{"id":"https://openalex.org/W2090327616","doi":"https://doi.org/10.1186/1471-2105-11-131","title":"Missing genes in the annotation of prokaryotic genomes","display_name":"Missing genes in the annotation of prokaryotic genomes","publication_year":2010,"publication_date":"2010-03-15","ids":{"openalex":"https://openalex.org/W2090327616","doi":"https://doi.org/10.1186/1471-2105-11-131","mag":"2090327616","pmid":"https://pubmed.ncbi.nlm.nih.gov/20230630"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-11-131","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-131","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-131","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/10.1186/1471-2105-11-131","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016058860","display_name":"Andrew Warren","orcid":"https://orcid.org/0000-0003-2660-0103"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew S Warren","raw_affiliation_strings":["Virginia Bioinformatics Institute, Virginia Tech, Blacksburg, VA, USA. anwarren@vt.edu","Virginia Bioinformatics Institute, Virginia Tech, Blacksburg, USA","Department of Computer Science, Virginia Tech, Blacksburg, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Bioinformatics Institute, Virginia Tech, Blacksburg, VA, USA. anwarren@vt.edu","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Virginia Bioinformatics Institute, Virginia Tech, Blacksburg, USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024547145","display_name":"Jeremy Archuleta","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeremy Archuleta","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, Blacksburg, VA, USA","Department of Computer Science Virginia Tech Blacksburg, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer Science Virginia Tech Blacksburg, USA#TAB#","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058539554","display_name":"Wu-chun Feng","orcid":"https://orcid.org/0000-0002-6015-0727"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu-chun Feng","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, Blacksburg, VA, USA","Department of Computer Science Virginia Tech Blacksburg, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer Science Virginia Tech Blacksburg, USA#TAB#","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060418877","display_name":"Jo\u00e3o Carlos Set\u00fabal","orcid":"https://orcid.org/0000-0001-9174-2816"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Carlos Setubal","raw_affiliation_strings":["Department of Computer Science, Virginia Tech, Blacksburg, VA, USA","Virginia Bioinformatics Institute, Virginia Tech, Blacksburg, VA, USA","Virginia Bioinformatics Institute, Virginia Tech, Blacksburg, USA","Department of Computer Science, Virginia Tech, Blacksburg, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Virginia Bioinformatics Institute, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Virginia Bioinformatics Institute, Virginia Tech, Blacksburg, USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016058860"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":2.994,"has_fulltext":true,"cited_by_count":118,"citation_normalized_percentile":{"value":0.91481944,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"11","issue":"1","first_page":"131","last_page":"131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.8817999958992004,"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":0.8817999958992004,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.010200000368058681,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.008899999782443047,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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":0.9297772645950317},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.8025709390640259},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.7234890460968018},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.7178943753242493},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.6446382999420166},{"id":"https://openalex.org/keywords/gene-annotation","display_name":"Gene Annotation","score":0.584070086479187},{"id":"https://openalex.org/keywords/gene-prediction","display_name":"Gene prediction","score":0.5798672437667847},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5143088102340698},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.44558632373809814},{"id":"https://openalex.org/keywords/refseq","display_name":"RefSeq","score":0.4444811940193176},{"id":"https://openalex.org/keywords/open-reading-frame","display_name":"Open reading frame","score":0.3007507920265198},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.060701847076416016}],"concepts":[{"id":"https://openalex.org/C2780530800","wikidata":"https://www.wikidata.org/wiki/Q7072921","display_name":"ORFS","level":5,"score":0.9297772645950317},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.8025709390640259},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.7234890460968018},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.7178943753242493},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.6446382999420166},{"id":"https://openalex.org/C2908923196","wikidata":"https://www.wikidata.org/wiki/Q5205742","display_name":"Gene Annotation","level":4,"score":0.584070086479187},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.5798672437667847},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5143088102340698},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.44558632373809814},{"id":"https://openalex.org/C151810110","wikidata":"https://www.wikidata.org/wiki/Q7307074","display_name":"RefSeq","level":4,"score":0.4444811940193176},{"id":"https://openalex.org/C47289529","wikidata":"https://www.wikidata.org/wiki/Q908550","display_name":"Open reading frame","level":4,"score":0.3007507920265198},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.060701847076416016}],"mesh":[{"descriptor_ui":"D005798","descriptor_name":"Genes, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005798","descriptor_name":"Genes, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005798","descriptor_name":"Genes, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011387","descriptor_name":"Prokaryotic Cells","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011387","descriptor_name":"Prokaryotic Cells","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011387","descriptor_name":"Prokaryotic Cells","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":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":8,"locations":[{"id":"doi:10.1186/1471-2105-11-131","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-131","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-131","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:20230630","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20230630","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:oai:doaj.org/article:3e50c3f519e94a98bc168ed7ae44ab0e","is_oa":false,"landing_page_url":"https://doaj.org/article/3e50c3f519e94a98bc168ed7ae44ab0e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 