Computational approaches for disease gene identification

Abstract

Identifying disease genes from the human genome is a crucial but challenging task in the area of bioinformatics research and medical health. In wet-lab experiments, disease genes are identified using mutation analysis, which is very expensive and labor intensive. In this thesis, we proposed novel computational approaches to prioritize and identify disease genes. The experimental results show that our work is more robust and accurate than other state-of-the-the-art techniques for disease gene identification.