{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T12:11:23Z","timestamp":1762603883985},"reference-count":36,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2013,10,3]],"date-time":"2013-10-03T00:00:00Z","timestamp":1380758400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"DOI":"10.1371\/journal.pcbi.1003234","type":"journal-article","created":{"date-parts":[[2013,10,3]],"date-time":"2013-10-03T21:12:00Z","timestamp":1380834720000},"page":"e1003234","update-policy":"http:\/\/dx.doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":6,"title":["ToPS: A Framework to Manipulate Probabilistic Models of Sequence Data"],"prefix":"10.1371","volume":"9","author":[{"given":"Andr\u00e9 Yoshiaki","family":"Kashiwabara","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"\u00cdgor","family":"Bonadio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vitor","family":"Onuchic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felipe","family":"Amado","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rafael","family":"Mathias","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alan Mitchell","family":"Durham","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2013,10,3]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1038\/nrg890","article-title":"Computational prediction of eukaryotic protein-coding genes","volume":"3","author":"MQ Zhang","year":"2002","journal-title":"Nat Rev Genet"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1093\/biostatistics\/kxq005","article-title":"Redefining CpG islands using hidden Markov models","volume":"1","author":"HAO Wu","year":"2010","journal-title":"Biostat"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"D290","DOI":"10.1093\/nar\/gkr1065","article-title":"The Pfam protein families database","volume":"40","author":"M Punta","year":"2012","journal-title":"Nucleic acids research"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1016\/j.jmb.2003.08.015","article-title":"Sequence Alignments and Pair Hidden Markov Models Using Evolutionary History","volume":"333","author":"B Knudsen","year":"2003","journal-title":"Journal of Molecular Biology"},{"key":"ref5","unstructured":"R Development Core Team (2009) R: A Language and Environment for Statistical Computing. Vienna, Austria: R Foundation for Statistical Computing."},{"key":"ref6","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1198\/1061860043524","article-title":"Variable length Markov chains: Methodology, Computing, and Software","volume":"13","author":"M Machler","year":"2004","journal-title":"Journal of Computational & Graphical Statistics"},{"key":"ref7","unstructured":"Harte D (2008) Reference manual package: HiddenMarkov. Wellington, New Zealand: Statistics Research Associates Limited."},{"key":"ref8","first-page":"121","article-title":"The General Hidden Markov Model Library: Analyzing Systems with Unobservable States","volume":"2004","author":"A Schliep","year":"2004","journal-title":"Proceedings of the Heinz-Billing-Price"},{"key":"ref9","unstructured":"Young S, Evermann G, Gales M, Hain T, Kershaw D, <etal>et al<\/etal>.. (2006) The HTK Book (for HTK Version 3.4). Cambridge: Cambridge University Engineering Department. 359 p."},{"key":"ref10","doi-asserted-by":"crossref","first-page":"2485","DOI":"10.1093\/bioinformatics\/btm350","article-title":"HMMoC \u2013 a compiler for hidden Markov models","volume":"23","author":"G Lunter","year":"2007","journal-title":"Bioinformatics"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"e139","DOI":"10.1093\/nar\/gkp662","article-title":"HMMCONVERTER 1.0: a toolbox for hidden Markov models","volume":"37","author":"TY Lam","year":"2009","journal-title":"Nucleic acids research"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"S140","DOI":"10.1093\/bioinformatics\/17.suppl_1.S140","article-title":"Integrating genomic homology into gene structure prediction","volume":"17","author":"I Korf","year":"2001","journal-title":"Bioinformatics"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"2878","DOI":"10.1093\/bioinformatics\/bth315","article-title":"TigrScan and GlimmerHMM: two open source ab initio eukaryotic gene-finders","volume":"20","author":"WH Majoros","year":"2004","journal-title":"Bioinformatics"},{"key":"ref14","first-page":"134","article-title":"A generalized hidden Markov model for the recognition of human genes in DNA","volume":"4","author":"D Kulp","year":"1996","journal-title":"Proc Int Conf Intell Syst Mol Biol"},{"key":"ref15","unstructured":"Burge C (1997) Identification of genes in human genomic DNA. [PhD Dissertation] Stanford University."