{"id":"https://openalex.org/W4284990104","doi":"https://doi.org/10.1093/bib/bbac283","title":"High-quality pan-genome of <i>Escherichia coli</i> generated by excluding confounding and highly similar strains reveals an association between unique gene clusters and genomic islands","display_name":"High-quality pan-genome of <i>Escherichia coli</i> generated by excluding confounding and highly similar strains reveals an association between unique gene clusters and genomic islands","publication_year":2022,"publication_date":"2022-07-09","ids":{"openalex":"https://openalex.org/W4284990104","doi":"https://doi.org/10.1093/bib/bbac283","pmid":"https://pubmed.ncbi.nlm.nih.gov/35809555"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbac283","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbac283","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101842498","display_name":"Yang Tong","orcid":"https://orcid.org/0009-0001-1134-2204"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Yang","raw_affiliation_strings":["Department of Physics, School of Science, Tianjin University , Tianjin 300072, China"],"affiliations":[{"raw_affiliation_string":"Department of Physics, School of Science, Tianjin University , Tianjin 300072, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074242312","display_name":"Feng Gao","orcid":"https://orcid.org/0000-0002-9563-3841"},"institutions":[{"id":"https://openalex.org/I4210151209","display_name":"Collaborative Innovation Center of Chemical Science and Engineering Tianjin","ror":"https://ror.org/0225a5s12","country_code":"CN","type":"facility","lineage":["https://openalex.org/I162868743","https://openalex.org/I205237279","https://openalex.org/I4210151209"]},{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feng Gao","raw_affiliation_strings":["Department of Physics, School of Science, Tianjin University , Tianjin 300072, China","Frontiers Science Center for Synthetic Biology and Key Laboratory of Systems Bioengineering (Ministry of Education), Tianjin University , Tianjin 300072, China","SynBio Research Platform, Collaborative Innovation Center of Chemical Science and Engineering (Tianjin) , Tianjin 300072, China"],"affiliations":[{"raw_affiliation_string":"Department of Physics, School of Science, Tianjin University , Tianjin 300072, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Frontiers Science Center for Synthetic Biology and Key Laboratory of Systems Bioengineering (Ministry of Education), Tianjin University , Tianjin 300072, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"SynBio Research Platform, Collaborative Innovation Center of Chemical Science and Engineering (Tianjin) , Tianjin 300072, China","institution_ids":["https://openalex.org/I4210151209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5074242312"],"corresponding_institution_ids":["https://openalex.org/I162868743","https://openalex.org/I4210151209"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":1.2009,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.77751889,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"23","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9995999932289124,"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":0.9995999932289124,"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/T11048","display_name":"Bacteriophages and microbial interactions","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.9074538350105286},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.7535038590431213},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.6234259009361267},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.5857748985290527},{"id":"https://openalex.org/keywords/genome-evolution","display_name":"Genome evolution","score":0.47212180495262146},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.44547581672668457},{"id":"https://openalex.org/keywords/comparative-genomics","display_name":"Comparative genomics","score":0.43132591247558594},{"id":"https://openalex.org/keywords/reference-genome","display_name":"Reference genome","score":0.4138588309288025},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.40199247002601624},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.3967413306236267}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.9074538350105286},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.7535038590431213},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.6234259009361267},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.5857748985290527},{"id":"https://openalex.org/C174600577","wikidata":"https://www.wikidata.org/wiki/Q5533491","display_name":"Genome evolution","level":4,"score":0.47212180495262146},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.44547581672668457},{"id":"https://openalex.org/C105176652","wikidata":"https://www.wikidata.org/wiki/Q1147112","display_name":"Comparative genomics","level":5,"score":0.43132591247558594},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.4138588309288025},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.40199247002601624},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.3967413306236267},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004926","descriptor_name":"Escherichia coli","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005810","descriptor_name":"Multigene Family","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016680","descriptor_name":"Genome, Bacterial","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D044404","descriptor_name":"Genomic Islands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D044404","descriptor_name":"Genomic Islands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D044404","descriptor_name":"Genomic