Heterophily-Aware Hypergraph Neural Networks for Cell Type Prediction Using Ligand-Receptor-Informed Single-Cell RNA-seq Data
PhD. Seminar by: Mahshad Hashemi
Date: Thursday, November 13, 2025
Time: 11:00 AM
Location: MH109 (Memorial Hall)
Accurately predicting cell types from single-cell RNA sequencing (scRNA-seq) data requires modelling complex cellular interactions that extend beyond pairwise transcriptional similarity. Ligand-receptor-mediated signalling is a key driver of such interactions, often spanning diverse cell types and exhibiting both homophilic and heterophilic patterns. In this work, we introduce a biologically informed framework for cell type prediction based on heterophily-aware hypergraph neural networks (HGNNs), where hyperedges represent multi-cell communication events derived from curated ligand–receptor pairs. This construction enables higher-order modelling of intercellular signalling and captures the combinatorial nature of ligand–receptor communication. We evaluate nine state-of-the-art hypergraph-based models, including HGNN, HyperGCN, UniGCNII, HyperND, AllDeepSets, AllSetTransformer, ED-HNN, SheafHyperGNN, and HyperUFG, which encompass diverse message passing paradigms such as spectral convolutions, diffusion dynamics, permutation-invariant set operations, and sheaf-theoretic encoding. Experiments on six benchmark scRNA-seq datasets reveal that architectures tailored to heterophilic structure substantially outperform their homophily-oriented counterparts.
Our results underscore the importance of both biologically grounded hypergraph design and heterophily-aware learning in advancing automated cell type annotation for complex tissue systems.
Internal Reader: Dr. Pooya Moradian Zadeh
Internal Reader: Dr. Jianguo Lu
External Reader: Dr. Mitra Mirhassani
Advisor (s): Dr. Luis Rueda, Dr. Alioum Ngom
