Adversarial dense graph convolutional networks for single-cell classification

Motivation: In single-cell transcriptomics applications, effective identification of cell types in multicellular organisms and in-depth study of the relationships between genes has become one of the main goals of bioinformatics research. However, data heterogeneity and random noise pose significant difficulties for scRNA-seq data analysis. Results: We have proposed an adversarial dense graph convolutional network architecture for single-cell classification. Specifically, to enhance the representation of higher-order features and the organic combination between features, dense connectivity mechanism and attention-based feature aggregation are introduced for feature learning in convolutional neural networks. To preserve the features of the original data, we use a feature reconstruction module to assist the goal of single-cell classification. In addition, HNNVAT uses virtual adversarial training to improve the generalization and robustness. Experimental results show that our model outperforms the existing classical methods in terms of classification accuracy on benchmark datasets. [GRAPHICS] .

Automated summary

In this study, we propose an adversarial dense graph convolutional network architecture for feature learning in single-cell classification. We introduce dense connectivity mechanism and attention-based feature aggregation to enhance the representation of higher-order features and the organic combination between features. A feature reconstruction module is used to preserve the features of the original data and assist in single-cell classification. Experimental results show that our model outperforms existing classical methods in terms of classification accuracy on benchmark datasets.