{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T03:13:36Z","timestamp":1770347616797,"version":"3.49.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2010,3,15]],"date-time":"2010-03-15T00:00:00Z","timestamp":1268611200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2010,12]]},"DOI":"10.1186\/1471-2105-11-131","type":"journal-article","created":{"date-parts":[[2010,3,16]],"date-time":"2010-03-16T07:15:45Z","timestamp":1268723745000},"source":"Crossref","is-referenced-by-count":89,"title":["Missing genes in the annotation of prokaryotic genomes"],"prefix":"10.1186","volume":"11","author":[{"given":"Andrew S","family":"Warren","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeremy","family":"Archuleta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu-chun","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jo\u00e3o Carlos","family":"Setubal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,3,15]]},"reference":[{"issue":"18","key":"3588_CR1","doi-asserted-by":"publisher","first-page":"5452","DOI":"10.1093\/nar\/gkh885","volume":"32","author":"MY Galperin","year":"2004","unstructured":"Galperin MY, Koonin EV: 'Conserved hypothetical' proteins: prioritization of targets for experimental study. Nucleic Acids Research 2004, 32(18):5452\u201363. 10.1093\/nar\/gkh885","journal-title":"Nucleic Acids Research"},{"issue":"3","key":"3588_CR2","doi-asserted-by":"publisher","first-page":"E42","DOI":"10.1371\/journal.pbio.0020042","volume":"2","author":"RJ Roberts","year":"2004","unstructured":"Roberts RJ: Identifying protein function-a call for community action. PLoS Biology 2004, 2(3):E42. 10.1371\/journal.pbio.0020042","journal-title":"PLoS Biology"},{"issue":"8","key":"3588_CR3","doi-asserted-by":"publisher","first-page":"3448","DOI":"10.1021\/cr068303k","volume":"107","author":"D Frishman","year":"2007","unstructured":"Frishman D: Protein annotation at genomic scale: the current status. Chemical Reviews 2007, 107(8):3448\u201366. 10.1021\/cr068303k","journal-title":"Chemical Reviews"},{"key":"3588_CR4","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/1471-2105-4-21","volume":"4","author":"TS Larsen","year":"2003","unstructured":"Larsen TS, Krogh A: EasyGene-a prokaryotic gene finder that ranks ORFs by statistical significance. BMC Bioinformatics 2003, 4: 21. 10.1186\/1471-2105-4-21","journal-title":"BMC Bioinformatics"},{"issue":"6","key":"3588_CR5","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1093\/bioinformatics\/btm009","volume":"23","author":"AL Delcher","year":"2007","unstructured":"Delcher AL, Bratke KA, Powers EC, Salzberg SL: Identifying bacterial genes and endosymbiont DNA with Glimmer. Bioinformatics 2007, 23(6):673\u2013679. 10.1093\/bioinformatics\/btm009","journal-title":"Bioinformatics"},{"key":"3588_CR6","doi-asserted-by":"publisher","first-page":"W451","DOI":"10.1093\/nar\/gki487","volume":"33","author":"J Besemer","year":"2005","unstructured":"Besemer J, Borodovsky M: GeneMark: web software for gene finding in prokaryotes, eukaryotes and viruses. Nucleic Acids Res 2005, 33: W451\u20134. 10.1093\/nar\/gki487","journal-title":"Nucleic Acids Res"},{"issue":"3","key":"3588_CR7","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1093\/bib\/bbl004","volume":"7","author":"I Friedberg","year":"2006","unstructured":"Friedberg I: Automated protein function prediction-the genomic challenge. Brief Bioinform 2006, 7(3):225\u2013242. 10.1093\/bib\/bbl004","journal-title":"Brief Bioinform"},{"issue":"8","key":"3588_CR8","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1016\/S0168-9525(01)02372-1","volume":"17","author":"M Skovgaard","year":"2001","unstructured":"Skovgaard M, Jensen LJ, Brunak S, Ussery D, Krogh A: On the total number of genes and their length distribution in complete microbial genomes. Trends in Genetics 2001, 17(8):425\u2013428. 