Advances in Cell-Type Identification using Heterophily-Aware Graph and Hypergraph Neural Networks on Single-Cell Transcriptomics - PhD Dissertation Defense by: Mahshad Hashemi

Thursday, December 18, 2025 - 11:00

The School of Computer Science is pleased to present…

Advances in Cell-Type Identification using Heterophily-Aware Graph and Hypergraph Neural Networks on Single-Cell Transcriptomics

PhD Dissertation Defense by: Mahshad Hashemi
Date: December 18, 2025
Time: 11:00 AM – 2:00 PM
Location: Essex Hall, Room 122

 

Abstract:

Single-cell RNA sequencing (scRNA-seq) enables detailed cell-type identification, but most methods rely only on expression similarity and overlook that cells communicate through ligand–receptor (LR) interactions. LR-based graphs and hypergraphs capture this biology but are highly heterophilic, causing standard GNNs to oversmooth and lose class separability. This dissertation develops models that remain accurate under such conditions. First, we construct LR-informed graphs for Baron pancreas datasets, quantify their low homophily, and benchmark classical and heterophily-aware GNNs under a consistent evaluation protocol. Second, we introduce HeteroGraphNet, which uses adaptive random walks with restart and a gated bi-kernel design to capture informative neighborhoods while separating homophilic and heterophilic signals. Finally, we extend LR modeling to hypergraphs to represent higher-order communication events. Together, these contributions form a reproducible pipeline for biologically grounded, heterophily-aware graph and hypergraph neural network cell-type prediction.

Keywords: Single-cell RNA-seq, L-R Communication, Heterophily, Graph Neural Networks, Hypergraph Neural Networks

 

Doctoral Committee:
Internal Reader: Dr. Jianguo Lu
Internal Reader: Dr. Pooya Moradianzade       
External Reader: Dr. Mitra Mirhassani
External Examiner: Dr. Sheridan Houghten (Brock University)            
Advisor: Dr. Luis Rueda and Dr. Alioune Ngom
Chair:    TBD