Abstract—Genetic diseases are predictable by the mutations in the gene sequences. Predicting a disease based on mutations is an important and challenging task in the medical diagnosis of genetic disorders such as Muscular dystrophy. Currently, this problem is handled for non-synonymous single nucleotide variants (SNVs) that capture only missense and nonsense mutations. Silent mutations do not result in changes in the encoded protein, but appear in the variation of codon usage pattern that results in disease. Hence, a new computational model is proposed for recognizing the disease using synonymous codon usage. The model adopts codon usage bias pattern as a feature vector by calculating the Relative Synonymous Codon Usage (RSCU) values from the mutated gene sequences. This paper addresses the problem by formulating it as multi- classification trained with feature vectors of fifty-nine RSCU frequency values from the mutated gene sequences. The outcome of trained model reports that the prediction accuracy of 86% in multi-class SVM with the RBF kernel.
Index Terms—Codon, codon usage bias, positional cloning, RSCU, silent mutations.
The authors are with the PSGR Krishnammal College for Women, Coimbatore, Tamil Nadu, India (e-mail: mail2sathyavikashini@gmail.com, msvijaya@psgrkc.com).
Cite: K. Sathyavikasini and M. S. Vijaya, "Muscular Dystrophy Disease Classification Using Relative Synonymous Codon Usage," International Journal of Machine Learning and Computing vol.6, no. 2, pp. 139-144, 2016.