},{"key":"ref16","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 Suppl 2","author":"M Stanke","year":"2003","journal-title":"Bioinformatics"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1109\/TIT.1983.1056741","article-title":"A universal data compression system","volume":"29","author":"J Rissanen","year":"1983","journal-title":"Information Theory, IEEE Transactions on"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1093\/nar\/26.2.544","article-title":"Microbial gene identification using Interpolated Markov Models","volume":"26","author":"S Salzberg","year":"1998","journal-title":"Nucleic Acids Research"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","article-title":"A tutorial on Hidden Markov Models and selected applications in speech recoginition","volume":"77","author":"LR Rabiner","year":"1989","journal-title":"Proccedings of the IEEE"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"755","DOI":"10.1093\/bioinformatics\/14.9.755","article-title":"Profile hidden Markov models","volume":"14","author":"SR Eddy","year":"1998","journal-title":"Bioinformatics"},{"key":"ref21","doi-asserted-by":"crossref","unstructured":"Durbin R, Eddy SR, Krogh A, Mitchison G (1998) Biological sequence analysis: Probabilistic models of proteins and nucleic acids. CambridgeUK: Cambridge University Press. 356 p.","DOI":"10.1017\/CBO9780511790492"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1214\/aos\/1176344136","article-title":"Estimating the dimension of a model","volume":"6","author":"G Schwarz","year":"1978","journal-title":"The Annals of Statistics"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1109\/TAC.1974.1100705","article-title":"A new look at the statistical model identification","volume":"AC-19","author":"H Akaike","year":"1974","journal-title":"IEEE transactions on automatic control"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"S10","DOI":"10.1186\/1471-2164-11-S5-S10","article-title":"Decreasing the number of false positives in sequence classification","volume":"11","author":"A Machado-Lima","year":"2010","journal-title":"BMC genomics"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1089\/cmb.1997.4.311","article-title":"Improved splice site detection in Genie","volume":"4","author":"MG Reese","year":"1997","journal-title":"J Comp Biol"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/S0166-6851(01)00363-2","article-title":"Phat\u2013a gene finding program for plasmodium falciparum","volume":"118","author":"SE Cawley","year":"2001","journal-title":"Mol Biochem Parasitol"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"6494","DOI":"10.1093\/nar\/gki937","article-title":"Gene identification in novel eukaryotic genomes by self-training algorithm","volume":"33","author":"A Lomsadze","year":"2005","journal-title":"Nucleic Acids Res"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"604","DOI":"10.1198\/1061860032030","article-title":"Estimating hidden semi-Markov chains from discrete sequences","volume":"12","author":"Y Gu\u00e9don","year":"2003","journal-title":"Journal of Computational and Graphical Statistics"},{"key":"ref29","doi-asserted-by":"crossref","unstructured":"Majoros W, Status I, Availability L (2007) Methods for Computational Gene Prediction. Cambridge: Cambridge University Press. 430 p.","DOI":"10.1017\/CBO9780511811135"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1101\/gr.229202","article-title":"Blat\u2013the blast-like alignment tool","volume":"12","author":"WJ Kent","year":"2002","journal-title":"Genome Research"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"636","DOI":"10.1126\/science.1105136","article-title":"The ENCODE (ENCyclopedia Of DNA Elements) Project","volume":"306","year":"2004","journal-title":"Science"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"6798","DOI":"10.1093\/nar\/gkm489","article-title":"CG dinucleotide clustering is a species-specific property of the genome","volume":"35","author":"JL Glass","year":"2007","journal-title":"Nucleic acids research"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"D98","DOI":"10.1093\/nar\/gkp1017","article-title":"DBTSS provides a tissue specific dynamic view of Transcription Start Sites","volume":"38","author":"R Yamashita","year":"2010","journal-title":"Nucleic acids research"},{"key":"ref34","doi-asserted-by":"crossref","unstructured":"Stanke M (2003) Gene prediction with a hidden Markov model. [PhD Dissertation] Universit\u00e4t G\u00f6ttingen.","DOI":"10.1093\/bioinformatics\/btg1080"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1186\/1471-2105-4-50","article-title":"Eval: a software package for analysis of genome annotations","volume":"4","author":"E Keibler","year":"2003","journal-title":"BMC Bioinformatics"},{"key":"ref36","unstructured":"Lafferty J, McCallum A, Pereira F (2001) Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In: ICML &apos;01 Proceedings of the Eighteenth International Conference on Machine Learning. pp. 282\u2013289."}],"container-title":["PLoS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pcbi.1003234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,5]],"date-time":"2023-07-05T01:35:39Z","timestamp":1688520939000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1003234"}},"subtitle":[],"editor":[{"given":"Hilmar","family":"Lapp","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2013,10,3]]},"references-count":36,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2013,10,3]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1003234","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,10,3]]}}}