Triclustering of Gene Expression Microarray data using Evolutionary Approach
This work addresses the challenge of identifying coherent gene patterns across conditions and time points for bioinformatics researchers, but it is incremental as it builds on existing triclustering methods with a modified fitness function.
The paper tackled the problem of triclustering gene expression microarray data by implementing an evolutionary algorithm with a new fitness function combining 3D Mean Square Residue and Least Square Approximation, resulting in good quality triclusters as observed in experiments on a yeast dataset.
In Tri-clustering, a sub-matrix is being created, which exhibit highly similar behavior with respect to genes, conditions and time-points. In this technique, genes with same expression values are discovered across some fragment of time points, under certain conditions. In this paper, triclustering using evolutionary algorithm is implemented using a new fitness function consisting of 3D Mean Square residue (MSR) and Least Square approximation (LSL). The primary objective is to find triclusters with minimum overlapping, low MSR, low LSL and covering almost every element of expression matrix, thus minimizing the overall fitness value. To improve the results of algorithm, new fitness function is introduced to find good quality triclusters. It is observed from experiments that, triclustering using EA yielded good quality triclusters. The experiment was implemented on yeast Saccharomyces dataset. Index Terms-Tri-clustering, Genetic Algorithm, Mean squared residue, Volume, Weights, Least square approximation.