Information-Theoretic Inference of Regulatory Networks Using Backward Elimination

Unraveling transcriptional regulatory networks is essential for understanding and predicting cellular responses in different developmental and environmental contexts. Information-theoretic methods of network inference have been shown to produce high-quality reconstructions because of their ability to infer both linear and non-linear dependencies between regulators and targets. In this paper, we introduce MRNETB an improved version of the previous information-theoretic algorithm, MRNET, which has competitive performance with state-of-the-art algorithms. MRNET infers a network by using a forward selection strategy to identify a maximally-independent set of neighbors for every variable. However, a known limitation of algorithms based on forward selection is that the quality of the selected subset strongly depends on the first variable selected. In this paper, we present MRNETB, an improved version of MRNET that overcomes this limitation by using a backward selection strategy followed by a sequential replacement. Our new variable selection procedure can be implemented with the same computational cost as the forward selection strategy. MRNETB was benchmarked against MRNET and two other information-theoretic algorithms, CLR and ARACNE. Our benchmark comprised 15 datasets generated from two regulatory network simulators, 10 of which are from the DREAM4 challenge, which was recently used to compare over 30 network inference methods. To assess stability of our results, each method was implemented with two estimators of mutual information. Our results show that MRNETB has significantly better performance than MRNET, irrespective of the mutual information estimation method. MRNETB also performs comparably to CLR and significantly better than ARACNE indicating that our new variable selection strategy can successfully infer high-quality networks.