Accurately Clustering Single-cell RNA-seq data by Capturing Structural Relations between Cells through Graph Convolutional Network

Single-cell RNA sequencing (scRNA-seq) technologies promise to characterize the transcriptome of genes at cellular resolution, which shed light on unfolding cell heterogeneity and diversity. Fast-growing scRNA-seq profiles require efficient clustering algorithms to identify the same type of cells. Although many methods have been developed for cell clustering, existing clustering methods are limited to extract the representations from expression data of individual cells, while ignoring the high-order structural relations between cells. Here, we proposed GraphSCC, a robust graph artificial intelligence model to cluster single cells by accounting for structural relations between cells. The representation learned from the graph convolutional network, together with another representation output from a denoising autoencoder network, are optimized by a dual self-supervised module for better cell clustering. The experimental results indicate that GraphSCC model outperforms state-of-the-art methods in terms of various evaluation metrics on both simulated and real datasets. Further visualizations show that GraphSCC provides representations for better intra-cluster compactness and inter-cluster separability.