BiCLUM: Bilateral Contrastive Learning for Unpaired Single-Cell Multi-Omics Integration

The integration of single-cell multi-omics data provides a powerful approach for understanding the complex interplay between different molecular modalities, such as RNA expression, chromatin accessibility and protein abundance, measured through assays like scRNA-seq, scATAC-seq and CITE-seq, at single-cell resolution. However, most existing single-cell technologies focus on individual modalities, limiting a comprehensive understanding of their interconnections. Integrating such diverse and often unpaired datasets remains a challenging task due to unknown cell correspondences across distinct feature spaces and limited insights into cell- type-specific activities in non-scRNA-seq modalities. In this work, we propose BiCLUM, a Bilateral Contrastive Learning approach for Unpaired single-cell Multi-omics integration, which simultaneously enforces cell-level and feature-level alignment across modalities. BiCLUM first transforms one modality, such as scATAC-seq, into the data space of another modality, such as scRNA-seq, using prior genomic knowledge. It then learns cell and gene embeddings simultaneously through a bilateral contrastive learning framework, incorporating both cell-level and feature-level contrastive losses. We evaluated BiCLUM on aligning gene expression with chromatin accessibility via three paired RNA-ATAC multi-omics datasets, as well as gene expression with protein expression via three CITE-seq datasets. The results demonstrate that BiCLUM either outperforms or is at least comparable to existing integration methods, excelling in both visualization and quantitative metrics. Furthermore, BiCLUM preserves the biological relevance of the integrated data, making it a potential powerful tool for downstream biological analysis, such as cell type identification and pathway exploration.