Identification of eukaryotic exons using empirical mode decomposition and modified Gabor-wavelet transform

Identifying exons in eukaryotes is an important topic in computational biology. In this paper, according to the three-base periodicity of eukaryotic exons, a model-independent method based on the empirical mode decomposition and the modified Gabor-wavelet transform has been developed for identifying exons in DNA sequences of eukaryotes. This novel technique is aimed particularly at detecting the significant components of short exons that are rarely observed with the traditional methods, and presents the advantage of noise suppression in the identification of exons. By using this method, the numerical DNA sequence represented by DNA-bending stiffness scheme is firstly decomposed by empirical mode decomposition into a collection of intrinsic mode functions. Then the first intrinsic mode function is used to compute the local spectrum by modified Gabor-wavelet transform. The performance of the proposed method is compared with two existing model-independent methods by using eukaryote data sets. Experimental results show that the proposed method outperforms the two assessed methods with respect to identification accuracy.