The Hybrid BPSO/BLDA Model for Gene Selection and Cancer Classification based on Microarray Data

Microarray data have an important role in identification and classification of the cancer tissues. Having a few samples of microarrays in cancer researches is always one of the most concerns which lead to some problems in designing the classifiers. Therefore, gene selection techniques should be utilized before classification to remove the non-informative genes from the microarray data. In this paper, a new method is proposed for gene selection based on hybrid Binary Particle Swarm Optimization (BPSO) and Bayesian Linear Discriminant Analysis (BLDA) in order to classify a large scale of microarray data. The proposed algorithm is applied on four cancer datasets and its results are compared with other existing methods. The results illustrate that the proposed algorithm has higher accuracy and validity in comparison to other existing methods and is able to select the small subset of informative genes in order to increase the classification accuracy.

Keywords:

Gene expression , Binary Particle Swarm Optimization , Bayesian Linear Discriminant Analysis , Classification , Gene selection