MoRE-GNN: Multi-omics Data Integration with a Heterogeneous Graph Autoencoder

TL;DR

MoRE-GNN tackles multi-omics single-cell data integration by learning data-driven, modality-specific graphs and applying heterogeneous graph convolution with attention to capture cross-modal relationships. It jointly optimizes clustering and cross-modal edge reconstruction losses to produce embeddings that reflect inter-modality structure. Across six public datasets, it outperforms a baseline in scenarios with strong cross-modal correlations and yields interpretable latent spaces, while its performance varies with dataset complexity and noise. The approach eliminates predefined priors, offers scalability, and provides a flexible framework for downstream analysis in precision medicine, albeit with room for robustness improvements across diverse contexts.

Abstract

The integration of multi-omics single-cell data remains challenging due to high-dimensionality and complex inter-modality relationships. To address this, we introduce MoRE-GNN (Multi-omics Relational Edge Graph Neural Network), a heterogeneous graph autoencoder that combines graph convolution and attention mechanisms to dynamically construct relational graphs directly from data. Evaluations on six publicly available datasets demonstrate that MoRE-GNN captures biologically meaningful relationships and outperforms existing methods, particularly in settings with strong inter-modality correlations. Furthermore, the learned representations allow for accurate downstream cross-modal predictions. While performance may vary with dataset complexity, MoRE-GNN offers an adaptive, scalable and interpretable framework for advancing multi-omics integration.

Figures (8)

• Figure 1: MoRE-GNN architecture for multi-omics single-cell integration. Multi-omics features (RNA, ATAC, ADT) are used to dynamically construct modality-specific adjacency matrices, resulting in a heterogeneous graph. MoRE-GNN processes this graph through: (1) convolutional embedding layers with modality-specific channels, (2) $L$ attentional interaction layers for cross-modal feature integration, and (3) a convolutional output layer. Final embeddings are clustered using Louvain clustering Blondel_2008 and reduced in dimensionality (UMAP) to reveal cell type structure.
• Figure 2: Two-dimensional PCA visualization of MoRE-GNN latent embeddings. Grey lines represent model-predicted edges, with node coloring reflecting degree (connectivity). Left: BM-CITE dataset containing three major cell populations (T cells, B cells, and myeloid cells) exhibits clearly defined triangular clustering patterns in the latent space. Right: Skin-SHARE dataset displays a more amorphous latent cloud structure due to the continuous gradient of cell states present in the biological system. The distinct geometric patterns reflect the underlying cellular composition and differentiation states within each dataset.
• Figure 3: UMAP visualization of the latent representations produced by MoRE-GNN and clustered by Louvain algorithm. Left: On BM-CITE, discrete immune cell populations are well-seperated into distinct clusters. Right: On Skin-SHARE, however, the continuous spectrum of cell states leads to less defined cluster boundaries.
• Figure 4: Cross-modality feature reconstruction from latent space on PBMC-TEA. Scatter plots show predicted vs. true feature values for (Left) ADT, (Middle) ATAC, and (Right) RNA. The red dashed line indicates perfect prediction. ADT prediction exhibits strong concordance with minimal systematic bias, though variance increases for higher-abundance features. ATAC prediction is more challenging: predictions capture low-abundance signals but systematically underestimate high-intensity features. RNA prediction shows moderate correlation, but high variability and compressed dynamic range suggest difficulty in modeling its broader expression spectrum. These trends highlight that MoRE-GNN embeddings capture biologically meaningful cross-modal structure, but its performance is strongly modality-dependent.
• Figure 5: Effect of PCA preprocessing on clustering quality. Louvain cluster assignments for LUNG-CITE are shown using PCA rediced features (Left) and raw normalized features (Right). Clusters are more visually coherent without PCA, which is consistent with higher recorded ARI (0.545 vs. 0.489) and NMI (0.672 vs. 0.597).