Subset-Contrastive Multi-Omics Network Embedding

2025-04-15

AI Summary

Existing single-cell multi-omics network embedding methods suffer from two key bottlenecks: prohibitive memory overhead and poor scalability; and ambiguous graph topology derived from similarity-based construction, which undermines graph representation learning. To address these, we propose SCoPE—the first scalable multi-omics graph embedding framework based on subgraph contrastive learning. SCoPE transforms similarity networks into topologically explicit, structure-enhanced graphs via subgraph sampling and a structural-aware contrastive learning paradigm. Its methodological innovations include similarity-guided negative sampling, cross-omics graph alignment, and an MLP-based encoder—jointly ensuring topological fidelity while drastically reducing memory consumption. Experiments demonstrate that SCoPE significantly improves cell-type clustering accuracy on single-cell data and achieves state-of-the-art performance in batch-integrated multi-omics analysis, matching full-graph methods using only limited subgraph views.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Motivation: Network-based analyses of omics data are widely used, and while many of these methods have been adapted to single-cell scenarios, they often remain memory- and space-intensive. As a result, they are better suited to batch data or smaller datasets. Furthermore, the application of network-based methods in multi-omics often relies on similarity-based networks, which lack structurally-discrete topologies. This limitation may reduce the effectiveness of graph-based methods that were initially designed for topologies with better defined structures. Results: We propose Subset-Contrastive multi-Omics Network Embedding (SCONE), a method that employs contrastive learning techniques on large datasets through a scalable subgraph contrastive approach. By exploiting the pairwise similarity basis of many network-based omics methods, we transformed this characteristic into a strength, developing an approach that aims to achieve scalable and effective analysis. Our method demonstrates synergistic omics integration for cell type clustering in single-cell data. Additionally, we evaluate its performance in a bulk multi-omics integration scenario, where SCONE performs comparable to the state-of-the-art despite utilising limited views of the original data. We anticipate that our findings will motivate further research into the use of subset contrastive methods for omics data.

Problem

• Memory-intensive network-based omics methods for single-cell data
• Similarity-based networks lack structurally-discrete topologies in multi-omics
• Scalable and effective analysis for large multi-omics datasets

Innovation

• Uses contrastive learning on large datasets
• Employs scalable subgraph contrastive approach
• Transforms pairwise similarity into strength