International Conference on Computer and Knowledge Engineering

Home / 11th International Conference on Computer and Knowledge Engineering

Identifying novel disease genes based on protein complexes and biological features

Authors :

Mahshad Hashemi¹ Eghbal Mansoori²

1- Shiraz university 2- Shiraz university

Keywords :

Disease Gene Identification, Protein Complexes, RWR, Heterogeneous Network

Abstract :

Humans are vulnerable to diseases with different origins. Some of them are caused by microorganisms such as viruses and bacteria, environmental conditions, and, most importantly, genetics. Because the majority of diseases are produced by the genes of a certain living organism, it is vital to examine the genetic traits in order to properly treat the condition. Normally, they are caused by genes that are related physically and functionally. Diseases that are phenotypically similar are known to have the same biological characteristics. Therefore, protein complexes, which are collections of proteins that interact with each other to perform biological functions, play a crucial role in prioritizing disease genes. In this paper, a multi-layer heterogeneous network was built, with a phenotype network in the first layer, a protein complex network in the second layer, and a protein interaction network in the last layer. The Random Walk with Restart (RWR) method was applied to the proposed network to prioritize and identify the disease genes. The experimental results show that the proposed method has reasonable performance when compared to various prominent disease gene identification methods.