss 1","raw_type":"article"},{"id":"pmh:oai:europepmc.org:2416597","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3410781","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":null,"raw_type":"Text"},{"id":"pmh:oai:nora.nerc.ac.uk:21175","is_oa":false,"landing_page_url":"http://nora.nerc.ac.uk/id/eprint/21175/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400758","display_name":"NERC Open Research Archive (Natural Environment Research Council)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I141816643","host_organization_name":"Natural Environment Research Council","host_organization_lineage":["https://openalex.org/I141816643"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Publication - Article"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-13-141","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-141","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-141","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5556430061","display_name":null,"funder_award_id":"CEH010021","funder_id":"https://openalex.org/F4320334631","funder_display_name":"Natural Environment Research Council"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320334631","display_name":"Natural Environment Research Council","ror":"https://ror.org/02b5d8509"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2041117131.pdf","grobid_xml":"https://content.openalex.org/works/W2041117131.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1527927437","https://openalex.org/W1578104218","https://openalex.org/W1975970608","https://openalex.org/W1980160222","https://openalex.org/W1989348205","https://openalex.org/W2022667872","https://openalex.org/W2030692069","https://openalex.org/W2107751776","https://openalex.org/W2114034054","https://openalex.org/W2117172325","https://openalex.org/W2123060905","https://openalex.org/W2127660113","https://openalex.org/W2135277010","https://openalex.org/W2136145671","https://openalex.org/W2144896636","https://openalex.org/W2155545841","https://openalex.org/W2155606054","https://openalex.org/W2158714788","https://openalex.org/W2169267759","https://openalex.org/W3145042860"],"related_works":["https://openalex.org/W1964572291","https://openalex.org/W4387948744","https://openalex.org/W1987520879","https://openalex.org/W184793361","https://openalex.org/W2352732738","https://openalex.org/W2123060905","https://openalex.org/W2559588208","https://openalex.org/W4318778067","https://openalex.org/W1923384484","https://openalex.org/W2361861616"],"abstract_inverted_index":{"BACKGROUND:":[0],"Computing":[1],"of":[2,34,42,68,99],"sequence":[3,117],"similarity":[4,15,43,78],"results":[5,17,44,109],"is":[6,45],"becoming":[7],"a":[8,46,52,57,65,104],"limiting":[9],"factor":[10],"in":[11,19],"metagenome":[12],"analysis.":[13],"Sequence":[14],"search":[16],"encoded":[18],"an":[20],"open,":[21],"exchangeable":[22],"format":[23],"have":[24],"the":[25,29,97],"potential":[26],"to":[27,110],"limit":[28],"needs":[30],"for":[31,40,54,63,76,115],"computational":[32,108],"reanalysis":[33],"these":[35],"data":[36,91,118],"sets.":[37,119],"A":[38],"prerequisite":[39],"sharing":[41],"common":[47],"reference.":[48],"DESCRIPTION:":[49],"We":[50],"introduce":[51],"mechanism":[53],"automatically":[55],"maintaining":[56],"comprehensive,":[58],"non-redundant":[59],"protein":[60],"database":[61],"and":[62,92],"creating":[64],"quarterly":[66],"release":[67],"this":[69],"resource.":[70],"In":[71],"addition,":[72],"we":[73,94],"present":[74,95],"tools":[75,93],"translating":[77],"searches":[79],"into":[80],"many":[81],"annotation":[82],"namespaces,":[83],"e.g.":[84],"KEGG":[85],"or":[86],"NCBI's":[87],"GenBank.":[88],"CONCLUSIONS:":[89],"The":[90],"allow":[96],"creation":[98],"multiple":[100],"result":[101],"sets":[102],"using":[103],"single":[105],"computation,":[106],"permitting":[107],"be":[111],"shared":[112],"between":[113],"groups":[114],"large":[116]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":31},{"year":2021,"cited_by_count":52},{"year":2020,"cited_by_count":38},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":27},{"year":2017,"cited_by_count":26},{"year":2016,"cited_by_count":39},{"year":2015,"cited_by_count":24},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}