Islands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bib/bbac283","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbac283","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"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":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:35809555","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35809555","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":"Briefings in bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life below water","id":"https://metadata.un.org/sdg/14","score":0.8299999833106995}],"awards":[{"id":"https://openalex.org/G518651691","display_name":null,"funder_award_id":"2018YFA0903700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7243257119","display_name":null,"funder_award_id":"21621004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G999540423","display_name":null,"funder_award_id":"31571358","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W1553112231","https://openalex.org/W1895949598","https://openalex.org/W1968146772","https://openalex.org/W1968828904","https://openalex.org/W1972422447","https://openalex.org/W1983761774","https://openalex.org/W1994670764","https://openalex.org/W2014456513","https://openalex.org/W2018345907","https://openalex.org/W2027831845","https://openalex.org/W2029702456","https://openalex.org/W2030685648","https://openalex.org/W2045204781","https://openalex.org/W2048620141","https://openalex.org/W2050783903","https://openalex.org/W2052426953","https://openalex.org/W2055615325","https://openalex.org/W2059612273","https://openalex.org/W2063655745","https://openalex.org/W2070524329","https://openalex.org/W2074879055","https://openalex.org/W2079327011","https://openalex.org/W2089859322","https://openalex.org/W2091328482","https://openalex.org/W2091543364","https://openalex.org/W2093610003","https://openalex.org/W2096093282","https://openalex.org/W2099143902","https://openalex.org/W2101414295","https://openalex.org/W2108473040","https://openalex.org/W2117207428","https://openalex.org/W2120187241","https://openalex.org/W2121695290","https://openalex.org/W2122673596","https://openalex.org/W2125456570","https://openalex.org/W2129978006","https://openalex.org/W2132682438","https://openalex.org/W2133579817","https://openalex.org/W2138988050","https://openalex.org/W2150550043","https://openalex.org/W2151183612","https://openalex.org/W2156103113","https://openalex.org/W2158847524","https://openalex.org/W2180747979","https://openalex.org/W2265889397","https://openalex.org/W2307372947","https://openalex.org/W2345791363","https://openalex.org/W2512449213","https://openalex.org/W2610656577","https://openalex.org/W2752183800","https://openalex.org/W2791965697","https://openalex.org/W2900285507","https://openalex.org/W2900629010","https://openalex.org/W2927961455","https://openalex.org/W2951254987","https://openalex.org/W2971117654","https://openalex.org/W3007303376","https://openalex.org/W3133795275","https://openalex.org/W3133801989","https://openalex.org/W3161596995","https://openalex.org/W3177542363","https://openalex.org/W3209996628","https://openalex.org/W4200070595","https://openalex.org/W4211040199","https://openalex.org/W4232481750","https://openalex.org/W6805033226"],"related_works":["https://openalex.org/W2279684808","https://openalex.org/W2414506155","https://openalex.org/W3137911940","https://openalex.org/W2752117239","https://openalex.org/W3217304749","https://openalex.org/W1975474703","https://openalex.org/W1493660383","https://openalex.org/W2894932706","https://openalex.org/W2066142713","https://openalex.org/W2759519215"],"abstract_inverted_index":{"The":[0],"pan-genome":[1,23,56,81,105,137,152,176],"analysis":[2,24,106,138],"of":[3,13,32,42,54,69,77,89,92,111,116,118,139,183],"bacteria":[4],"provides":[5,127],"detailed":[6],"insight":[7],"into":[8],"the":[9,18,22,30,40,46,52,55,67,75,90,96,108,145,156,167,181],"diversity":[10],"and":[11,45,155,161,171],"evolution":[12],"a":[14,86,134,148,175],"bacterial":[15],"population.":[16],"However,":[17],"genomes":[19,119],"involved":[20],"in":[21,80,95],"should":[25,101],"be":[26,102],"checked":[27],"carefully,":[28],"as":[29,131,133],"inclusion":[31,68],"confounding":[33],"strains":[34,49,72,100],"would":[35],"have":[36,120],"unfavorable":[37],"effects":[38],"on":[39],"identification":[41,182],"core":[43],"genes,":[44],"highly":[47,70],"similar":[48,71],"could":[50],"bias":[51],"results":[53,76],"state":[57],"(open":[58],"versus":[59],"closed).":[60],"In":[61],"this":[62,140],"study,":[63],"we":[64],"found":[65],"that":[66],"also":[73],"affects":[74],"unique":[78,93,157,168],"genes":[79,94,158],"analysis,":[82],"which":[83,126,178],"leads":[84],"to":[85],"significant":[87],"underestimation":[88],"number":[91],"pan-genome.":[97],"Therefore,":[98],"these":[99],"excluded":[103],"from":[104,174],"at":[107],"early":[109],"stage":[110],"data":[112],"processing.":[113],"Currently,":[114],"tens":[115],"thousands":[117],"been":[121],"sequenced":[122],"for":[123,136],"Escherichia":[124],"coli,":[125],"an":[128,164],"unprecedented":[129],"opportunity":[130],"well":[132],"challenge":[135],"classical":[141],"model":[142],"organism.":[143],"Using":[144],"proposed":[146],"strategies,":[147],"high-quality":[149],"E.":[150],"coli":[151],"was":[153,159],"obtained,":[154],"extracted":[160],"analyzed,":[162],"revealing":[163],"association":[165],"between":[166],"gene":[169],"clusters":[170],"genomic":[172,184],"islands":[173],"perspective,":[177],"may":[179],"facilitate":[180],"islands.":[185]},"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":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2022-07-11T00:00:00"}
