Clustering single-cell multi-omics data via multi-subspace contrastive learning with structural smoothness

The integration of single-cell multi-omics data can uncover the underlying regulatory basis of diverse cell types and states. However, single-cell data inherently suffer from high levels of noise, sparsity, and intercellular heterogeneity, which pose significant challenges to the accuracy and robustness of clustering algorithms. Most existing multi-omics clustering approaches primarily focus on the integration of omics individuality and commonality across modalities, but they ignore the diverse feature extraction of the low-dimensional representation before the fusion of single-cell multi-omics data, and the feature smoothing consistency of the diverse features after the fusion of single-cell multi-omics data. In order to address above issues, we propose a novel multi-subspace contrastive learning with structural smoothness method for single-cell multi-omics data clustering (scMUSCLE), which is designed to address the challenges inherent in multi-omics data integration. First, the proposed scMUSCLE method leverages the degree structure to enhance structural diversity of each omics modality. Second, we perform multi-subspace contrastive learning to improve the diversity exploration across multi-omics features. Next, we propose an adaptive graph convolution clustering module, which establishes an adaptive feedback mechanism between intra-cluster smoothness and the downstream clustering task. Extensive experiments on four benchmark multi-omics datasets demonstrate the effectiveness and robustness. The source code can be found on the GitHub repository: https://github.com/GodIsGad/scMUSCLE.