Inferring an organism-specific optimal threshold for predicting protein coding regions in eukaryotes based on a bootstrapping algorithm

Abstract

The accuracy of prediction methods based on power spectrum analysis depends on the threshold that is used to discriminate between protein coding and non-coding sequences in the genomes of eukaryotes. Because the structure of genes vary among different eukaryotes, it is difficult to determine the best prediction threshold for a eukaryote relying only on prior biological knowledge. To improve the accuracy of prediction methods based on power spectral analysis, we developed a novel method based on a bootstrap algorithm to infer organism-specific optimal thresholds for eukaryotes. As prior information, our method requires the input of only a few annotated protein coding regions from the organism being studied. Our results show that using the calculated optimal thresholds for our test datasets, the average prediction accuracy of our method is 81%, an increase of 19% over that obtained using the same empirical threshold P=4 for all datasets. The proposed method is simple and convenient and easily applied to infer optimal thresholds that can be used to predict coding regions in the genomes of most organisms.

Identification of Protein Coding Regions in the Eukaryotic DNA Sequences Based on Marple Algorithm and Wavelet Packets Transform

“…Compute wavelet packet reconstruction based on the original approximation coefficients at level and the modified coefficients. [28,53] developed a novel method based on the bootstrap algorithm and Rao's sliding window strategy [20] to infer organism-specific optimal thresholds for different eukaryotes, and this integrate algorithm has improved the prediction accuracy than the conventional universal threshold based methods. In this paper, we use the threshold selection method developed by Kwan et al [29,54].…”

“…is a widely used compound measure which considers both sides of and from the global perspective [28].…”

“…So parametric spectrum methods such as AR modeling were developed for detection of coding regions in small DNA sequences [15,[23][24][25][26][27]. And AR modeling has been proved to be able to produce stronger PSD and weaker artifacts than DFT-based methods [26][27][28], especially performing well in finding the small size coding regions. In this paper, a novel technique based on Marple algorithm of AR PSD and wavelet packets transform is presented to identify the protein coding regions in eukaryotic DNA sequences.…”