TrioCuckoo: A Multi Objective Cuckoo Search Algorithm for Triclustering Microarray Gene Expression Data

Abstract

Analyzing time series microarray dataset is a challenging task due to its three dimensional characteristic. Clustering techniques are applied to analyze gene expression data to extract group of genes under the tested samples based on a similarity measure. Biclustering appears as an evolution of clustering due to its ability to mine subgroups of genes and conditions from the data set, where the genes exhibit highly correlated patterns of behavior under certain experimental conditions. Triclustering contains a subset of genes that contains information related to the behavior of some genes from under some conditions over certain time periods. In this work, TrioCuckoo, a multi objective cuckoo search algorithm is proposed to extract co-expressed genes over samples and times with two different encoding representation of triclustering solution. TrioCuckoo is evaluated using two real life datasets such as the breast cancer and PGC-1 alpha time course datasets. The experimental analyses are conducted to identify the performance of the proposed work with existing triclustering approaches and Particle Swarm Optimization (PSO).The proposed work identifies the key genes which are involved in the breast cancer. The gene ontology, functional annotation and transcription factor binding site analysis are performed to establish the biological significance of genes belonging to the resultant cluster for Breast cancer.