10.1016\/S0168-9525(01)02372-1","journal-title":"Trends in Genetics"},{"key":"3588_CR9","doi-asserted-by":"publisher","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","volume":"25","author":"SF Altschul","year":"1997","unstructured":"Altschul SF, Madden TL, Schaffer AA, Zhang J, Zhang Z, Miller W, Lipman DJ: Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Acids Research 1997, 25: 3389\u20133402. 10.1093\/nar\/25.17.3389","journal-title":"Nucleic Acids Research"},{"key":"3588_CR10","volume-title":"International Journal of Concurrency and Computation: Practice and Experience (CCPE)","author":"P Balaji","year":"2010","unstructured":"Balaji P, Feng W, Lin H, Archuleta J, Matsuoka S, Warren A, Setubal J, Lusk E, Thakur R, Foster I, Katz DS, Jha S, Shinpaugh K, Coghlan S, Reed D: Global-scale Distributed I\/O with ParaMEDIC. International Journal of Concurrency and Computation: Practice and Experience (CCPE) 2010, in press."},{"key":"3588_CR11","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1093\/nar\/gkg111","volume":"31","author":"TT K Pruitt","year":"2003","unstructured":"K Pruitt TT, Maglott D: RefSeq and LocusLink: NCBI gene-centered resources. Nucleic Acid Res 2003, 31: 34\u201337. 10.1093\/nar\/gkg111","journal-title":"Nucleic Acid Res"},{"key":"3588_CR12","first-page":"2","volume-title":"Computer Communications and Networks, 2004. ICCCN 2004. Proceedings. 13th International Conference on","author":"S Varadarajan","year":"2004","unstructured":"Varadarajan S: System X: building the Virginia Tech supercomputer. Computer Communications and Networks, 2004. ICCCN 2004. Proceedings. 13th International Conference on 2004, 2."},{"key":"3588_CR13","volume-title":"In Proceedings of ClusterWorld 2003","author":"AE Darling","year":"2003","unstructured":"Darling AE, Carey L, Feng W: The Design, Implementation, and Evaluation of mpiBLAST. In Proceedings of ClusterWorld 2003 2003."},{"key":"3588_CR14","first-page":"72b","volume":"1","author":"H Lin","year":"2005","unstructured":"Lin H, Ma X, Chandramohan P, Geist A, Samatova N: Efficient Data Access for Parallel BLAST. Parallel and Distributed Processing Symposium, International 2005, 1: 72b.","journal-title":"Parallel and Distributed Processing Symposium, International"},{"key":"3588_CR15","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1145\/1242531.1242542","volume-title":"CF '07: Proceedings of the 4th international conference on Computing frontiers","author":"O Thorsen","year":"2007","unstructured":"Thorsen O, Smith B, Sosa CP, Jiang K, Lin H, Peters A, Feng W: Parallel genomic sequence-search on a massively parallel system. In CF '07: Proceedings of the 4th international conference on Computing frontiers. New York, NY, USA: ACM; 2007:59\u201368. full_text"},{"key":"3588_CR16","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1089\/omi.2005.9.91","volume":"9","author":"F Veloso","year":"2005","unstructured":"Veloso F, Riadi G, Aliaga D, Lieph R, Holmes DS: Large-Scale, Multi-Genome Analysis of Alternate Open Reading Frames in Bacteria and Archaea. OMICS: A Journal of Integrative Biology 2005, 9: 91\u2013105. 10.1089\/omi.2005.9.91","journal-title":"OMICS: A Journal of Integrative Biology"},{"issue":"11","key":"3588_CR17","doi-asserted-by":"publisher","first-page":"3569","DOI":"10.1128\/JB.01767-08","volume":"191","author":"A Wattam","year":"2009","unstructured":"Wattam A, Williams K, Snyder E, Jr NA, Shukla M, Dickerman AW, Crasta OR, Kenyon R, Lu J, Shallom JM, Yoo H, Ficht TA, Tsolis RM, Munk C, Tapia R, Han CS, Detter JC, Bruce D, Brettin TS, Sobral B, Boyle S, Setubal J: Analysis of ten Brucella genomes reveals evidence for horizontal gene transfer despite preferred intracellular lifestyle. J of Bacteriology 2009, 191(11):3569\u201379. 