Machine-Learning-Based Taxonomical Approach to Predict Circular RNA

Abstract

Machine-learning approach is a good alternative for big-data analytics with high accuracy. Circular RNA plays a major role in development of many diseases such as diabetes, heart failure, osteoarthritis, Alzheimer, cancer, etc. Several circular RNA detection techniques have been developed. In this paper, we provide machine-learning-based taxonomical technique to predict circular RNA sequences from RNA Sequences. Here, we compared various types of circular RNA detection techniques with their performance regarding the metrics such as specificity, sensitivity, accuracy, MCC and precision. Among all of these comparison methods, it is concluded that none of the metrics were dominated.