{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T08:14:38Z","timestamp":1760170478471},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"S6","license":[{"start":{"date-parts":[[2008,5,28]],"date-time":"2008-05-28T00:00:00Z","timestamp":1211932800000},"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":[[2008,12]]},"DOI":"10.1186\/1471-2105-9-s6-s15","type":"journal-article","created":{"date-parts":[[2008,5,28]],"date-time":"2008-05-28T14:15:46Z","timestamp":1211984146000},"source":"Crossref","is-referenced-by-count":29,"title":["An improved string composition method for sequence comparison"],"prefix":"10.1186","volume":"9","author":[{"given":"Guoqing","family":"Lu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shunpu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2008,5,28]]},"reference":[{"key":"2626_CR1","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1080\/106351598260897","volume":"47","author":"JJ Wiens","year":"1998","unstructured":"Wiens JJ, Servedio MR: Phylogenetic analysis and intraspecific variation: performance of parsimony, likelihood, and distance methods. Syst Biol 1998, 47: 228\u201353. 10.1080\/106351598260897","journal-title":"Syst Biol"},{"key":"2626_CR2","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1126\/science.290.5491.471","volume":"290","author":"TK Attwood","year":"2000","unstructured":"Attwood TK: Genomics: the Babel of bioinformatics. Science 2000, 290: 471\u2013473. 10.1126\/science.290.5491.471","journal-title":"Science"},{"key":"2626_CR3","unstructured":"Pearson WR: Protein sequence comparison and protein evolution. Tutorial-ISMB2000 Tutorial-ISMB2000"},{"key":"2626_CR4","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1093\/bioinformatics\/btg005","volume":"19","author":"S Vinga","year":"2003","unstructured":"Vinga S, Almeida J: Alignment free sequence comparison-a review. Bioinformatics 2003, 19: 513\u2013523. 10.1093\/bioinformatics\/btg005","journal-title":"Bioinformatics"},{"key":"2626_CR5","doi-asserted-by":"publisher","first-page":"8117","DOI":"10.1128\/JVI.75.17.8117-8126.2001","volume":"75","author":"E Herniou","year":"2001","unstructured":"Herniou E, Luque T, Chen X, Vlak J, Winstanley D, Cory J, O'Reilly D: Use of whole genome sequence data to infer baculovirus phylogeny. J Virol 2001, 75: 8117\u20138126. 10.1128\/JVI.75.17.8117-8126.2001","journal-title":"J Virol"},{"key":"2626_CR6","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1007\/s00239-001-0054-5","volume":"54","author":"C House","year":"2002","unstructured":"House C, Fitz-Gibbon S: Using homolog groups to create a whole-genomic tree of free-living organisms: An update. J Mol Evol 2002, 54: 539\u2013547. 10.1007\/s00239-001-0054-5","journal-title":"J Mol Evol"},{"key":"2626_CR7","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1101\/gr.176501","volume":"12","author":"B Snel","year":"2002","unstructured":"Snel B, Bork P, Huynen MA: Genomes in flux: the evolution of archaeal and proteobacterial gene content. Genome Research 2002, 12: 17\u201325. 10.1101\/gr.176501","journal-title":"Genome Research"},{"key":"2626_CR8","doi-asserted-by":"publisher","first-page":"2122","DOI":"10.1093\/bioinformatics\/btg295","volume":"19","author":"HH Otu","year":"2003","unstructured":"Otu HH, Sayood K: A new sequence distance measure for phylogenetic tree construction. Bioinformatics 2003, 19: 2122\u201330. 10.1093\/bioinformatics\/btg295","journal-title":"Bioinformatics"},{"key":"2626_CR9","doi-asserted-by":"publisher","first-page":"048702","DOI":"10.1103\/PhysRevLett.88.048702","volume":"88","author":"D Benedetto","year":"2002","unstructured":"Benedetto D, Caglioti E, Loreto V: Language trees and zipping. Physical Review Letters 2002, 88: 048702. 10.1103\/PhysRevLett.88.048702","journal-title":"Physical Review Letters"},{"key":"2626_CR10","first-page":"107","volume-title":"Proceedings of the Sixth Annual International Computing and Combinatorics Conference (RECOMB)","author":"X Chen","year":"2000","unstructured":"Chen X, Kwong S, Li M: A compression algorithm for DNA sequences and its applications in genome comparison. In Proceedings of the Sixth Annual International Computing and Combinatorics Conference (RECOMB). ACM Press; 2000:107\u2013117."},{"key":"2626_CR11","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1093\/bioinformatics\/17.2.149","volume":"17","author":"M Li","year":"2001","unstructured":"Li M, Badger JH, Chen X, Kwong S, Kearney P, Zhang H: An information-based sequence distance and its application to whole mitochondrial genome phylogeny. Bioinformatics 2001, 17: 149\u2013154. 10.1093\/bioinformatics\/17.2.149","journal-title":"Bioinformatics"},{"key":"2626_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1142\/S0219720004000442","volume":"2","author":"B Hao","year":"2004","unstructured":"Hao B, Qi J: Prokaryote phylogeny without sequence alignment: from avoidance signature to composition distance. J Bioinform Comput Biol 2004, 2: 1\u201319. 10.1142\/S0219720004000442","journal-title":"J Bioinform Comput Biol"},{"key":"2626_CR13","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1007\/s00239-004-0255-9","volume":"60","author":"ZG Yu","year":"2005","unstructured":"Yu ZG, Zhou LQ, Anh VV, Chu KH, Long SC, Deng JQ: Phylogeny of prokaryotes and chloroplasts revealed by a simple composition approach on all protein sequences from complete genomes without sequence alignment. J Mol Evol 2005, 60: 538\u2013545. 