A comparative study on gene ranking and classification methods using microarray gene expression profiles

Microarray gene expression profiles are generally consists of very large number of genes. The total numbers of samples in the gene expression profiles are usually very less. Therefore, ranking of informative genes plays an important role in sample classification. In this paper, we present a comparative study on different gene ranking methods by applying them to two datasets. Support vector machine (SVM) with different kernels and a K-nearest neighbor (K-NN) classifier have been used to perform the classification task. Our results demonstrate the importance of informative gene ranking to classify test samples accurately.