A new asynchronous parallel algorithm for inferring large-scale gene regulatory networks

Abstract

The reconstruction of gene regulatory networks (GRNs) from high-throughput experimental data has been considered one of the most important issues in systems biology research. With the development of high-throughput technology and the complexity of biological problems, we need to reconstruct GRNs that contain thousands of genes. However, when many existing algorithms are used to handle these large-scale problems, they will encounter two important issues: low accuracy and high computational cost. To overcome these difficulties, the main goal of this study is to design an effective parallel algorithm to infer large-scale GRNs based on high-performance parallel computing environments. In this study, we proposed a novel asynchronous parallel framework to improve the accuracy and lower the time complexity of large-scale GRN inference by combining splitting technology and ordinary differential equation (ODE)-based optimization. The presented algorithm uses the sparsity and modularity of GRNs to split whole large-scale GRNs into many small-scale modular subnetworks. Through the ODE-based optimization of all subnetworks in parallel and their asynchronous communications, we can easily obtain the parameters of the whole network. To test the performance of the proposed approach, we used well-known benchmark datasets from Dialogue for Reverse Engineering Assessments and Methods challenge (DREAM), experimentally determined GRN of Escherichia coli and one published dataset that contains more than 10 thousand genes to compare the proposed approach with several popular algorithms on the same high-performance computing environments in terms of both accuracy and time complexity. The numerical results demonstrate that our parallel algorithm exhibits obvious superiority in inferring large-scale GRNs.

Fig 1. Outline of reconstructing large-scale gene networks by using the LSGPA.

Fig 2. Outline of Parallel Computing.

Fig 3. Difference between LSGPA and the two methods LSGPA and NARROMI in four indexes.

Val() in vertical axis represents one of the four indexes for different methods.

Fig 4. Difference of two methods LSGPA and PCA-CMI in four indexes.

Fig 5. ROC curves of LSGPA on DREAM5 in size 202.

Fig 6. ROC curves of LSGPA on DREAM5 in size 1505.

The subfigure shows the details.

Fig 7. The calculated indexes for different parameter thresholds θ with size 202.

Fig 8. The calculated indexes for different thresholds θ with size 1505.

Fig 9. Speed up of the LSGPA against NARROMI and PCA-CIM for different gene numbers from E.coli.

Fig 10. Speed up of the LSGPA against Genie3 for different gene numbers from datasets in [13].