10.1128\/JB.01767-08","journal-title":"J of Bacteriology"},{"issue":"18","key":"3588_CR18","doi-asserted-by":"publisher","first-page":"6258","DOI":"10.1128\/JB.187.18.6258-6264.2005","volume":"187","author":"KT Konstantinidis","year":"2005","unstructured":"Konstantinidis KT, Tiedje JM: Towards a Genome-Based Taxonomy for Prokaryotes. Journal of Bacteriology 2005, 187(18):6258\u20136264. 10.1128\/JB.187.18.6258-6264.2005","journal-title":"Journal of Bacteriology"},{"issue":"9","key":"3588_CR19","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1038\/nrmicro1236","volume":"3","author":"D Gevers","year":"2005","unstructured":"Gevers D, Cohan FM, Lawrence JG, Spratt BG, Coenye T, Feil EJ, Stackebrandt E, de Peer YV, Vandamme P, Thompson FL, Swings J: Re-evaluating prokaryotic species. Nat Rev Micro 2005, 3(9):733\u2013739. 10.1038\/nrmicro1236","journal-title":"Nat Rev Micro"},{"issue":"2","key":"3588_CR20","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1038\/sj.hdy.6801011","volume":"100","author":"DM Ward","year":"2007","unstructured":"Ward DM, Cohan FM, Bhaya D, Heidelberg JF, Kuhl M, Grossman A: Genomics, environmental genomics and the issue of microbial species. Heredity 2007, 100(2):207\u2013219. 10.1038\/sj.hdy.6801011","journal-title":"Heredity"},{"issue":"7","key":"3588_CR21","doi-asserted-by":"publisher","first-page":"2567","DOI":"10.1073\/pnas.0409727102","volume":"102","author":"KT Konstantinidis","year":"2005","unstructured":"Konstantinidis KT, Tiedje JM: Genomic insights that advance the species definition for prokaryotes. Proceedings of the National Academy of Sciences of the United States of America 2005, 102(7):2567\u20132572. 10.1073\/pnas.0409727102","journal-title":"Proceedings of the National Academy of Sciences of the United States of America"},{"key":"3588_CR22","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1128\/JB.01202-08","volume":"191","author":"M Deloger","year":"2009","unstructured":"Deloger M, Karoui ME, Petit M: A Genomic Distance Based on MUM Indicates Discontinuity between Most Bacterial Species and Genera. J Bacteriol 2009, 191: 91\u201399. 10.1128\/JB.01202-08","journal-title":"J Bacteriol"},{"issue":"9","key":"3588_CR23","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1093\/bioinformatics\/17.9.847","volume":"17","author":"EM Zdobnov","year":"2001","unstructured":"Zdobnov EM, Apweiler R: InterProScan - an integration platform for the signature-recognition methods in InterPro. Bioinformatics 2001, 17(9):847\u2013848. 10.1093\/bioinformatics\/17.9.847","journal-title":"Bioinformatics"},{"key":"3588_CR24","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1186\/1471-2105-11-119","volume":"11","author":"D Hyatt","year":"2010","unstructured":"Hyatt D, Chen G, LoCascio P, Land M, Larimer F, Hauser L: Prodigal: prokaryotic gene recognition and translation initiation site identification. BMC Bioinformatics 2010, 11: 119. 10.1186\/1471-2105-11-119","journal-title":"BMC Bioinformatics"},{"key":"3588_CR25","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1099\/ijs.0.64483-0","volume":"57","author":"J Goris","year":"2007","unstructured":"Goris J, Konstantinidis KT, Klappenbach JA, Coenye T, Vandamme P, Tiedje JM: DNA-DNA hybridization values and their relationship to whole-genome sequence similarities. Int J Syst Evol Microbiol 2007, 57: 81\u201391. 10.1099\/ijs.0.64483-0","journal-title":"Int J Syst Evol Microbiol"},{"issue":"24","key":"3588_CR26","doi-asserted-by":"publisher","first-page":"4322","DOI":"10.1093\/bioinformatics\/bti701","volume":"21","author":"P Nielsen","year":"2005","unstructured":"Nielsen P, Krogh A: Large-scale prokaryotic gene prediction and comparison to genome annotation. Bioinformatics 2005, 21(24):4322\u20134329. 