Gene regulatory network inference algorithm based on spectral signed directed graph convolution

TL;DR

This paper introduces MSGRNLink, a novel spectral signed directed graph convolution framework for more accurate gene regulatory network inference from single-cell RNA sequencing data, outperforming existing methods.

Contribution

The paper presents a new spectral graph convolution method tailored for signed directed graphs, specifically designed for gene regulatory network inference.

Findings

MSG RNLink outperforms baseline models in AUROC on simulated and real datasets.

Parameter sensitivity analysis shows robustness of MSGRNLink.

In a bladder cancer case study, MSGRNLink predicts more known edges and signs.

Abstract

Accurately reconstructing Gene Regulatory Networks (GRNs) is crucial for understanding gene functions and disease mechanisms. Single-cell RNA sequencing (scRNA-seq) technology provides vast data for computational GRN reconstruction. Since GRNs are ideally modeled as signed directed graphs to capture activation/inhibition relationships, the most intuitive and reasonable approach is to design feature extractors based on the topological structure of GRNs to extract structural features, then combine them with biological characteristics for research. However, traditional spectral graph convolution struggles with this representation. Thus, we propose MSGRNLink, a novel framework that explicitly models GRNs as signed directed graphs and employs magnetic signed Laplacian convolution. Experiments across simulated and real datasets demonstrate that MSGRNLink outperforms all baseline models in AUROC. Parameter sensitivity analysis and ablation studies confirmed its robustness and the importance of each module. In a bladder cancer case study, MSGRNLink predicted more known edges and edge signs than benchmark models, further validating its biological relevance.