Table of Contents Author Guidelines Submit a Manuscript
The Scientific World Journal
Volume 2013, Article ID 393570, 7 pages
Research Article

A Robust Hybrid Approach Based on Estimation of Distribution Algorithm and Support Vector Machine for Hunting Candidate Disease Genes

1Devision of Medical Genetics, Tongji University School of Medicine, Shanghai 200092, China
2Key Lab for Basic Research in Cardiology, Ministry of Education, Tongji University, Shanghai 200092, China

Received 23 October 2012; Accepted 25 November 2012

Academic Editors: R. Jiang, W. Tian, J. Wan, and X. Zhao

Copyright © 2013 Li Li et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


Microarray data are high dimension with high noise ratio and relatively small sample size, which makes it a challenge to use microarray data to identify candidate disease genes. Here, we have presented a hybrid method that combines estimation of distribution algorithm with support vector machine for selection of key feature genes. We have benchmarked the method using the microarray data of both diffuse B cell lymphoma and colon cancer to demonstrate its performance for identifying key features from the profile data of high-dimension gene expression. The method was compared with a probabilistic model based on genetic algorithm and another hybrid method based on both genetics algorithm and support vector machine. The results showed that the proposed method provides new computational strategy for hunting candidate disease genes from the profile data of disease gene expression. The selected candidate disease genes may help to improve the diagnosis and treatment for diseases.