{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T02:47:42Z","timestamp":1761965262798,"version":"build-2065373602"},"reference-count":47,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2011,6,30]],"date-time":"2011-06-30T00:00:00Z","timestamp":1309392000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"DOI":"10.1371\/journal.pone.0021588","type":"journal-article","created":{"date-parts":[[2011,6,30]],"date-time":"2011-06-30T20:57:19Z","timestamp":1309467439000},"page":"e21588","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":48,"title":["On the Representability of Complete Genomes by Multiple Competing Finite-Context (Markov) Models"],"prefix":"10.1371","volume":"6","author":[{"given":"Armando J.","family":"Pinho","sequence":"first","affiliation":[]},{"given":"Paulo J. S. G.","family":"Ferreira","sequence":"additional","affiliation":[]},{"given":"Ant\u00f3nio J. R.","family":"Neves","sequence":"additional","affiliation":[]},{"given":"Carlos A. C.","family":"Bastos","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2011,6,30]]},"reference":[{"key":"ref1","first-page":"340","article-title":"Compression of DNA sequences.","author":"S Grumbach","year":"1993"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1109\/DCC.1996.488385","article-title":"A guaranteed compression scheme for repetitive DNA sequences.","author":"E Rivals","year":"1996"},{"key":"ref3","first-page":"151","article-title":"Significantly lower entropy estimates for natural DNA sequences.","author":"D Loewenstern","year":"1997"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/51.940049","article-title":"A compression algorithm for DNA sequences.","volume":"20","author":"X Chen","year":"2001","journal-title":"IEEE Engineering in Medicine and Biology Magazine"},{"key":"ref5","first-page":"253","article-title":"DNA sequence compression using the normalized maximum likelihood model for discrete regression.","author":"I Tabus","year":"2003"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1397","DOI":"10.1002\/spe.619","article-title":"A simple and fast DNA compressor.","volume":"34","author":"G Manzini","year":"2004","journal-title":"Software\u2014Practice and Experience"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1145\/1055709.1055711","article-title":"An efficient normalized maximum likelihood algorithm for DNA sequence compression.","volume":"23","author":"G Korodi","year":"2005","journal-title":"ACM Trans on Information Systems"},{"key":"ref8","first-page":"190","article-title":"DNA compression challenge revisited.","author":"B Behzadi","year":"2005"},{"key":"ref9","first-page":"33","article-title":"Normalized maximum likelihood model of order-1 for the compression of DNA sequences.","author":"G Korodi","year":"2007"},{"key":"ref10","first-page":"43","article-title":"A simple statistical algorithm for biological sequence compression.","author":"MD Cao","year":"2007"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1575","DOI":"10.1093\/bioinformatics\/btp117","article-title":"Textual data compression in computational biology: a synopsis.","volume":"25","author":"R Giancarlo","year":"2009","journal-title":"Bioinformatics"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1109\/TIT.1977.1055714","article-title":"A universal algorithm for sequential data compression.","volume":"23","author":"J Ziv","year":"1977","journal-title":"IEEE Trans on Information Theory"},{"key":"ref13","first-page":"823","article-title":"Statistical patterns in primary structures of the functional regions of the genome in <italic>Escherichia coli<\/italic> : I. Frequency characteristics.","volume":"20","author":"MY Borodovsky","year":"1986","journal-title":"Molecular Biology"},{"key":"ref14","first-page":"833","article-title":"Statistical patterns in primary structures of the functional regions of the genome in <italic>Escherichia coli<\/italic> : II. Nonuniform Markov models.","volume":"20","author":"MY Borodovsky","year":"1986","journal-title":"Molecular Biology"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1007\/BF02458838","article-title":"Codon preference and primary sequence structure in protein-coding regions.","volume":"51","author":"S Tavar\u00e9","year":"1989","journal-title":"Bulletin of Mathematical Biology"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/0097-8485(93)85004-V","article-title":"GENMARK: Parallel gene recognition for both DNA strands.","volume":"17","author":"MY Borodovsky","year":"1993","journal-title":"Computers & Chemistry"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/S0959-440X(98)80069-9","article-title":"Finding the genes in genomic DNA.","volume":"8","author":"CB Burge","year":"1998","journal-title":"Current Opinion in Structural Biology"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1006\/geno.1999.5854","article-title":"Interpolated Markov models for eukaryotic gene finding.","volume":"59","author":"SL Salzberg","year":"1999","journal-title":"Genomics"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"ii215","DOI":"10.1093\/bioinformatics\/btg1080","article-title":"Gene prediction with a hidden Markov model and a new intron submodel.","volume":"19","author":"M Stanke","year":"2003","journal-title":"Bioinformatics"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1093\/bioinformatics\/btm009","article-title":"Identifying bacterial genes and endosymbiont DNA with Glimmer.","volume":"23","author":"AL Delcher","year":"2007","journal-title":"Bioinformatics"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"e132","DOI":"10.1093\/nar\/gkq275","article-title":"<italic>Ab initio<\/italic> gene identification in metagenomic sequences.","volume":"38","author":"W Zhu","year":"2010","journal-title":"Nucleic Acids Research"},{"key":"ref22","article-title":"FragGeneScan: