{"id":"https://openalex.org/W2103970813","doi":"https://doi.org/10.1093/bioinformatics/btn276","title":"Annotation of metagenome short reads using proxygenes","display_name":"Annotation of metagenome short reads using proxygenes","publication_year":2008,"publication_date":"2008-08-09","ids":{"openalex":"https://openalex.org/W2103970813","doi":"https://doi.org/10.1093/bioinformatics/btn276","mag":"2103970813","pmid":"https://pubmed.ncbi.nlm.nih.gov/18689842"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btn276","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn276","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/16/i7/49051134/bioinformatics_24_16_i7.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/24/16/i7/49051134/bioinformatics_24_16_i7.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081024973","display_name":"Daniel Dalevi","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"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":"Daniel Dalevi","raw_affiliation_strings":["1 Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, 2Genome Biology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek and 3Microbial Ecology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek, CA 94598, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, 2Genome Biology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek and 3Microbial Ecology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek, CA 94598, USA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I196679689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085966412","display_name":"Natalia Ivanova","orcid":"https://orcid.org/0000-0002-5802-9485"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"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":"Natalia N. Ivanova","raw_affiliation_strings":["1 Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, 2Genome Biology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek and 3Microbial Ecology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek, CA 94598, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, 2Genome Biology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek and 3Microbial Ecology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek, CA 94598, USA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I196679689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110267591","display_name":"Konstantinos Mavromatis","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"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 Mavromatis","raw_affiliation_strings":["1 Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, 2Genome Biology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek and 3Microbial Ecology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek, CA 94598, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, 2Genome Biology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek and 3Microbial Ecology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek, CA 94598, USA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I196679689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037297745","display_name":"Sean Hooper","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"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":"Sean D. Hooper","raw_affiliation_strings":["1 Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, 2Genome Biology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek and 3Microbial Ecology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek, CA 94598, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, 2Genome Biology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek and 3Microbial Ecology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek, CA 94598, USA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I196679689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017958076","display_name":"Ernest Szeto","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"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":"Ernest Szeto","raw_affiliation_strings":["1 Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, 2Genome Biology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek and 3Microbial Ecology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek, CA 94598, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, 2Genome Biology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek and 3Microbial Ecology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek, CA 94598, USA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I196679689"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075159561","display_name":"Philip Hugenholtz","orcid":"https://orcid.org/0000-0001-5386-7925"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"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":"Philip Hugenholtz","raw_affiliation_strings":["1 Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, 2Genome Biology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek and 3Microbial Ecology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek, CA 94598, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, 2Genome Biology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek and 3Microbial Ecology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek, CA 94598, USA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I196679689"]}]},{"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/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"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 C. Kyrpides","raw_affiliation_strings":["1 Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, 2Genome Biology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek and 3Microbial Ecology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek, CA 94598, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, 2Genome Biology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek and 3Microbial Ecology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek, CA 94598, USA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I196679689"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079693902","display_name":"Victor Markowitz","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"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":"Victor M. Markowitz","raw_affiliation_strings":["1 Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, 2Genome Biology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek and 3Microbial Ecology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek, CA 94598, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1 Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, 2Genome Biology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek and 3Microbial Ecology Program, DOE Joint Genome Institute, 2800 Mitchell Dr, Walnut Creek, CA 