A computational approach for prediction of donor splice sites with improved accuracy. (7th September 2016)

• Record Type: Journal Article
• Authors: Meher, Prabina Kumar; Sahu, Tanmaya Kumar; Rao, A.R.; Wahi, S.D.
• Is Part Of: Journal of theoretical biology. Volume 404(2016)
• Page Start: 285
• Page End: 294
• Publication Date: 2016-09-07
• Subjects: WMM Weighted Matrix Method -- MLAs Machine Learning Approaches -- ANNs Artificial Neural Networks -- SVM Support Vector Machine -- TSS True Splice Site -- FSS False Splice Site -- HS3d Homo Sapiens Splice Site Dataset -- bp base pairs -- MEM Maximum Entropy Model -- MDD Maximal Dependency Decomposition -- MM1 Markov Model of first order -- ROC Receiving Operating Characteristics -- AUC- ROC Area Under ROC Curve -- SE Standard Error -- PR Precision-Recall -- AUC-PR Area Under PR curve -- PWM Position Weight Matrix; Machine learning -- PreDOSS -- Sequence encoding -- Di-nucleotide dependency -- Conditional error; Biology -- Periodicals; Biological Science Disciplines -- Periodicals; Biology -- Periodicals; Biologie -- Périodiques; Theoretische biologie; Biology; Periodicals; 571.05
• DOI: 10.1016/j.jtbi.2016.06.013
• Languages: English
• ISSNs: 0022-5193

Abstract

Abstract: Identification of splice sites is important due to their key role in predicting the exon-intron structure of protein coding genes. Though several approaches have been developed for the prediction of splice sites, further improvement in the prediction accuracy will help predict gene structure more accurately. This paper presents a computational approach for prediction of donor splice sites with higher accuracy. In this approach, true and false splice sites were first encoded into numeric vectors and then used as input in artificial neural network (ANN), support vector machine (SVM) and random forest (RF) for prediction. ANN and SVM were found to perform equally and better than RF, while tested on HS3D and NN269 datasets. Further, the performance of ANN, SVM and RF were analyzed by using an independent test set of 50 genes and found that the prediction accuracy of ANN was higher than that of SVM and RF. All the predictors achieved higher accuracy while compared with the existing methods like NNsplice, MEM, MDD, WMM, MM1, FSPLICE, GeneID and ASSP, using the independent test set. We have also developed an online prediction server (PreDOSS) available athttp://cabgrid.res.in:8080/predoss, for prediction of donor splice sites using the proposed approach. Highlights: We have proposed an approach for prediction of donor splice sites. The developed approach achieved higher accuracy than several existing approaches. Proposed approach will supplement the existing methods for predicting splice sites. An online server PreDOSS has been developed for predicting donor splice sites easily.