A Hybrid Data and Knowledge Driven Approach for Gene Clustering and Network Reconstruction

Many methods have been developed for reverse engineering gene networks from time series expression data. However, when the number of genes and the complexity of regulation increase, it becomes increasingly difficult to infer gene networks. To tackle this scalability problem, this study presents an approach with two phases: gene clustering and network reconstruction. To perform gene clustering, a hybrid data and knowledge-driven method is developed to calculate both data and semantic similarity between genes. In the network reconstruction procedure, a Boolean network model is inferred from the gene clusters. A series of experiments are conducted to investigate the effect of the hybrid similarity measure in gene clustering and network reconstruction. The results prove the feasibility and effectiveness of the proposed approach.