Asian Journal of Information Technology
ISSN: Online 1993-5994ISSN: Print 1682-3915
Abstract
In the recent genomic epoch, the recognition of the genetic diseases is paramount. It is a convoluted task to recognize a heritable disease that is certainly caused by genetic mutations. Identification of disease based on mutations in the gene sequences is an important and challenging task in the medical diagnosis of genetic disorders. This study addresses this problem by developing new model by extracting mutational features as discriminative descriptors for predicting the disease accurately. The disease gene sequences are mutated by espousing a technique like positional cloning on the reference cDNA sequence. A rare genetic disorder such as muscular dystrophy is taken as a sample for this research. This disease is a complicated neuromuscular ailment with a prominent social impact that impairs the working of the locomotive muscle tissues. The versatile causes of this disease bring about the requirement of new hereditary patterns that can diagnose patients using biological information. There are diverse significant forms of muscular dystrophy and it is imperative to identify the type of muscular dystrophy for proper medical diagnosis and medication. Hence, a data driven model is developed using pattern recognition techniques by aggregating the features related to all kinds of mutations for predicting the disease precisely. Results indicate that the SVM classifier is found to acquire the best accuracy of 90.5% for predicting muscular dystrophy.
How to cite this article:
Sathyavikasini Kalimuthu and Vijaya Vijayakumar. Data Driven Approach for Genetic Disorder Prediction by
Aggregating Mutational Features.
DOI: https://doi.org/10.36478/ajit.2017.675.685
URL: https://www.makhillpublications.co/view-article/1682-3915/ajit.2017.675.685