Biclustering of microarray data with MOSPO based on crowding distance

Abstract

Background: High-throughput microarray technologies have generated and accumulated massive amounts of gene expression datasets that contain expression levels of thousands of genes under hundreds of different experimental conditions. The microarray datasets are usually presented in 2D matrices, where rows represent genes and columns represent experimental conditions. The analysis of such datasets can discover local structures composed by sets of genes that show coherent expression patterns under subsets of experimental conditions. It leads to the development of sophisticated algorithms capable of extracting novel and useful knowledge from a biomedical point of view. In the medical domain, these patterns are useful for understanding various diseases, and aid in more accurate diagnosis, prognosis, treatment planning, as well as drug discovery.

Scatter search-based identification of local patterns with positive and negative correlations in gene expression data

“…These algorithms are optimization metaheuristics which are adapted to gene expression data, such as evolutionary approaches [31][32][33], multiobjective evolutionary approaches [34,35], greedy randomized adaptive search [36], simulated annealing [37], particle swarm Optimization [38] or estimation of distribution algorithms [39]. Most of these algorithms use the MSR as part of their merit function to characterize the types of patterns that are relevant to be found.…”

A Framework for Mining Coherent Patterns Using Particle Swarm Optimization based Biclustering

“…Liu et al [19] proposed a multi-objective immune biclustering (MOIB) algorithm for mining biclusters from microarray data based on the immune response principle of the immune system. Liu et al [20] proposed a crowding distance based multi-objective Particle Swarm Optimization biclustering, it is based on heuristic search technique which simulates the movement of flocks of birds,aims to find the nearest neighbor based on crowding distance and -dominance which converges to the Pareto front and guarantees diversity of solutions. Sarkar et al [21] have presented a review on Particle Swarm Optimization and shows that how well PSO hybridize with other clustering algorithms and yields better results in various optimization problems in terms of efficiency and accuracy.…”

Differential biclustering for gene expression analysis

“…One of the main applications of DNA microarray data is to compare the biological activities of the genes in two types of cells, such as normal and disease cells [12]. There are many cases where the conditions belong to two classes, and there is a need to find the set of significant genes for each class.…”

“…Biclustering can be used to find a subset of genes that have similar expression profiles under a subset of the conditions [12,13] as defined in Definition 1. Identifying a subset of genes that are related under a subset of conditions is an important challenge.…”

“…Missing values and noise add more limitations in applying the traditional clustering techniques on gene expression data [4]. Traditional clustering algorithms assume that related genes should have similar expression profiles in all the conditions [12]. This assumption does not hold in all of the experiments.…”