A hybrid adversarial autoencoder-graph network model with dynamic fusion for robust scRNA-seq clustering

Background Single-cell RNA sequencing (scRNA-seq) allows the exploration of biological heterogeneity among different cell types within tissues at a single-cell resolution. Cell clustering serves as a foundation for scRNA-seq data analysis and provides new insights into the heterogeneity of cells wit...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:BMC genomics Ročník 26; číslo 1; s. 749 - 13
Hlavní autori: Tang, Binhua, Feng, Yingying, Gao, Xinyu
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: London BioMed Central 18.08.2025
BioMed Central Ltd
Springer Nature B.V
BMC
Predmet:
Ablation
Adversarial AE
Algorithms
Animal Genetics and Genomics
Artificial neural networks
Autoencoder
Biomedical and Life Sciences
Cluster Analysis
Clustering
Cross-attention mechanism
Data analysis
Data integration
Datasets
Electronic data processing
GCN
Gene expression
Gene sequencing
Genomics of isolated human populations
Graphical representations
Heterogeneity
Humans
Learning
Life Sciences
Machine learning
Methods
Microarrays
Microbial Genetics and Genomics
Neural networks
Normal distribution
Plant Genetics and Genomics
Proteomics
RNA sequencing
RNA-Seq - methods
ScRNA-seq
Self-supervised clustering
Sensory integration
Single-Cell Gene Expression Analysis - methods
China
ScRNA-seq
GCN
Self-supervised clustering
Adversarial AE
Cross-attention mechanism
ISSN:1471-2164, 1471-2164
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Background Single-cell RNA sequencing (scRNA-seq) allows the exploration of biological heterogeneity among different cell types within tissues at a single-cell resolution. Cell clustering serves as a foundation for scRNA-seq data analysis and provides new insights into the heterogeneity of cells within complex tissues. However, the inherent features of scRNA-seq data, such as heterogeneity, sparsity, and high dimensionality, pose significant technical challenges for effective cell clustering. Results Here, we present a novel deep clustering method, scCAGN, based on an adversarial autoencoder (AAE) and a cross-attention graph convolutional network (GCN), to address the above challenges in scRNA-seq data analysis. Specifically, to enhance data reconstruction, scCAGN utilizes adversarial autoencoders to augment encoder capabilities. Graph feature representations obtained via a GCN were integrated using a dynamic information fusion mechanism, yielding enhanced feature representations. In addition, scCAGN combines three different loss functions to optimize clustering performance through a joint clustering approach. By leveraging a unique information fusion and joint mechanism, scCAGN extracts deep cell features without labeled information, thus improving cell classification efficiency. Our findings show that scCAGN surpasses the existing methods in clustering performance across eight typical scRNA-seq datasets, achieving a maximum Normalized Mutual Information (NMI) improvement of 11.94%, notably reaching an NMI of 0.9732 in the QS_diaphragm dataset. It showed an average NMI improvement of 13% across the eight benchmark datasets, surpassing the lowest-performing method. Further ablation and hyperparameter analyses validated the robustness of the proposed method. The code is available at: http://github.com/gladex/scCAGN . Conclusion scCAGN integrates AAE and cross-attention GCN with dynamic fusion, achieving state-of-the-art scRNA-seq clustering (0.9732 NMI, 13% average gain) across eight datasets. Validated via ablation and hyperparameter tests, it advances label-free cell discovery and enables further multimodal integration to dissect cellular heterogeneity.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1471-2164
1471-2164
DOI:10.1186/s12864-025-11941-y