scGTN: Deep Siamese Graph Transformer Network for Single-cell RNA Sequencing Clustering
Researchers have introduced scGTN, a novel framework for clustering single-cell RNA sequencing (scRNA-seq) data. This method addresses limitations in existing approaches by integrating gene expression profiles with complex intercellular structural information. scGTN constructs two augmented graph views to capture complementary data, utilizes a Siamese graph transformer network to incorporate shortest-path information and node-wise distances, and employs an optimal transport strategy for self-supervised clustering. Experiments on benchmark datasets show scGTN outperforms current methods. AI
IMPACT This new framework could improve the accuracy and depth of analysis in biological research involving single-cell RNA sequencing.