GRRFNet: Guided Regularized Random Forest-based Gene Regulatory Network Inference Using Data Integration

Abstract

Gene regulatory network (GRN) inference based on gene expression data is still a huge challenge in systems biology. Genomic data, including time-series expression data, steady-state data, knockout data, and other biological data, such as Gene Ontology (GO) annotations, provide information on potential gene regulation. However, most existing methods continue to use only a single dataset for GRN inference. To integrate these types of data and improve the accuracy of inference, we propose a new data-integration strategy based on guided regular random forest (GRRF) for GRN inference, dubbed GRRFNet. Specifically, first, time-series data and steady-state data as main datasets are integrated to generate learning samples; simultaneously, other datasets are processed to design penalty coefficients for guiding feature selection; then, a GRRF model is applied to integrate the prior information with a main dataset to learn the transcription function and evaluate the importance of feature; finally, the score of the feature's importance is used as the possibility of the gene regulatory relationships to construct the GRN. To evaluate the performance of GRRFNet, we compare it with GENIE3, dynGENIE3, and GRIEF at the artificial DREAM4 dataset and the real Escherichia coli dataset. Although GRRFNet does not yield the best performance on every network, its competitiveness is still reflected herein.