scSGL: Signed Graph Learning for Single-Cell Gene Regulatory Network Inference

Abstract

Elucidating the topology of gene regulatory networks (GRN) from large single-cell RNA sequencing (scRNAseq) datasets, while effectively capturing its inherent cell-cycle heterogeneity, is currently one of the most pressing problems in computational systems biology. Recently, graph learning (GL) approaches based on graph signal processing (GSP) have been developed to infer graph topology from signals defined on graphs. However, existing GL methods are not suitable for learning signed graphs, which represent a characteristic feature of GRNs, as they account for both activating and inhibitory relationships between genes. To this end, we propose a novel signed GL approach, scSGL, that incorporates the similarity and dissimilarity between observed gene expression data to construct gene networks. The proposed approach is formulated as a non-convex optimization problem and solved using an efficient ADMM framework. In our experiments on simulated and real single cell datasets, scSGL compares favorably with other single cell gene regulatory network reconstruction algorithms.