AGTformer: Synergistic global transformer and adaptive graph gating for Accurate scRNA-seq clustering

Single-cell RNA sequencing (scRNA-seq) enables transcriptomic profiling at single-cell resolution, but accurate identification of cell subpopulations remains challenging because of the high dimensionality, sparsity, and dropout effects of scRNA-seq data. Existing deep learning-based clustering methods have shown promising performance, yet many primarily emphasize local neighborhood aggregation and may fail to adequately capture long-range cellular dependencies. Here, we propose Synergistic Global Transformer and Adaptive Graph Gating for Accurate scRNA-seq Clustering (AGTformer), an unsupervised clustering framework that combines adaptive edge reweighting with global latent-space modeling. AGTformer employs an Adaptive Adjacency Gating mechanism to dynamically reweight existing edges in the initial cell-cell graph, thereby reducing the influence of unreliable local connections and improving the stability of topology-aware representation learning. It further incorporates a Global Transformer refinement module to model long-range cell-cell dependencies beyond local graph propagation. Through the synergy of local topology-aware learning and global contextual refinement, AGTformer learns discriminative latent representations for clustering. Experiments on ten public scRNA-seq datasets demonstrate that AGTformer achieves superior clustering performance over representative baseline methods. In addition, visualization, sensitivity analysis, and ablation study support the effectiveness of the proposed components in improving representation quality for scRNA-seq clustering. These results suggest that AGTformer is a useful framework for unsupervised characterization of cellular heterogeneity in single-cell transcriptomic data.