Predicting Protein Coding Regions by Six-Base Nucleotide Distribution

Identification of protein coding regions in genomic sequences is a significant problem in bioinformatics. A significant number of techniques for identifying coding regions in genomic sequences are based on Fourier representation for the sequence of nucleotides and spectral analysis methods in order to detect protein coding regions. These methods usually consider 3-base periodicity signal. In this paper, we propose a method that analyzes the distribution of nucleotides at six positions (hexamer distribution). We present the six-base nucleotide distribution (SBND) algorithm and implementation results on genomic sequences of Drosophila Melanogaster, Rat, Cow and also from H. sapiens. The performance is compared with one of the best methods available in the literature and the results establish the viability of the proposed approach.