August 2, 2025Open Access

Hypergraph Neural Networks Reveal Spatial Domains from Single-cell Transcriptomics Data

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Hypergraph neural networks uncover spatial domains in single-cell transcriptomics, suggesting better model relationships among cell clusters.

MAIN FINDING: Hypergraph neural networks effectively reveal spatial domains from single-cell transcriptomics data.
KEY EVIDENCE: Our model integrates histological image features and gene expression profiles to learn meaningful representations.
APPROACH: The framework uses hyperedges from dense overlapping subgraphs and combines them with autoencoders.
SIGNIFICANCE: This method enhances the understanding of complex cell relationships in spatial transcriptomics.

Soltani et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

August 2, 2025Open Access

View Full Paper

Ask AI

Bookmark

Authors

Hypergraph neural networks uncover spatial domains in single-cell transcriptomics, suggesting better model relationships among cell clusters.

MAIN FINDING: Hypergraph neural networks effectively reveal spatial domains from single-cell transcriptomics data.
KEY EVIDENCE: Our model integrates histological image features and gene expression profiles to learn meaningful representations.
APPROACH: The framework uses hyperedges from dense overlapping subgraphs and combines them with autoencoders.
SIGNIFICANCE: This method enhances the understanding of complex cell relationships in spatial transcriptomics.

Soltani et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark