scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration
This provides a scalable and flexible solution for large-scale multi-omics data integration, addressing a bottleneck in single-cell sequencing for biological research.
The paper tackles the challenge of integrating unpaired single-cell multi-omics data by introducing scMRDR, a scalable generative framework that disentangles latent representations into shared and specific components, achieving excellent performance on benchmark datasets in terms of batch correction, modality alignment, and biological signal preservation.
Advances in single-cell sequencing have enabled high-resolution profiling of diverse molecular modalities, while integrating unpaired multi-omics single-cell data remains challenging. Existing approaches either rely on pair information or prior correspondences, or require computing a global pairwise coupling matrix, limiting their scalability and flexibility. In this paper, we introduce a scalable and flexible generative framework called single-cell Multi-omics Regularized Disentangled Representations (scMRDR) for unpaired multi-omics integration. Specifically, we disentangle each cell's latent representations into modality-shared and modality-specific components using a well-designed $β$-VAE architecture, which are augmented with isometric regularization to preserve intra-omics biological heterogeneity, adversarial objective to encourage cross-modal alignment, and masked reconstruction loss strategy to address the issue of missing features across modalities. Our method achieves excellent performance on benchmark datasets in terms of batch correction, modality alignment, and biological signal preservation. Crucially, it scales effectively to large-level datasets and supports integration of more than two omics, offering a powerful and flexible solution for large-scale multi-omics data integration and downstream biological discovery.