A Graph Embedded Feature Decoupling Model for Clustering Single Cell RNA-seq Data

The rapid development in single-cell RNA sequencing (scRNA-seq) has dramatically enhanced our insight into cellular heterogeneity and disease mechanisms. In the analysis of scRNA-seq data, cell clustering plays a vital role in downstream tasks. The advent of deep learning has revolutionized the analysis method for cell clustering. However, due to the high dimensionality and sparsity of scRNA-seq data, neural network-based methods often capture a multitude of spurious correlations. This oversight results in redundancy within the low-dimensional feature space, making it difficult to distinguish cell subpopulations. To address these limitations, we introduce the Graph Embedded Feature Decoupling model (scGEFD), a two-phase approach for cell clustering. During the first phase, we capture cellular structural information by graph neural network. In the second phase, we propose a feature decoupling method inspired by the Barlow Twins. Specifically, we refine feature representations by minimizing discrepancies between two perturbed sample versions, which reduces redundancy in the latent space and further accentuates biologically pertinent features. Consequently, scGEFD outperforms state-of-the-art clustering methods on ten real-world datasets, providing more accurate and meaningful biological insights from scRNA-seq data.