Single-cell Curriculum Learning-based Deep Graph Embedding Clustering

TL;DR

This paper introduces scCLG, a novel deep graph embedding clustering method for single-cell RNA sequencing data that uses curriculum learning and a multi-objective autoencoder to improve cell clustering accuracy.

Contribution

The paper proposes a new curriculum learning-based deep graph clustering approach with a multi-criteria autoencoder and selective training strategy for better single-cell data analysis.

Findings

Outperforms state-of-the-art clustering methods on multiple datasets.

Effectively handles high dropout rates and data heterogeneity.

Improves cell clustering accuracy and robustness.

Abstract

The swift advancement of single-cell RNA sequencing (scRNA-seq) technologies enables the investigation of cellular-level tissue heterogeneity. Cell annotation significantly contributes to the extensive downstream analysis of scRNA-seq data. However, The analysis of scRNA-seq for biological inference presents challenges owing to its intricate and indeterminate data distribution, characterized by a substantial volume and a high frequency of dropout events. Furthermore, the quality of training samples varies greatly, and the performance of the popular scRNA-seq data clustering solution GNN could be harmed by two types of low-quality training nodes: 1) nodes on the boundary; 2) nodes that contribute little additional information to the graph. To address these problems, we propose a single-cell curriculum learning-based deep graph embedding clustering (scCLG). We first propose a Chebyshev graph convolutional autoencoder with multi-criteria (ChebAE) that combines three optimization objectives, including topology reconstruction loss of cell graphs, zero-inflated negative binomial (ZINB) loss, and clustering loss, to learn cell-cell topology representation. Meanwhile, we employ a selective training strategy to train GNN based on the features and entropy of nodes and prune the difficult nodes based on the difficulty scores to keep the high-quality graph. Empirical results on a variety of gene expression datasets show that our model outperforms state-of-the-art methods. The code of scCLG will be made publicly available at https://github.com/LFD-byte/scCLG.