10.1093\/bioinformatics\/bti701","journal-title":"Bioinformatics"},{"issue":"12","key":"3588_CR27","doi-asserted-by":"publisher","first-page":"2607","DOI":"10.1093\/nar\/29.12.2607","volume":"29","author":"J Besemer","year":"2001","unstructured":"Besemer J, Lomsadze A, Borodovsky M: GeneMarkS: a self-training method for prediction of gene starts in microbial genomes. Implications for finding sequence motifs in regulatory regions. Nucl Acids Res 2001, 29(12):2607\u20132618. 10.1093\/nar\/29.12.2607","journal-title":"Nucl Acids Res"},{"issue":"4","key":"3588_CR28","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1016\/j.jmb.2003.08.057","volume":"333","author":"W Tian","year":"2003","unstructured":"Tian W, Skolnick J: How Well is Enzyme Function Conserved as a Function of Pairwise Sequence Identity? Journal of Molecular Biology 2003, 333(4):863\u2013882. 10.1016\/j.jmb.2003.08.057","journal-title":"Journal of Molecular Biology"},{"key":"3588_CR29","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1093\/dnares\/8.1.11","volume":"8","author":"T Hayashi","year":"2001","unstructured":"Hayashi T, Makino K, Ohnishi M, Kurokawa K, Ishii K, Yokoyama K, Han C, Ohtsubo E, Nakayama K, Murata T, Tanaka M, Tobe T, Iida T, Takami H, Honda T, Sasakawa C, Ogasawara N, Yasunaga T, Kuhara S, Shiba T, Hattori M, Shinagawa H: Complete Genome Sequence of Enterohemorrhagic Eschelichia coli O157:H7 and Genomic Comparison with a Laboratory Strain K-12. DNA Res 2001, 8: 11\u201322. 10.1093\/dnares\/8.1.11","journal-title":"DNA Res"},{"issue":"suppl_1","key":"3588_CR30","doi-asserted-by":"publisher","first-page":"D169","DOI":"10.1093\/nar\/gkn664","volume":"37","author":"Consortium TU","year":"2009","unstructured":"Consortium TU: The Universal Protein Resource (UniProt) 2009. Nucl Acids Res 2009, 37(suppl_1):D169\u2013174.","journal-title":"Nucl Acids Res"},{"issue":"suppl_1","key":"3588_CR31","first-page":"D281","volume":"36","author":"RD Finn","year":"2008","unstructured":"Finn RD, Tate J, Mistry J, Coggill PC, Sammut SJ, Hotz H, Ceric G, Forslund K, Eddy SR, Sonnhammer ELL, Bateman A: The Pfam protein families database. Nucl Acids Res 2008, 36(suppl_1):D281\u2013288.","journal-title":"Nucl Acids Res"},{"issue":"10","key":"3588_CR32","doi-asserted-by":"crossref","first-page":"3386","DOI":"10.1128\/jb.174.10.3386-3391.1992","volume":"174","author":"A Hochman","year":"1992","unstructured":"Hochman A, Figueredo A, Wall JD: Physiological functions of hydroperoxidases in Rhodobacter capsulatus. Journal of Bacteriology 1992, 174(10):3386\u20133391.","journal-title":"Journal of Bacteriology"},{"issue":"4","key":"3588_CR33","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1016\/S1673-8527(07)60039-3","volume":"34","author":"S Zhao","year":"2007","unstructured":"Zhao S, Zhang Q, Chen Z, Zhao Y, Zhong J: The Factors Shaping Synonymous Codon Usage in the Genome of Burkholderia mallei. Journal of Genetics and Genomics 2007, 34(4):362\u2013372. 10.1016\/S1673-8527(07)60039-3","journal-title":"Journal of Genetics and Genomics"},{"issue":"8","key":"3588_CR34","doi-asserted-by":"publisher","first-page":"1585","DOI":"10.1007\/s11274-007-9652-8","volume":"24","author":"S Zhao","year":"2008","unstructured":"Zhao S, Zhang Q, Chen Z, Zhong J: The factors dictating the codon usage variation among the genes in the genome of Burkholderia pseudomallei. World Journal of Microbiology and Biotechnology 2008, 24(8):1585\u20131592. 10.1007\/s11274-007-9652-8","journal-title":"World Journal of Microbiology and Biotechnology"},{"issue":"6","key":"3588_CR35","doi-asserted-by":"publisher","first-page":"1487","DOI":"10.1111\/j.1365-2958.2008.06495.x","volume":"70","author":"MR Hemm","year":"2008","unstructured":"Hemm MR, Paul BJ, Schneider TD, Storz G, Rudd KE: Small membrane proteins found by comparative genomics and ribosome binding site models. Molecular Microbiology 2008, 70(6):1487\u20131501. 