Genetic algorithm-neural network: feature extraction for bioinformatics data.

Abstract

With the advance of gene expression data in the bioinformatics field, the questions which frequently arise, for both computer and medical scientists, are which genes are significantly involved in discriminating cancer classes and which genes are significant with respect to a specific cancer pathology. Numerous computational analysis models have been developed to identify informative genes from the microarray data, however, the integrity of the reported genes is still uncertain. This is mainly due to the misconception of the objectives of microarray study. Furthermore, the application of various preprocessing techniques in the microarray data has jeopardised the quality of the microarray data. As a result, the integrity of the findings has been compromised by the improper use of techniques and the ill-conceived objectives of the study. This research proposes an innovative hybridised model based on genetic algorithms (GAs) and artificial neural networks (ANNs), to extract the highly differentially expressed genes for a specific cancer pathology. The proposed method can efficiently extract the informative genes from the original data set and this has reduced the gene variability errors incurred by the preprocessing techniques. The novelty of the research comes from two perspectives. Firstly, the research emphasises on extracting informative features from a high dimensional and highly complex data set, rather than to improve classification results. Secondly, the use of ANN to compute the fitness function of GA which is rare in the context of feature extraction. Two benchmark microarray data have been taken to research the prominent genes expressed in the tumour development and the results show that the genes respond to different stages of tumourigenesis (i.e. different fitness precision levels) which may be useful for early malignancy detection. The extraction ability of the proposed model is validated based on the expected results in the synthetic data sets. In addition, two bioassay data have been used to examine the efficiency of the proposed model to extract significant features from the large, imbalanced and multiple data representation bioassay data.