Advances of swarm intelligent systems in gene expression data classification

The step forward in the development of microarray technology of gene expression has created new opportunities in further exploration of living systems, source of disease and drug development and cancer biology. In the analysis of gene expression profiles, the number of tissue samples with genes expression levels available is usually small compared with the number of genes. This can lead either to possible overfitting and dimensionality curse or even to a complete failure in analysis of microarray data. So, the dramatic increase in genomic data volumes make it a challenging task to select genes that are really indicative of the tissue classification a key step to accurately pick out the information from such microarrays.
On the other hand, in the last decades, swarm intelligent systems have gained much attention and wide applications in different fields such as solving the gene expression data classification problem. These algorithms are efficient in dealing with optimization issues, and they are also relatively simple to implement with the ability to fast converge to a reasonably good solution. They engage probabilistic rules instead of deterministic ones and require neither derivatives of cost function. In this paper, a hybrid algorithm based on swarm intelligence systems is utilized to classify gene expression data