High-accuracy splice site prediction based on sequence component and position features

Abstract

ABSTRACT. Identification of splice sites plays a key role in the annotation of genes. Consequently, improvement of computational prediction of splice sites would be very useful. We examined the effect of the window size and the number and position of the consensus bases with a chi-square test, and then extracted the sequence multi-scale component features and the position and adjacent position relationship features of consensus sites. Then, we constructed a novel classification model using a support vector machine with the previously selected features and applied it to the Homo sapiens splice site dataset. This method greatly improved cross-validation accuracies for training sets with true and spurious splice sites of both equal and different proportions. This method was also applied to the NN269 dataset for further evaluation and independent testing. The results were superior to those obtained with previous methods, and demonstrate the stability and superiority of this method for prediction of splice sites.

A computational approach for prediction of donor splice sites with improved accuracy

“…For the present study, 2796 TSS (http:// www.sci.unisannio.it/docenti/rampone/EI_true.zip) and 90924 FSS sequences (http:// www.sci.unisannio.it/docenti/rampone/EI_false_1.zip) are considered, where each sequence is of 140bp long (70bp on the exon end terminus and 70bp at the beginning of intron) with conserved GT at 71 st and 72 nd positions respectively. This dataset has also been used in earlier studies (Li et al 2012;Wei et al 2013). …”

“…Furthermore, the amount of false splice sites in a genomic sequence is so enormous that even a subtle improvement in prediction accuracy could drastically influence the absolute large number of pseudo-sites in predicted results (Li et al 2012). Therefore, it is required to envisage new approach(s) to predict splice sites with higher accuracy.…”

Analysis of Effect of the Position on Weighted Degree Kernel for Splice Site Prediction

“…Owing to the tremendous increase in genomic sequence data, there is an urgent demand to improve the efficiency of computational algorithms for gene annotation [1]. The accurate prediction of splice sites plays a key role in the annotation of genes in eukaryotes [2].…”

Evaluating the Accuracy of Splice Site Prediction based on Integrating Jensen-Shannon Divergence and a Polynomial Equation of Order 2

“…Position weight matrix (PWM) is a common model for splice site prediction [2], [3], [4]. The varieties of PWMs have been used for splice site prediction such as Weight Array Models [5] and Windowed Weight Array Model [6].…”

“…These methods use the complex non-linear transformation and learn the complex features of locality surrounding of the consensus AG/GT dinucleotides [7], [8]. Support vector machine is another method for splice site prediction [3]. Most of the splice site detection methods focus on the improvement of classification performance [9], [10].…”