BRIDGE: Biological Evidence Refinement and Heterogeneous Dynamic Gating for Gene Regulatory Networks
Researchers have developed a new framework called BRIDGE to improve the inference of gene regulatory networks from single-cell RNA sequencing data. This method addresses challenges posed by noisy and sparse data by employing contrastive learning and heterogeneous gated encoding to adaptively regulate information transfer between genes and cells. Experiments demonstrate that BRIDGE achieves state-of-the-art performance, outperforming existing methods like GCLink, particularly in few-shot transfer scenarios across different cell types. A case study on hESC data further validated the biological relevance of BRIDGE's predictions. AI