Elephant search optimization combined with deep neural network for microarray data analysis

Abstract

Even though there is a plethora of research in Microarray gene expression data analysis, still, it poses challenges for researchers to effectively and efficiently analyze the large yet complex expression of genes. The feature (gene) selection method is of paramount importance for understanding the differences in biological and non-biological variation between samples. In order to address this problem, Elephant search (ESA) based optimization is proposed to select best gene expressions from the large volume of microarray data. Firefly search (FFS) is also used to understand the effectiveness of the Elephant search method in feature selection process. Stochastic gradient descent based Deep Neural Network as Deep learning (DL) with softmax activation function is then used on the reduced features (genes) for better classification of different samples according to their gene expression levels. The experiments are carried out on ten most popular Cancer microarray gene selection datasets, obtained from UCI machine learning repository. The empirical results obtained by the proposed elephant search based deep learning approach are compared with the most recent published article for its suitability in future Bioinformatics research. Finally, Statistical significance test by one-way ANOVA with post hoc Tukey’s test is conducted to deduce a number of insights on the selection of the best classification model.