q-bio.GNNov 10, 2026

Bridging Graph and Pairwise Learning for Gene Regulatory Network Inference from scRNA-seq Data

Authors: Hang Li, Jiaxin Qi, Yan Cui, Yuhua Zheng, Jianqiang Huang

Organizations: Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, 310024, Zhejiang, China · Computer Network Information Center, Chinese Academy of Sciences, Haidian, 100083, Beijing, China

Abstract

Motivation: Gene regulatory networks (GRNs) capture the underlying interactions through which transcription factors (TFs) regulate genes. Based on gene expression data, existing GRN inference approaches generally fall into two categories: graph-based methods, which model the GRN as a whole graph, and pairwise-based methods, which decompose the GRN into individual TF-target gene pairs for modeling. However, each approach exhibits limitations that are precisely the strengths of its counterpart. Graph-based methods tend to overfit due to their reliance on a single training graph, whereas pairwise-based methods benefit from abundant TF-target training pairs. In contrast, pairwise-based methods overlook the global topological structure, which is essential for comprehensively capturing regulatory mechanisms. Results: To address these limitations, we propose scGPL, an end-to-end unified framework that jointly models global regulatory topology and local interactions. scGPL extracts macro-level features from the global regulatory graph and introduces a dynamic, importance-guided subgraph sampling mechanism to capture fine-grained local dependencies. By fusing global representations with subgraph-enhanced local features, our framework bridges the gap between the two paradigms, incorporating essential whole-graph topological dependencies while retaining the data abundance advantage of pairwise methods. Extensive experiments on seven benchmark datasets demonstrate that scGPL consistently achieves state-of-the-art performance, with up to 13.7% improvement over the strongest baseline, validating the effectiveness of our integrative design. Availability and implementation: The source code is maintained on GitHub (https://github.com/talent-hang/scGPL), and the datasets and versioned releases are archived at https://doi.org/10.5281/zenodo.21608485 for reproducibility.

Figures & tables

Explore similar work

CardsList
  1. BRIDGE: Biological Evidence Refinement and Heterogeneous Dynamic Gating for Gene Regulatory Networks

    Jun 2, 2026Ziyang Dong, Shanwen Tan, Hengchuang Yin +5Heterogeneous GNNsGraph SSL

  2. Towards Universal Gene Regulatory Network Inference: Unlocking Generalizable Regulatory Knowledge in Single-cell Foundation Models

    May 1, 2026Jiaxin Qi, Hang Li, Yan Cui +2Gene Regulatory Network InferenceSingle-Cell Transcriptomics