Inferring gene regulatory networks from perturbed gene expression data using a dynamic Bayesian network with a Markov Chain Monte Carlo algorithm

In understanding the biological role of genes and gene products, the analysis of gene regulatory functions is important. Computational methods for running gene regulatory networks inference have its own limitations. For instance, Bayesian Network and Boolean Network are unable to model the cyclic relationship and the interaction uncertainties, which are important elements in the biological networks. Hence, Dynamic Bayesian Network (DBN) was employed in this research to overcome the limitations. Even though DBN performs better than other methods in term of accuracy, its prediction accuracy is still considered low. Due to this, optimization algorithm is necessary to improve the accuracy performance. Therefore, this research is concerned on inferring gene regulatory networks using DBN with Markov Chain Monte Carlo (MCMC) algorithm for the improvement of prediction accuracy. The research results were compared with the results from previous works in terms of accuracy, sensitivity and specificity. Experimental results show that our proposed approach (DBN with MCMC) is better than existing work in term of prediction accuracy.