TL;DR
The framework integrates three modules: dual-reconstruction to fuse attribute-structure information, contrastive learning under label guidance to extract semantic similarities, and deep embedding clustering to enable iterative optimization.
BACKGROUND Single-cell RNA sequencing (scRNA-seq) enables cellular characterization at single-cell resolution. However, its high dimensionality, sparsity, and noise make clustering challenging. Approaches utilizing contrastive learning and data augmentation have been introduced to improve representation quality for scRNA-seq clustering. In particular, dual contrastive frameworks combining instance- and cluster-level objectives can capture both cell-cell similarities and inter-cluster variations. However, existing dual contrastive frameworks focus primarily on discrete cluster boundaries, neglecting the biological continuity inherent in scRNA-seq data. METHODS We propose scFANCL, a dual contrastive framework designed to capture biological continuity in scRNA data. Rather than treating all non-augmented samples as negatives, scFANCL applies a cosine-similarity-based threshold to exclude cells of the same type from the negative pool, preserving continuous transcriptional relationships among them while maintaining inter-cluster separation. RESULTS Extensive experiments across seven publicly available scRNA-seq datasets demonstrated that scFANCL achieves competitive clustering performance compared with existing baseline methods, consistently yielding high ARI and NMI scores across datasets of varying size and complexity. Ablation studies further confirmed the contribution of the false negative filtering component, showing measurable improvements over variants without filtering. Downstream analyses further suggest that the learned embeddings may reflect biologically meaningful transcriptional transitions, including continuous differentiation trajectories within related cell types. The source code is available at https://github.com/mjuailab/scFANCL. CONCLUSIONS scFANCL addresses a key limitation of conventional contrastive learning by applying a cosine-similarity-based threshold to exclude cells of the same type from the negative pool, thereby preserving biological continuity within cell types while maintaining inter-cluster separation. Evaluations across seven benchmark scRNA-seq datasets demonstrate competitive clustering performance, with learned embeddings capturing biologically meaningful transcriptional structure and characteristics of rare cell populations.
Experiments on three cross-patient scRNA-seq data sets demonstrate that PathoGraph achieves stable annotation performance across 32 directed reference-to-query transfer tasks, showing competitive and stable performance compared with representative marker-based, correlation-based, and model-based annotation methods.
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.
Prior-enhanced Inference for Spatial Transcriptomic Cell Type Mapping (PRISM), a novel three-stage framework integrating biological prior construction, pseudo-label generation, and multi-level ST refinement, shows strong robustness to domain shift and platform heterogeneity.
SaDGAE, an unsupervised deep graph autoencoder (GAE) framework that jointly models gene expression patterns and cell–cell relationships, achieves strong and competitive clustering performance, yielding biologically interpretable clusters and accurately recovering known marker gene patterns.
Single-cell RNA sequencing (scRNA-seq) provides a novel perspective to explore cellular biology at the single-cell resolution. Single-cell clustering is a crucial step to reveal cell types and the corresponding biological functions. However, when dealing with the high dimensionality and complexity of scRNA-seq data, existing deep models fail to comprehensively capture the intrinsic attribute information and structural relationships within the data. In this study, we propose a novel single-cell deep clustering model named scDFVA. The proposed scDFVA consists of a variational graph attention autoencoder (AE), a zero-inflated negative binomial (ZINB) based AE, and a self-supervised clustering. To better simulate sparse and zero-inflated scRNA-seq data, we incorporate the ZINB model into the AE. The variational graph attention AE is introduced to learn the cell structure information. scDFVA achieves representation learning within a joint framework comprising a ZINB-based AE and a variational graph attention AE, effectively fusing gene expression and cell structure information. Furthermore, scDFVA performs self-supervised clustering training on the latent fusion representations of cells to achieve mutual supervision between representation learning and clustering. Experiments indicated that scDFVA outperformed several other competing methods, demonstrating that our method is beneficial in single-cell clustering.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
