Browsing by Author "Sathyavikasini, K"

Now showing 1 - 3 of 3

ENSEMBLE LEARNING FOR IDENTIFYING MUSCULAR DYSTROPHY DISEASES USING CODON BIAS PATTERN
(Springer Link, 2017-03-17) Sathyavikasini, K; Vijaya, M S
Hereditary traits are anticipated by the mutations in the gene sequences. Identifying a disease based on mutations is an essential and challenging task in the determination of genetic disorders such as Muscular dystrophy. Silent mutation is a single nucleotide variant does not result in changes in the encoded protein but appear in the variation of codon usage pattern that results in disease. A new ensemble learning-based computational model is proposed using the synonymous codon usage for identifying the muscular dystrophy disease. The feature vector is designed by calculating the Relative Synonymous Codon Usage (RSCU) values from the mutated gene sequences and a model is built by adopting codon usage bias pattern. 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. Finally, a model is built based on ensemble learning LibD3C algorithm to recognize muscular dystrophy disease classification. Experiments showed that the accuracy of the classifier shows 90%, which proves that ensemble-based learning, is effective for predicting muscular dystrophy disease.
IDENTIFICATION OF RARE GENETIC DISORDER FROM SINGLE NUCLEOTIDE VARIANTS USING SUPERVISED LEARNING TECHNIQUE
(Institute of Advanced Engineering and Science (IAES), 2016) Sathyavikasini, K; Vijaya, M S
Muscular dystrophy is a rare genetic disorder that affects the muscular system which deteriorates the skeletal muscles and hinders locomotion. In the finding of genetic disorders such as Muscular dystrophy, the disease is identified based on mutations in the gene sequence. A new model is proposed for classifying the disease accurately using gene sequences, mutated by adopting positional cloning on the reference cDNA sequence. The features of mutated gene sequences for missense, nonsense and silent mutations aims in distinguishing the type of disease and the classifiers are trained with commonly used supervised pattern learning techniques.10-fold cross validation results show that the decision tree algorithm was found to attain the best accuracy of 100%. In summary, this study provides an automatic model to classify the muscular dystrophy disease and shed a new light on predicting the genetic disorder from gene based features through pattern recognition model.
PREDICTING MUSCULAR DYSTROPHY WITH SEQUENCE BASED FEATURES FOR POINT MUTATIONS
(IEEE, 2016-03-17) Sathyavikasini, K; Vijaya, M S
Hefty amounts of biological data are accumulated for research with the advancement of sequencing technologies. Genetic diseases are caused by the deformity in the inherited genes. Identifying trait diseases through DNA analysis is a prime task in diagnosing an ailment. Identification of disease based on mutations in the gene sequences is an essential and challenging task in the medical diagnosis of genetic disorders such as Muscular dystrophy. Muscular dystrophy is a rare disease that alters the structure and nature of the muscles that deteriorate the musculoskeletal system and hinder locomotion. There are nine major kinds of muscular dystrophy and it is vital to identify the type of muscular dystrophy for proper diagnosis and treatment. Hence a new model is proposed for predicting the disease accurately with the gene sequences, which are mutated by adopting an approach like positional cloning on the reference cDNA sequence. This paper addresses the problem by considering mutated gene sequences of fifty five genes that causes five types of muscular dystrophy and developing an efficient pattern recognition model using supervised pattern classification technique. The resultant the trained model shows the prediction accuracy of 100% by estimating using 10-fold cross validation.