Classification of Microarray Gene Expression Data using Weighted Grey Wolf Optimizer based Fuzzy Clustering

With the emergence of DNA microarray technology, scientists are continuously studying the expression levels of a large number of genes over different instances of time points. Analyzing the DNA microarray data confirm that the expression levels of two different genes vary simultaneously with the effect of external stimuli exhibiting different patterns. Therefore soft fuzzy clustering plays an important role in detecting patterns belonging to multiple clusters at the same time. Therefore this article proposes a novel fuzzy clustering technique utilizing weighted distance measure instead of the Euclidean distance using Grey Wolf Optimizer (GWO) as the global optimization techniques. Here clustering of microarray data is posed as a single objective optimization problem where the objective is to minimize the variability within the cluster and simultaneously maximizes the variability between the cluster. The newly proposed fuzzy-based weighted GWO clustering technique (Fuzzy-WDGWO) is then compared with some of the existing clustering techniques. Four different artificial datasets and three different real-life gene expression datasets have been considered to verify the efficiency of the proposed Fuzzy-WDGWO clustering technique both numerically as well as pictorially. Experimental analysis and performance evaluation of the proposed Fuzzy-WDGWO clustering technique show the superiority over the other existing clustering techniques such as PSO-FCM, FA-FCM, GWO-FCM, GWO-FCM, DE-FCM.