10.1007\/s00239-004-0255-9","journal-title":"J Mol Evol"},{"key":"2626_CR14","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1637\/7625-042706R1.1","volume":"51","author":"XF Wan","year":"2007","unstructured":"Wan XF, Wu X, Lin G, Holton SB, Desmone RA, Shyu CR, Guan Y, Emch ME: Computational identification of reassortments in avian influenza viruses. Avian Dis 2007, 51: 434\u2013439. 10.1637\/7625-042706R1.1","journal-title":"Avian Dis"},{"key":"2626_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00239-003-2493-7","volume":"58","author":"J Qi","year":"2004","unstructured":"Qi J, Wang B, Hao BI: Whole proteome prokaryote phylogeny without sequence alignment: A K -string composition approach. J Mol Evol 2004, 58: 1\u201311. 10.1007\/s00239-003-2493-7","journal-title":"J Mol Evol"},{"key":"2626_CR16","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1504\/IJBRA.2006.010602","volume":"2","author":"X Wu","year":"2006","unstructured":"Wu X, Wan X, Wu G, Xu D, Lin G: Phylogenetic analysis using complete signature information of whole genomes and clustered Neighbour-Joining method. Int J Bioinform Res Appl 2006, 2: 219\u2013248.","journal-title":"Int J Bioinform Res Appl"},{"key":"2626_CR17","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1093\/bioinformatics\/18.1.100","volume":"18","author":"G Stuart","year":"2002","unstructured":"Stuart G, Moffet K, Baker S: Integrated gene and species phylogenies from unaligned whole genome sequence. Bioinformatics 2002, 18: 100\u2013108. 10.1093\/bioinformatics\/18.1.100","journal-title":"Bioinformatics"},{"key":"2626_CR18","doi-asserted-by":"publisher","first-page":"554","DOI":"10.1093\/oxfordjournals.molbev.a004111","volume":"19","author":"G Stuart","year":"2002","unstructured":"Stuart G, Moffet K, Leader J: A comprehensive vertebrate phylogeny using vector representation of protein sequences from whole genomes. Mol Biol Evol 2002, 19: 554\u2013562.","journal-title":"Mol Biol Evol"},{"key":"2626_CR19","doi-asserted-by":"publisher","first-page":"1744","DOI":"10.1093\/bioinformatics\/btm248","volume":"23","author":"X Wu","year":"2007","unstructured":"Wu X, Cai Z, Wan X, Hoang T, Goebel R, Lin G: Nucleotide composition string selection in HIV-1 subtyping using whole genomes. Bioinformatics 2007, 23: 1744\u20131752. 10.1093\/bioinformatics\/btm248","journal-title":"Bioinformatics"},{"key":"2626_CR20","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1080\/07391102.1986.10507643","volume":"4","author":"V Brendel","year":"1986","unstructured":"Brendel V, Beckmann JS, Trifonov EN: Linguistics of nucleotide sequences: Morphology and comparison of vocabularies. J Biomol Struct Dyn 1986, 4: 11\u201321.","journal-title":"J Biomol Struct Dyn"},{"key":"2626_CR21","doi-asserted-by":"publisher","first-page":"35","DOI":"10.2307\/2532033","volume":"45","author":"JF Gentleman","year":"1989","unstructured":"Gentleman JF, Mullin RC: The distribution of the frequency of occurrence of nucleotide subsequence, based on their overlap capability. Biometrics 1989, 45: 35\u201352. 10.2307\/2532033","journal-title":"Biometrics"},{"key":"2626_CR22","doi-asserted-by":"publisher","first-page":"1431","DOI":"10.2307\/2533509","volume":"53","author":"TJ Wu","year":"1997","unstructured":"Wu TJ, Burke JP, Davison DB: A measure of DNA sequence dissimilarity based on Mahalanobis distance between frequencies of words. Biometrics 1997, 53: 1431\u20131439. 10.2307\/2533509","journal-title":"Biometrics"},{"key":"2626_CR23","volume-title":"Options for the Control of Influenza VI","author":"S Zhang","year":"2007","unstructured":"Zhang S, Fang X, Davis T, Ruben D, Lu G: Multidimensional scaling and model-based clustering analyses for the clade assignments of the HPAI H5N1 viruses. In Options for the Control of Influenza VI. London. Blackwell; 2007:in press."},{"key":"2626_CR24","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1093\/nar\/10.1.375","volume":"10","author":"RD Sege","year":"1982","unstructured":"Sege RD, Saxberg BEH: A statistical test for comparing several nucleotide sequences. Nucleic Acids Research 1982, 10: 375\u2013389. 10.1093\/nar\/10.1.375","journal-title":"Nucleic Acids Research"},{"key":"2626_CR25","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1214\/aos\/1176347615","volume":"18","author":"R Arritia","year":"1990","unstructured":"Arritia R, Gordon L, Waterman WS: The Erd\u00f6s-R\u00e9nyi law in distribution, for coin tossing and sequence matching. Annals of Statistics 1990, 18: 539\u2013570. 10.1214\/aos\/1176347615","journal-title":"Annals of Statistics"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-9-S6-S15.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1471-2105-9-S6-S15\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1471-2105-9-S6-S15.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,1,22]],"date-time":"2019-01-22T03:42:47Z","timestamp":1548128567000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/1471-2105-9-S6-S15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,5,28]]},"references-count":25,"journal-issue":{"issue":"S6","published-print":{"date-parts":[[2008,12]]}},"alternative-id":["2626"],"URL":"https:\/\/doi.org\/10.1186\/1471-2105-9-s6-s15","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2008,5,28]]},"article-number":"S15"}}