Gene based disease prediction using pattern similarity based classification

Abstract

In today’s biology research in a single experiment scientist can simultaneously measure the expression of levels of thousands of genes. The molecular level of the cell is represented in gene expression profile. And it helps for medical diagnosis tools. For addressing the fundamental harms which helps to diagnosis and discovery gene expression data along with diseases classification is included. Monitoring of large number of gene expressions is possible because of this DNAmicroarray technique. Using this large quantity of gene data, experts are trying to find the probability of disease classification using gene expression dataset. Number of technique has been formed with comfortable results over these years. Still there are issues which need to be address and understood. To overcome this disease classification difficulty, it is required to review at the problem, the related issues and proposed solutions together. This paper presents a comprehensive clustering method and classification method such as Partial Swarm Optimization algorithm, K-NN classification algGene Based Disease Prediction using Pattern Similarity Based Classification algorithm and estimate them based on their classification accuracy, evaluation time and to reveal biological information about genes. Based on our multiclass classification method to diagnosis the diseases and also find severity levels of diseases. Our experimental results show that proposed semi supervised classifier performance improved in accuracy percentage.