Construction of reliable heterogeneous network using protein sequence similarity for the prioritization of candidate disease genes

Identifying candidate disease genes are significant to improve medical care. In previous research works the Random walk with restart and diffusion profile (RWRDP) and Random walk-based algorithm on the reliable heterogeneous network (RWRHN) were used to prioritize the candidate disease genes. The topological and phenotype similarity was used to predict the candidate disease gene in the existing systems. But this similarity measure does not predict the candidate disease gene effectively. To overcome these difficulties the existing algorithms have been improved to predict the candidate disease genes. In order to improve the performance measure and reduce the prediction error, Random walk-based algorithm on the reliable heterogeneous network-Piecewise linear regression-protein sequence similarity (RWRHN-PLR-SS) is introduced. Then the candidate diseases genes are ranked. Finally RWRHN-PLR-SS is used to predict novel causal genes for 20 diseases, including breast cancer, diabetes mellitus type 2, Cancer and Prostate cancer, Alzheimer disease, Atrial fibrillation as well as to detect disease-related protein complexes. The experimental results show that the proposed algorithms achieve higher performance compared with the existing and the other proposed algorithms.