Gat2Get: A Novel Approach to Infer Gene Regulatory Network from Gene Activity using Dynamic Bayesian Network learning

Discovering Gene Regulatory Network (GRN) gives some idea about gene pathways and helps many potential applications in medicine. The essential source of data for this task is the gene expression data. High complexity and poor quality of gene expression data acquired by high throughput methods like microarray provide many difficulties in the context of the current issue. A promising method for evaluating gene expression noisy data to characterize processes made up of locally interacting components is Bayesian Network. In fact, because of the intricacy of the inputs and results of the cellular mechanism, inferring GRN from expression data presents numerous difficulties. This work proposes a new approach for inferring GRNs from time series gene expression data. The present work extends the existing Bayesian Network methods to include the regulation properties of genes to improve the process of capturing natural classes during inferring the relations between genes. The proposed approach is evaluated in comparing to the corresponding techniques of the related works, and the results show the ability of the present approach is efficient to some level to deal with such high dimensional data even without dimension reduction, but in the presence of regulatory information.