scGTN: Deep Siamese Graph Transformer Network for Single-cell RNA Sequencing Clustering

2026-06-17

AI Summary

This work addresses the challenges posed by data sparsity, noise, and complex higher-order cellular structures in single-cell RNA sequencing (scRNA-seq) clustering. To overcome these limitations, the authors propose a novel self-supervised clustering framework that models scRNA-seq data as a graph and constructs two augmented graph views. For the first time, this approach integrates a Siamese graph Transformer with an optimal transport strategy to explicitly capture shortest paths and node distances among cells, thereby jointly leveraging gene expression profiles and higher-order structural dependencies. Extensive experiments on multiple benchmark datasets demonstrate that the proposed method significantly outperforms existing clustering algorithms, achieving superior robustness and accuracy.

Abstract

Single-cell RNA sequencing (scRNA-seq) serves a pivotal role in characterizing gene expression at the cellular level, enabling the identification of cell types and advancing the understanding of cellular heterogeneity. Despite the significant progress in scRNA-seq data clustering, we argue that current methods always ignore the sparsity and noise, as well as the complex intercellular structural information inherent in scRNA-seq data. Toward this end, in this paper, we propose a novel single-cell RNA-seq clustering framework via deep Siamese Graph Transformer Network (termed scGTN), which explicitly integrates gene expression profile and intercellular structural dependencies for cell clustering. In particular, we formulate scRNA-seq data as a graph and construct two augmented graph views that serve as dual views to capture complementary intercellular information. Then, a Siamese graph transformer network is employed to explicitly incorporate shortest-path information and node-wise distances for capturing richer structural relationships between cells. Finally, we employ an optimal transport strategy to guide the cell clustering in a self-supervised manner. Extensive experiments on multiple benchmark scRNA-seq datasets demonstrate that our scGTN consistently outperforms existing methods. Our code is available at https://github.com/W-RMSL/scGTN.

Problem

• scRNA-seq
• clustering
• sparsity
• noise
• structural information

Innovation

• Siamese Graph Transformer
• single-cell RNA sequencing
• graph representation
• optimal transport
• self-supervised clustering