{"id":"https://openalex.org/W2106651224","doi":"https://doi.org/10.1186/1471-2105-9-546","title":"Barcodes for genomes and applications","display_name":"Barcodes for genomes and applications","publication_year":2008,"publication_date":"2008-12-01","ids":{"openalex":"https://openalex.org/W2106651224","doi":"https://doi.org/10.1186/1471-2105-9-546","mag":"2106651224","pmid":"https://pubmed.ncbi.nlm.nih.gov/19091119"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-9-546","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-546","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-546","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/10.1186/1471-2105-9-546","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058786170","display_name":"Fengfeng Zhou","orcid":"https://orcid.org/0000-0002-8108-6007"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fengfeng Zhou","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology, University of Georgia, Athens, GA 30602, USA. ffzhou@csbl.bmb.uga.edu","University of Georgia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology, University of Georgia, Athens, GA 30602, USA. ffzhou@csbl.bmb.uga.edu","institution_ids":["https://openalex.org/I165733156"]},{"raw_affiliation_string":"University of Georgia,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026918414","display_name":"Victor Olman","orcid":null},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Victor Olman","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology and Institute of Bioinformatics, and BioEnergy Science Center (BESC), University of Georgia, Athens, GA, 30602, USA","University of Georgia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology and Institute of Bioinformatics, and BioEnergy Science Center (BESC), University of Georgia, Athens, GA, 30602, USA","institution_ids":["https://openalex.org/I165733156"]},{"raw_affiliation_string":"University of Georgia,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020171946","display_name":"Ying Xu","orcid":"https://orcid.org/0000-0002-7856-3343"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Xu","raw_affiliation_strings":["Department of Biochemistry and Molecular Biology and Institute of Bioinformatics, and BioEnergy Science Center (BESC), University of Georgia, Athens, GA, 30602, USA","University of Georgia,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biochemistry and Molecular Biology and Institute of Bioinformatics, and BioEnergy Science Center (BESC), University of Georgia, Athens, GA, 30602, USA","institution_ids":["https://openalex.org/I165733156"]},{"raw_affiliation_string":"University of Georgia,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":3.6504,"has_fulltext":true,"cited_by_count":106,"citation_normalized_percentile":{"value":0.93528568,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"9","issue":"1","first_page":"546","last_page":"546"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.7785000205039978,"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":0.7785000205039978,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.039400000125169754,"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":0.03680000081658363,"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/genome","display_name":"Genome","score":0.8821979761123657},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.6853560209274292},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.6720551252365112},{"id":"https://openalex.org/keywords/barcode","display_name":"Barcode","score":0.6713691353797913},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6183711290359497},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.47209709882736206},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.41594892740249634},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.32628655433654785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.1519084870815277}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.8821979761123657},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.6853560209274292},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6720551252365112},{"id":"https://openalex.org/C2776841711","wikidata":"https://www.wikidata.org/wiki/Q856","display_name":"Barcode","level":2,"score":0.6713691353797913},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6183711290359497},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.47209709882736206},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.41594892740249634},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.32628655433654785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.1519084870815277},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D001483","descriptor_name":"Base Sequence","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","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":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-9-546","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-546","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-546","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:19091119","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19091119","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:d43996bca0474b099870f04e94f0de00","is_oa":false,"landing_page_url":"https://doaj.org/article/d43996bca0474b099870f04e94f0de00","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 9, Iss 1, p 546 (2008)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2621371","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2621371","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"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-9-546","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-9-546","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-9-546","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/G2954911513","display_name":null,"funder_award_id":"ITR-IIS-0407204","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3375237257","display_name":null,"funder_award_id":"CCF0621700","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3453259917","display_name":null,"funder_award_id":"DBI-0354771","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4883808398","display_name":null,"funder_award_id":"DBI-0542119","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5864136272","display_name":"ITR Collaborative Research:  Combinatorial Algorithms for Biological Data Clustering","funder_award_id":"0407204","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7137655021","display_name":"Computational Prediction of Biological Networks in Microbes and Applications to Cyanobacteria","funder_award_id":"0542119","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7168705754","display_name":"A Computational Capability for Fast and Reliable Characterization of Protein Complexes","funder_award_id":"0354771","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306352","display_name":"Georgia Cancer Coalition","ror":"https://ror.org/0009gvn90"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337509","display_name":"Biological and Environmental Research","ror":"https://ror.org/0114b2m14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2106651224.pdf","grobid_xml":"https://content.openalex.org/works/W2106651224.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1980415262","https://openalex.org/W1980914602","https://openalex.org/W1981229471","https://openalex.org/W1987853052","https://openalex.org/W1994035189","https://openalex.org/W1999232678","https://openalex.org/W2000190756","https://openalex.org/W2004469916","https://openalex.org/W2030154486","https://openalex.org/W2036848170","https://openalex.org/W2047448447","https://openalex.org/W2096984027","https://openalex.org/W2100310722","https://openalex.org/W2113824405","https://openalex.org/W2127284416","https://openalex.org/W2130956021","https://openalex.org/W2138952930","https://openalex.org/W2140211206","https://openalex.org/W2141394464","https://openalex.org/W2142967793","https://openalex.org/W2150337627","https://openalex.org/W2162732321","https://openalex.org/W2915868289","https://openalex.org/W3004540582","https://openalex.org/W3145128584","https://openalex.org/W4246105018","https://openalex.org/W4372046852"],"related_works":["https://openalex.org/W2210738511","https://openalex.org/W2487541429","https://openalex.org/W1910109602","https://openalex.org/W2080583581","https://openalex.org/W4297131566","https://openalex.org/W2017364432","https://openalex.org/W2329606903","https://openalex.org/W3195915274","https://openalex.org/W4285082713","https://openalex.org/W2344981695"],"abstract_inverted_index":{"BACKGROUND:":[0],"Each":[1],"genome":[2,44,188],"has":[3,87],"a":[4,180],"stable":[5],"distribution":[6],"of":[7,35,59,105,118,123,130,135,150,175],"the":[8,28,47,57,116,119,128,140,166],"combined":[9],"frequency":[10,38],"for":[11,31,54,95,147,185],"each":[12,43,55],"k-mer":[13,37],"and":[14,45,91,103,127,144,156,158,172,182,189],"its":[15,60],"reverse":[16],"complement":[17],"measured":[18],"in":[19,121],"sequence":[20,62,69],"fragments":[21,63,70],"as":[22,24],"short":[23,61],"1000":[25],"bps":[26],"across":[27],"whole":[29],"genome,":[30,56],"1<k<6.":[32],"The":[33],"collection":[34],"these":[36],"distributions":[39],"is":[40],"unique":[41],"to":[42,76,89,165],"termed":[46],"genome's":[48],"barcode.":[49],"RESULTS:":[50],"We":[51],"found":[52],"that":[53,78],"majority":[58],"have":[64,142],"highly":[65,83],"similar":[66],"barcodes":[67,73,137,141,160,177],"while":[68],"with":[71],"different":[72,143,148],"typically":[74],"correspond":[75],"genes":[77],"are":[79,162],"horizontally":[80,106],"transferred":[81,107],"or":[82],"expressed.":[84],"This":[85],"observation":[86],"led":[88],"new":[90,181],"more":[92],"effective":[93,183],"ways":[94],"addressing":[96],"two":[97],"challenging":[98],"problems:":[99],"metagenome":[100,111,190],"binning":[101,112,125],"problem":[102],"identification":[104],"genes.":[108],"Our":[109],"barcode-based":[110],"algorithm":[113],"substantially":[114],"improves":[115],"state":[117],"art":[120],"terms":[122],"both":[124],"accuracies":[126],"scope":[129],"applicability.":[131],"Other":[132],"attractive":[133],"properties":[134,174],"genomes":[136,151,176],"include":[138],"(a)":[139],"identifiable":[145],"characteristics":[146],"classes":[149],"like":[152],"prokaryotes,":[153],"eukaryotes,":[154],"mitochondria":[155],"plastids,":[157],"(b)":[159],"similarities":[161],"generally":[163],"proportional":[164],"genomes'":[167],"phylogenetic":[168],"closeness.":[169],"CONCLUSION:":[170],"These":[171],"other":[173],"make":[178],"them":[179],"tool":[184],"studying":[186],"numerous":[187],"analysis":[191],"problems.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":7}],"updated_date":"2026-06-18T10:00:31.954636","created_date":"2025-10-10T00:00:00"}
