Microarray data biclustering with multi-objective immune algorithm

High throughput technologies yield large-scale datasets on genomic variation in diverse populations, allowing the study of these variations and their association with disease and their complex traits. Systematic functional characterization of genes identified in the genome sequencing projects is urgently needed in the post-genomic era. Biclustering, which searches for subsets of individuals that are coherent in their behavior across a subset of the features, is a very useful data mining technique in microarray data analysis and has presented its advantages in many applications. This paper proposes a novel multi-objective immune biclustering (MOIB) algorithm, based on the immune response principle of the immune system, to mine biclusters from microarray data. In the algorithm, we extends ε-dominance and performs the mechanism of crowding computation to obtain many Pareto optimal solutions distributed onto the Pareto front. Experimental results on real datasets show that our approach can effectively And more significant biclusters than other biclustering algorithms.