Computer intelligence spots genes linked to Duchenne Muscular Dystrophy
Thursday, March 16, 2017
Using computational intelligence, researchers have identified a set of genes that are "collectively responsible" for Duchenne Muscular Dystrophy (DMD), a genetic disease causing progressive decay in muscles.
Surama Biswas and Sriyankar Acharyya, both from the Department of Computer Science and Engineering, Maulana Abul Kalam Azad University of Technology, West Bengal, mined a dataset of around 50,000 genes to obtain a sub-set containing 30 genes.
"The sub-set containing 30 genes are collectively discriminant in gene expression between DMD affected patients and normal persons. This means that although these genes are present in both affected and normal people, the way the instructions encoded in these genes are used to synthesise gene products (usually proteins), are different in the two categories of people," Biswas told IANS on Thursday.
The genes identified may be clinically investigated to design new drugs and/or modify existing drugs for DMD, Biswas said.
To hunt for the genes in a reasonable amount of time, two algorithms were devised based on existing meta-heuristic algorithms.
Meta-heuristic aims to find good or near-optimal solutions at a reasonable computational cost and time.
DMD affects about one in 5,000 males at birth. It is the most common type of muscular dystrophy. Lack of or defect in muscle cell structural proteins is the basic cause of muscular dystrophy.
Although a gene called DMD has previously been identified, Biswas said the disease is triggered by a collection of all the genes.
Explaining their motivation for the study, Biswas said: "DMD may affect a boy of the age group 3-5 years. DMD initially affects the muscles of limbs causing gradual decay and hampers mobility. Finally it harms the muscles of major organs which leads to death. Application of computational intelligence / soft computing in healthcare of women and kids is the thrust area of our research group."
"Shortage/unavailability of data is always a limitation for computational research. More methods and datasets may always be employed for validating the research," Biswas added.
The study is available in Springer's Computer Society of India (CSI) transactions on ICT (information and communication technology) journal for March issue (volume 5).
s