10.1111\/j.1365-2958.2008.06495.x","journal-title":"Molecular Microbiology"},{"key":"3588_CR36","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1128\/JB.00872-09","volume":"192","author":"MR Hemm","year":"2010","unstructured":"Hemm MR, Paul BJ, Miranda-Rios J, Zhang A, Soltanzad N, Storz G: Small Stress Response Proteins in Escherichia coli: Proteins Missed by Classical Proteomic Studies. J Bacteriol 2010, 192: 46\u201358. 10.1128\/JB.00872-09","journal-title":"J Bacteriol"},{"issue":"6","key":"3588_CR37","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1101\/gr.089714.108","volume":"19","author":"A Marchais","year":"2009","unstructured":"Marchais A, Naville M, Bohn C, Bouloc P, Gautheret D: Single-pass classification of all noncoding sequences in a bacterial genome using phylogenetic profiles. Genome Research 2009, 19(6):1084\u20131092. 10.1101\/gr.089714.108","journal-title":"Genome Research"},{"issue":"3","key":"3588_CR38","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1094\/PHYTO-100-3-0208","volume":"100","author":"NF Almeida","year":"2010","unstructured":"Almeida NF, Yan S, Cai R, Clarke CR, Morris CE, Schaad NW, Schuenzel EL, Lacy GH, Sun X, Jones JB, Castillo JA, Bull CT, Leman S, Guttman DS, Setubal JC, Vinatzer BA: PAMDB, A Multilocus Sequence Typing and Analysis Database and Website for Plant-Associated Microbes. Phytopathology 2010, 100(3):208\u2013215. 10.1094\/PHYTO-100-3-0208","journal-title":"Phytopathology"},{"key":"3588_CR39","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1186\/1471-2105-9-182","volume":"9","author":"S Yooseph","year":"2008","unstructured":"Yooseph S, Li W, Sutton G: Gene identification and protein classification in microbial metagenomic sequence data via incremental clustering. BMC Bioinformatics 2008, 9: 182. 10.1186\/1471-2105-9-182","journal-title":"BMC Bioinformatics"},{"issue":"10","key":"3588_CR40","doi-asserted-by":"publisher","first-page":"3976","DOI":"10.1073\/pnas.0813403106","volume":"106","author":"DR Yoder-Himes","year":"2009","unstructured":"Yoder-Himes DR, Chain PS, Zhu Y, Wurtzel O, Rubin EM, Tiedje JM, Sorek R: Mapping the Burkholderia cenocepacia niche response via high-throughput sequencing. Proc Natl Acad Sci USA 2009, 106(10):3976\u201381. 10.1073\/pnas.0813403106","journal-title":"Proc Natl Acad Sci USA"},{"key":"3588_CR41","volume-title":"Chapman & Hall\/CRC","author":"BW Silverman","year":"1986","unstructured":"Silverman BW: Density estimation for statistics and data analysis. Chapman & Hall\/CRC 1986."},{"key":"3588_CR42","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198523963.001.0001","volume-title":"Applied smoothing techniques for data analysis","author":"AW Bowman","year":"1997","unstructured":"Bowman AW, Azzalini A: Applied smoothing techniques for data analysis. Oxford, Oxford University Press; 1997."},{"key":"3588_CR43","volume-title":"R: A Language and Environment for Statistical Computing","author":"R Development Core Team","year":"2009","unstructured":"R Development Core Team:R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria; 2009. [ http:\/\/www.R-project.org ]"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-11-131.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1471-2105-11-131\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-11-131.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T03:39:17Z","timestamp":1711337957000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/1471-2105-11-131"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,3,15]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2010,12]]}},"alternative-id":["3588"],"URL":"https:\/\/doi.org\/10.1186\/1471-2105-11-131","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,3,15]]},"article-number":"131"}}