11, Iss 1, p 131 (2010)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:3098052","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3098052","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/103182","is_oa":true,"landing_page_url":"http://www.biomedcentral.com/1471-2105/11/131","pdf_url":null,"source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"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:vtechworks.lib.vt.edu:10919/18846","is_oa":true,"landing_page_url":"http://hdl.handle.net/10919/18846","pdf_url":null,"source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"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":"","raw_type":"Journal article"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/18847","is_oa":true,"landing_page_url":"http://hdl.handle.net/10919/18847","pdf_url":null,"source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"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:vtechworks.lib.vt.edu:10919/94389","is_oa":true,"landing_page_url":"http://hdl.handle.net/10919/94389","pdf_url":null,"source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"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":"","raw_type":"Article - Refereed"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-11-131","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-11-131","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-11-131","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2090327616.pdf","grobid_xml":"https://content.openalex.org/works/W2090327616.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W145805655","https://openalex.org/W1642507902","https://openalex.org/W1873623553","https://openalex.org/W1978164115","https://openalex.org/W1987139333","https://openalex.org/W1994456450","https://openalex.org/W1997145886","https://openalex.org/W2017335389","https://openalex.org/W2022366078","https://openalex.org/W2024866217","https://openalex.org/W2025686663","https://openalex.org/W2062233253","https://openalex.org/W2071031214","https://openalex.org/W2072038175","https://openalex.org/W2084018711","https://openalex.org/W2088724842","https://openalex.org/W2099836442","https://openalex.org/W2100320834","https://openalex.org/W2100702435","https://openalex.org/W2103601429","https://openalex.org/W2105199251","https://openalex.org/W2106090237","https://openalex.org/W2112286591","https://openalex.org/W2115313399","https://openalex.org/W2117725451","https://openalex.org/W2118360643","https://openalex.org/W2119027485","https://openalex.org/W2120561624","https://openalex.org/W2123153443","https://openalex.org/W2127036970","https://openalex.org/W2128777911","https://openalex.org/W2129905273","https://openalex.org/W2131892542","https://openalex.org/W2134375163","https://openalex.org/W2134650310","https://openalex.org/W2141885858","https://openalex.org/W2143485490","https://openalex.org/W2154478075","https://openalex.org/W2158714788","https://openalex.org/W2161062388","https://openalex.org/W2165009364","https://openalex.org/W2165270659","https://openalex.org/W2167209023","https://openalex.org/W2582743722","https://openalex.org/W2951726307","https://openalex.org/W4210323379","https://openalex.org/W4211000692","https://openalex.org/W4285719527","https://openalex.org/W4388290870"],"related_works":["https://openalex.org/W2149629850","https://openalex.org/W1978801575","https://openalex.org/W2029252138","https://openalex.org/W4306784270","https://openalex.org/W2101899141","https://openalex.org/W4200441850","https://openalex.org/W2071205060","https://openalex.org/W2058497199","https://openalex.org/W2117510233","https://openalex.org/W1896121662"],"abstract_inverted_index":{"BACKGROUND:":[0],"Protein-coding":[1],"gene":[2,25,132,146,210,228],"detection":[3,204],"in":[4,14,99,134],"prokaryotic":[5,24,81,213],"genomes":[6],"is":[7,231],"considered":[8],"a":[9,56,92,233,253],"much":[10],"simpler":[11],"problem":[12],"than":[13,72,181],"intron-containing":[15],"eukaryotic":[16],"genomes.":[17],"However":[18],"there":[19],"have":[20,28,47,54,103,127],"been":[21],"reports":[22],"that":[23,85,108,140,197],"finder":[26],"programs":[27],"problems":[29],"with":[30,137,189],"small":[31,50,179,222],"genes":[32,107,117,158,164,176,201],"(either":[33],"over-predicting":[34],"or":[35,73],"under-predicting).":[36],"Therefore":[37],"the":[38,138,174,237,242],"question":[39],"arises":[40],"as":[41,156],"to":[42,60,75,121,131,144,161,241,246,252],"whether":[43,248],"current":[44,112],"genome":[45,113,214],"annotations":[46,215],"systematically":[48],"missing,":[49],"genes.":[51,223],"RESULTS:":[52],"We":[53,148],"developed":[55],"high-performance":[57],"computing":[58],"methodology":[59,66],"investigate":[61],"this":[62,65],"problem.":[63],"In":[64],"we":[67,102],"compare":[68],"all":[69,79],"ORFs":[70,98,142],"larger":[71],"equal":[74],"33":[76],"aa":[77],"from":[78,111],"fully-sequenced":[80],"replicons.":[82],"Based":[83],"on":[84,236],"comparison,":[86],"and":[87,124,192,212],"using":[88],"conservative":[89,243],"criteria":[90,244],"requiring":[91],"minimum":[93],"taxonomic":[94],"diversity":[95],"between":[96],"conserved":[97],"different":[100],"genomes,":[101],"discovered":[104],"1,153":[105],"candidate":[106],"are":[109,118,178,202],"missing":[110,116,145,175,227],"annotations.":[114],"These":[115],"similar":[119],"only":[120],"each":[122],"other":[123],"do":[125],"not":[126],"any":[128],"strong":[129],"similarity":[130,160],"sequences":[133],"public":[135],"databases,":[136],"implication":[139],"these":[141,167,200,206],"belong":[143],"families.":[147],"also":[149],"uncovered":[150],"38,895":[151],"intergenic":[152],"ORFs,":[153],"readily":[154],"identified":[155],"putative":[157],"by":[159,205],"currently":[162],"annotated":[163],"(we":[165],"call":[166],"absent":[168],"annotations).":[169],"The":[170,224],"vast":[171],"majority":[172],"of":[173,186,199,221,226],"found":[177,230],"(less":[180],"100":[182],"aa).":[183],"A":[184],"comparison":[185],"select":[187],"examples":[188],"GeneMark,":[190],"EasyGene":[191],"Glimmer":[193],"predictions":[194],"yields":[195],"evidence":[196],"some":[198],"escaping":[203],"programs.":[207],"CONCLUSIONS:":[208],"Prokaryotic":[209],"finders":[211],"require":[216],"improvement":[217],"for":[218],"accurate":[219],"prediction":[220],"number":[225],"families":[229],"likely":[232],"lower":[234],"bound":[235],"actual":[238],"number,":[239],"due":[240],"used":[245],"determine":[247],"an":[249],"ORF":[250],"corresponds":[251],"real":[254],"gene.":[255]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":7}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
