A topology-preserving dimensionality reduction method for single-cell RNA-seq data using graph autoencoder

Dimensionality reduction is crucial for the visualization and interpretation of the high-dimensional single-cell RNA sequencing (scRNA-seq) data. However, preserving topological structure among cells to low dimensional space remains a challenge. Here, we present the single-cell graph autoencoder (scGAE), a dimensionality reduction method that preserves topological structure in scRNA-seq data. scGAE builds a cell graph and uses a multitask-oriented graph autoencoder to preserve topological structure information and feature information in scRNA-seq data simultaneously. We further extended scGAE for scRNA-seq data visualization, clustering, and trajectory inference. Analyses of simulated data showed that scGAE accurately reconstructs developmental trajectory and separates discrete cell clusters under different scenarios, outperforming recently developed deep learning methods. Furthermore, implementation of scGAE on empirical data showed scGAE provided novel insights into cell developmental lineages and preserved inter-cluster distances.

Automated summary

Dimensionality reduction is crucial for visualizing and interpreting high-dimensional single-cell RNA sequencing data, and the single-cell graph autoencoder (scGAE) introduced in this study preserves both topological structure and feature information simultaneously. By extending scGAE for data visualization, clustering, and trajectory inference, it outperforms recent deep learning methods in accurately reconstructing developmental trajectories and separating cell clusters. Implementation on empirical data provides new insights into cell developmental lineages and maintains inter-cluster distances.