94598, USA","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I196679689"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":2.7291,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.90581221,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"24","issue":"16","first_page":"i7","last_page":"i13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.660099983215332,"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":0.660099983215332,"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":0.08129999786615372,"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"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.023800000548362732,"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/metagenomics","display_name":"Metagenomics","score":0.9290286302566528},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6747325658798218},{"id":"https://openalex.org/keywords/pyrosequencing","display_name":"Pyrosequencing","score":0.6713870167732239},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6163052320480347},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4907263517379761},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.47631487250328064},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.47149914503097534},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.462909996509552},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4450143575668335},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.41832906007766724},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41044285893440247},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3403412997722626},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.26418444514274597},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.2382430136203766},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2281491458415985},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.1498205065727234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1235608160495758}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.9290286302566528},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6747325658798218},{"id":"https://openalex.org/C125009961","wikidata":"https://www.wikidata.org/wiki/Q2342248","display_name":"Pyrosequencing","level":3,"score":0.6713870167732239},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6163052320480347},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4907263517379761},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.47631487250328064},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.47149914503097534},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.462909996509552},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4450143575668335},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.41832906007766724},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41044285893440247},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3403412997722626},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.26418444514274597},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.2382430136203766},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2281491458415985},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.1498205065727234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1235608160495758},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[{"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":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D002874","descriptor_name":"Chromosome Mapping","qualifier_ui":"Q000379","qualifier_name":"methods","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":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016366","descriptor_name":"Open Reading Frames","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","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}],"locations_count":5,"locations":[{"id":"doi:10.1093/bioinformatics/btn276","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn276","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/16/i7/49051134/bioinformatics_24_16_i7.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:18689842","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18689842","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:escholarship.org/ark:/13030/qt2nr7x7zm","is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/2nr7x7zm","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":"","raw_type":"article"},{"id":"pmh:oai:espace.library.uq.edu.au:UQ:262634","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402388","display_name":"Queensland's institutional digital repository (The University of Queensland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165143802","host_organization_name":"The University of Queensland","host_organization_lineage":["https://openalex.org/I165143802"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:qt2nr7x7zm","is_oa":false,"landing_page_url":"http://www.escholarship.org/uc/item/2nr7x7zm","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":"Dalevi, Daniel; Ivanova, Natalia N.; Mavromatis, Konstantinos; Hooper, Sean; Szeto, Ernest; Hugenholtz, Phillip; \u00c2\u00a0et al.(2008). Annotation of metagenome short reads using proxygenes. Lawrence Berkeley National Laboratory: Lawrence Berkeley National Laboratory. Retrieved from: http://www.escholarship.org/uc/item/2nr7x7zm","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btn276","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btn276","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/24/16/i7/49051134/bioinformatics_24_16_i7.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1900149929","https://openalex.org/W1990453950","https://openalex.org/W1995614275","https://openalex.org/W2029481180","https://openalex.org/W2103461849","https://openalex.org/W2114034054","https://openalex.org/W2126809954","https://openalex.org/W2132415967","https://openalex.org/W2141885858","https://openalex.org/W2148000475","https://openalex.org/W2152517415","https://openalex.org/W2156296225","https://openalex.org/W2167062509","https://openalex.org/W4210400672"],"related_works":["https://openalex.org/W2359295417","https://openalex.org/W2144480915","https://openalex.org/W2005015095","https://openalex.org/W2001808934","https://openalex.org/W2156417649","https://openalex.org/W2161558410","https://openalex.org/W2355827030","https://openalex.org/W638577851","https://openalex.org/W2968354375","https://openalex.org/W2158877985"],"abstract_inverted_index":{"MOTIVATION:":[0],"A":[1],"typical":[2],"metagenome":[3,130,159],"dataset":[4,160],"generated":[5],"using":[6,107,121],"a":[7,21,48,87,92,149,158,163],"454":[8],"pyrosequencing":[9,101],"platform":[10],"consists":[11],"of":[12,20,26,51,59,62,70,91,100,157,166],"short":[13,45,83],"reads":[14,72,84,102],"sampled":[15],"from":[16],"the":[17,80,98,137,144,155],"collective":[18],"genome":[19],"microbial":[22],"community.":[23],"The":[24,66],"amount":[25],"sequence":[27,126],"in":[28,57],"such":[29,52],"datasets":[30,53,131],"is":[31,77,140],"usually":[32,54,89],"insufficient":[33],"for":[34],"assembly,":[35],"and":[36,111,114,169],"traditional":[37],"gene":[38],"prediction":[39],"cannot":[40],"be":[41],"applied":[42],"to":[43,73,103],"unassembled":[44],"reads.":[46],"As":[47],"result,":[49],"analysis":[50],"involves":[55],"comparisons":[56],"terms":[58],"relative":[60],"abundances":[61],"various":[63],"protein":[64,74,104,125],"families.":[65],"latter":[67],"requires":[68],"assignment":[69,99],"individual":[71],"families,":[75],"which":[76,152],"hindered":[78],"by":[79],"fact":[81],"that":[82,118,136],"contain":[85],"only":[86],"fragment,":[88],"small,":[90],"protein.":[93],"RESULTS:":[94],"We":[95,147],"have":[96],"considered":[97],"families":[105],"directly":[106],"RPS-BLAST":[108],"against":[109,124],"COG":[110],"Pfam":[112],"databases":[113],"indirectly":[115],"via":[116],"proxygenes":[117],"are":[119],"identified":[120],"BLASTx":[122],"searches":[123],"databases.":[127],"Using":[128],"simulated":[129],"as":[132],"benchmarks,":[133],"we":[134],"show":[135],"proxygene":[138],"method":[139,151],"more":[141],"accurate":[142],"than":[143],"direct":[145],"assignment.":[146],"introduce":[148],"clustering":[150],"significantly":[153],"reduces":[154],"size":[156],"while":[161],"maintaining":[162],"faithful":[164],"representation":[165],"its":[167],"functional":[168],"taxonomic":[170],"content.":[171]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":7}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}