Preprint
Nov 2026
Bridging Graph and Pairwise Learning for Gene Regulatory Network Inference from scRNA-seq Data
By fusing global representations with subgraph-enhanced local features, the scGPL framework bridges the gap between the two paradigms, incorporating essential whole-graph topological dependencies while retaining the data abundance advantage of pairwise methods.
Han Li, Jia-Xin Qi, Yan Cui et al.
· 0 citations