A statistical approach for 5′ splice site prediction using short sequence motifs and without encoding sequence data

Abstract

BackgroundMost of the approaches for splice site prediction are based on machine learning techniques. Though, these approaches provide high prediction accuracy, the window lengths used are longer in size. Hence, these approaches may not be suitable to predict the novel splice variants using the short sequence reads generated from next generation sequencing technologies. Further, machine learning techniques require numerically encoded data and produce different accuracy with different encoding procedures. Therefore, splice site prediction with short sequence motifs and without encoding sequence data became a motivation for the present study.ResultsAn approach for finding association among nucleotide bases in the splice site motifs is developed and used further to determine the appropriate window size. Besides, an approach for prediction of donor splice sites using sum of absolute error criterion has also been proposed. The proposed approach has been compared with commonly used approaches i.e., Maximum Entropy Modeling (MEM), Maximal Dependency Decomposition (MDD), Weighted Matrix Method (WMM) and Markov Model of first order (MM1) and was found to perform equally with MEM and MDD and better than WMM and MM1 in terms of prediction accuracy.ConclusionsThe proposed prediction approach can be used in the prediction of donor splice sites with higher accuracy using short sequence motifs and hence can be used as a complementary method to the existing approaches. Based on the proposed methodology, a web server was also developed for easy prediction of donor splice sites by users and is available at http://cabgrid.res.in:8080/sspred.Electronic supplementary materialThe online version of this article (doi:10.1186/s12859-014-0362-6) contains supplementary material, which is available to authorized users.

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

“…This dataset is a compilation of human splice sites extracted from 269 genes that was used in various studies as benchmark dataset (Baten et al 2008;Li et el. 2012;Golam Bari et al 2014;Meher et al 2014b). The NN269 dataset consists of 1324 TSS and 4922 FSS, where each sequence is of 15bp long having conserved GT at 8 th and 9 th positions respectively.…”

“…However, the TSS and FSS sequences occurring in nature are not completely distinct from each other. Therefore, there should be similarity between the sequences of TSS and FSS to judge the actual predictive ability of the prediction method (Meher et al 2014b). Thus, a similarity search was performed to analyze the sequence distribution,…”

“…Meher et al (2014b). Sixteen error matrices (without diagonal element because of i≠j) corresponding to s×t ={AA, AT, AG, AC, …, GG, GC} are possible both for TSS and FSS dataset separately.2.5.…”

A systems genomics approach to uncover patient-specific pathogenic pathways and proteins in a complex disease

“…Functional miRNA-TS-s have been found in open reading frames including exonic and intronic regions as well as in the 5' untranslated regions [12][13][14][15] . There are a multitude of predictive algorithms for the identification of splicing enhancer or silencing sites [16][17][18] , or motifs for lncRNA binding [19][20][21][22] , however in this study we focused on two regulatory effects as examples; SNPs occurring in transcription factors binding sites and in miRNA target sites.…”

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

“…Since the performance of the SVM-based methods largely depends on DNA encoding method, there are some works to effectively encode DNA for feature extraction [12], [13], [14], [15]. Another approach for prediction splice sites is statistical analysis, recently a statistical method is presented for the prediction of donor splice sites, which is based on dinucleotide dependencies at all possible positions [16].…”