predicting genes in short and error-prone reads.","author":"M Rho","year":"2010","journal-title":"Nucleic Acids Research"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"3669","DOI":"10.1093\/nar\/gkg596","article-title":"SIC: a tool to detect short inverted segments in a biological sequence.","volume":"31","author":"D Robelin","year":"2003","journal-title":"Nucleic Acids Research"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"3679","DOI":"10.1093\/nar\/gkg613","article-title":"SPA: simple web tool to assess statistical significance of DNA patterns.","volume":"31","author":"H Richard","year":"2003","journal-title":"Nucleic Acids Research"},{"key":"ref25","first-page":"47","article-title":"CpG island identification with higher order and variable order Markov models.","author":"Z Liu","year":"2007"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1016\/0005-1098(78)90005-5","article-title":"Modeling by shortest data description.","volume":"14","author":"J Rissanen","year":"1978","journal-title":"Automatica"},{"key":"ref27","first-page":"8","article-title":"Compression of strings with approximate repeats.","author":"L Allison","year":"1998"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"S10","DOI":"10.1186\/1471-2105-8-S2-S10","article-title":"Comparative analysis of long DNA sequences by per element information content using different contexts.","volume":"8","author":"TI Dix","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1186\/1471-2105-8-252","article-title":"Compression-based classification of biological sequences and structures via the universal similarity metric: experimental assessment.","volume":"8","author":"P Ferragina","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1186\/1471-2105-11-599","article-title":"A genome alignment algorithm based on compression.","volume":"11","author":"MD Cao","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1007\/BF02458580","article-title":"Minimum message length encoding and the comparison of macromolecules.","volume":"52","author":"L Allison","year":"1990","journal-title":"Bulletin of Mathematical Biology"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/0097-8485(92)80038-2","article-title":"A maximum entropy principle for the distribution of local complexity in naturally occurring nucleotide sequences.","volume":"16","author":"P Salamon","year":"1992","journal-title":"Computers & Chemistry"},{"key":"ref33","first-page":"407","article-title":"Discovering simple DNA sequences by the algorithmic significance method.","volume":"9","author":"A Milosavljevi\u0107","year":"1993","journal-title":"Computer Applications in the Biosciences"},{"key":"ref34","article-title":"Text compression.","author":"TC Bell","year":"1990","journal-title":"Prentice Hall"},{"article-title":"Data compression - The complete reference.","year":"2007","author":"D Salomon","key":"ref35"},{"article-title":"Introduction to data compression.","year":"2006","author":"K Sayood","key":"ref36"},{"article-title":"Inverted-repeats-aware finite-context models for DNA coding.","year":"2008","author":"AJ Pinho","key":"ref37"},{"key":"ref38","first-page":"370","article-title":"An essay towards solving a problem in the doctrine of chances.","volume":"53","author":"T Bayes","year":"1763","journal-title":"Philosophical Transactions of the Royal Society of London"},{"key":"ref39","first-page":"621","article-title":"M\u00e9moire sur la probabilit\u00e9 des causes par les \u00e9v\u00e9nements.","volume":"6","author":"PS Laplace","year":"1774"},{"article-title":"The logic of chance","year":"1888","author":"J Venn","key":"ref40"},{"article-title":"Letter.","year":"1889","author":"GF Hardy","key":"ref41"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1017\/S0071368600004389","article-title":"On some disputed questions of probability.","volume":"8","author":"ET Whittaker","year":"1920","journal-title":"Trans of the Faculty of Actuaries"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1093\/mind\/XLI.164.409","article-title":"Probability: the deductive and inductive problems.","volume":"XLI","author":"WE Johnson","year":"1932","journal-title":"Mind"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"1091","DOI":"10.1214\/aos\/1176345975","article-title":"W. E. Johnson&apos;s \u201csufficientness\u201d postulate.","volume":"10","author":"SL Zabell","year":"1982","journal-title":"The Annals of Statistics"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1007\/BF01236567","article-title":"The rule of succession.","volume":"31","author":"SL Zabell","year":"1989","journal-title":"Erkenntnis"},{"key":"ref46","first-page":"47","article-title":"Using Dirichlet mixture priors to derive hidden Markov models for protein families.","author":"M Brown","year":"1993"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1093\/bioinformatics\/12.4.327","article-title":"Dirichlet mixtures: a method for improved detection of weak but significant protein sequence homology.","volume":"12","author":"K Sj\u00f6lander","year":"1996","journal-title":"Bioinformatics"}],"container-title":["PLoS ONE"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pone.0021588","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,10,24]],"date-time":"2018-10-24T05:55:40Z","timestamp":1540360540000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0021588"}},"subtitle":[],"editor":[{"given":"Christos A.","family":"Ouzounis","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2011,6,30]]},"references-count":47,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2011,6,30]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0021588","relation":{},"ISSN":["1932-6203"],"issn-type":[{"type":"electronic","value":"1932-6203"}],"subject":[],"published":{"date-parts":[[2011,6,30]]}}}