ScReNI: Single-cell Regulatory Network Inference Through Integrating scRNA-seq and scATAC-seq Data

Abstract

Each cell possesses a unique gene regulatory network. However, limited methods exist for inferring cell-specific regulatory networks, particularly through the integration of single-cell RNA sequencing (scRNA-seq) and single-cell assay for transposase-accessible chromatin using sequencing (scATAC-seq) data. Herein, we develop a novel algorithm, named single-cell regulatory network inference (ScReNI), for inferring gene regulatory networks at the single-cell level. In ScReNI, the nearest neighbors algorithm is utilized to establish the neighboring cells for each cell, where nonlinear regulatory relationships between gene expression and chromatin accessibility are inferred through a modified random forest. ScReNI is designed to analyze both paired and unpaired datasets for scRNA-seq and scATAC-seq. ScReNI demonstrates more accurate regulatory relationships and outperforms existing cell-specific network inference methods in network-based cell clustering. ScReNI also shows superior performance in inferring cell type-specific regulatory networks through integrating gene expression and chromatin accessibility. Importantly, ScReNI offers the unique function of identifying cell-enriched regulators based on each cell-specific network. Overall, ScReNI facilitates the inferences of cell-specific regulatory networks and cell-enriched regulators, providing insights into single-cell regulatory mechanisms of diverse biological processes. ScReNI is available at https://github.com/Xuxl2020/ScReNI.

Keywords: Cell-enriched regulators; Cell-specific regulatory networks; Nearest neighbors; Network-based cell clustering; Single-cell multi-omics.