Inference of time-delayed gene regulatory networks based on dynamic Bayesian network hybrid learning method

Abstract

Gene regulatory networks (GRNs) research reveals complex life phenomena from the perspective of gene interaction, which is an important research field in systems biology. Traditional Bayesian networks have a high computational complexity, and the network structure scoring model has a single feature. Information-based approaches cannot identify the direction of regulation. In order to make up for the shortcomings of the above methods, this paper presents a novel hybrid learning method (DBNCS) based on dynamic Bayesian network (DBN) to construct the multiple time-delayed GRNs for the first time, combining the comprehensive score (CS) with the DBN model. DBNCS algorithm first uses CMI2NI (conditional mutual inclusive information-based network inference) algorithm for network structure profiles learning, namely the construction of search space. Then the redundant regulations are removed by using the recursive optimization algorithm (RO), thereby reduce the false positive rate. Secondly, the network structure profiles are decomposed into a set of cliques without loss, which can significantly reduce the computational complexity. Finally, DBN model is used to identify the direction of gene regulation within the cliques and search for the optimal network structure. The performance of DBNCS algorithm is evaluated by the benchmark GRN datasets from DREAM challenge as well as the SOS DNA repair network in Escherichia coli, and compared with other state-of-the-art methods. The experimental results show the rationality of the algorithm design and the outstanding performance of the GRNs.

Keywords: comprehensive score model; dynamic Bayesian network; gene regulatory networks; multiple time-delayed; network structure profiles.

Figure 1. Comparison of DREAM3 10 nodes real GRNs and inferred GRNs

Figure 2. Comparison of the results of constructing DREAM3 10-node GRNs with DBNCS algorithm

Figure 3. Comparison of DREAM3 50 nodes real GRNs and inferred GRNs

Figure 4. Comparison of the results of constructing DREAM3 50-node GRNs with DBNCS algorithm

Figure 5. SOS DNA repair system of Escherichia coli

Figure 6. Comparison of Escherichia coli SOS DNA repair network and inferred gene regulatory network

Figure 7. Comparison of the results of constructing SOS DNA repair network in E. coli 9-node GRNs with DBNCS algorithm

Figure 8. The diagram of DBNCS method

(1) Using the CMI2NI algorithm, and through the gene microarray data to construct from the five genes and the interaction between the composition of the network structure profiles. (2) Redundant regulations are removed by RO algorithm: 2–3, 1–4. (3) The network structure profiles after the redundancy are decomposed into a series of cliques consisting of two co-expressing genes without loss: 2–1, 5–4, 1–3, 4–2, 3–5, the number of cliques is the same as the regulation relationship. (4) For each clique structure, the regulatory gene, target gene and the transcriptional delay are determined by the DBN based on the CS model to generate a series of dynamic sub-networks: 2→1,5→4,1→3,4→2,3→5. (5) Integration of a series of sub-networks, and get the final multiple time-delayed GRNs. The solid lines in Figure represent the true regulation between genes, and the dotted lines represent the redundancy correlation between the two genes.