Two Methods for Improving Performance of a HMM and their Application for Gene Finding
Proceedings of the 5th International Conference on Intelligent Systems for Molecular Biology
Isochores merit the prefix 'iso'
Computational Biology and Chemistry
Hi-index | 0.00 |
Hidden Markov models (HMMs) are effective tools to detect series of statistically homogeneous structures, but they are not well suited to analyse complex structures such as DNA sequences. Numerous methodological difficulties are encountered when using HMMs to model non geometric distribution such as exons length, to segregate genes from transposons or retroviruses, or to determine the isochore classes of genes. The aim of this paper is to suggest new tools for the exploration of genome data. We show that HMMs can be used to analyse complex gene structures with bell-shaped length distribution by introducing macros-states. Our HMMs methods take into account many biological properties and were developped to model the isochore organisation of the chimpanzee genome which is considered as a fondamental level of genome organisation. A clear isochore structure in the chimpanzee genome, correlated with the gene density and guanine-cytosine content, has been identified.