| dc.description.abstract | RNA editing process like Adenosine to Intosine (A-to-I) often influences basic functions like splicing stability and most importantly the translation. Thus knowledge about editing sites is of great importance in molecular biology. With the growth of known editing sites, machine learning or data centric approaches are now being applied to solve this problem of prediction of RNA editing sites. In this paper, we propose EPAI-NC, a novel method for prediction of RNA editing sites. We have used l-mer composition and ngapped l-mer composition as features and used Pearson Correlation Coefficient to select features according to Pareto Principle. Locally deep support vector machines were used to train the classification model of EPAI-NC. EPAI-NC significantly enhances the prediction accuracy compared to the previous state-of-the-art methods when tested on standard benchmark and independent dataset. | en_US |
