A survey on machine learning approaches in gene expression classification in modelling computational diagnostic system for complex diseases

Abstract

In recent days, the survivability of people around the world has increased in a higher rate. The notable reason is the impact of the evolution of new technologies in medical systems that are invented to provide and improve healthcare for peoples. But still, there are some diseases, which may be identified also can be controlled. But there isn’t any permanent solution for them such as cancer, psychiatric disorders etc. For those diseases, medical practitioners finds some way to discover medicine by analyzing the patient’s genetic information such as DNA. Microarray technology is helpful in capturing biological genetic information to computer data. Computational techniques can be applied on those large set of genetic data of every individuals with or without disease, so that the genes that are responsible for the disease occurrence can be pointed out. Differentially Expressed Genes (DEG) are identified using many techniques. Machine Learning (ML) algorithms plays a significant role in identifying the distinction between normal genes and unhealthy genes, extracted from human genome. This paper is focusing on providing an in depth overview on different techniques on ML that are used to analyze and classifies the gene expression profiles of various diseases are discussed.