Heterogeneous Graph Contrastive Learning for Drug-Gene-Disease Motif Prediction
- 1University of North Carolina at Chapel Hill
Abstract
Drug repurposing and target discovery offer critical strategies for advancing therapeutic development by uncovering the potential biological pathways and novel associations among drugs, genes, and diseases. However, experimental discovery remains expensive and time-consuming, which limits the scalability of large-scale studies. In addition, existing computational approaches often struggle to effectively integrate heterogeneous biomedical data, capture the complex higher-order topological signatures of biological interactomes, and generalize to unseen entities. Here, we present HANAMI (Heterogeneous grAph coNtrastive leArning for drug-gene-disease Motif predIction), a multi-view deep graph learning framework designed to model complex interactions among drugs, genes, and diseases. HANAMI integrates diverse heterogeneous biomedical knowledge, including chemical structures, genomic sequences, and clinical phenotypes, and leverages relation-aware topology encoding, structure-aware aggregation, and contrastive learning to enable accurate motif prediction with biological context from the network. Systematic evaluation on benchmark datasets shows that HANAMI achieves up to 6% improvements over existing state-of-the-art methods in predicting drug-gene-disease motifs. The framework further demonstrates strong inductive generalization, maintaining an [~]18% performance advantage in zero-shot settings involving previously unseen entities. Beyond predictive performance, HANAMI effectively prioritizes drug-disease relationships investigated in Phase II or III trials while identifying candidate genes that suggest plausible mechanistic links. Together, HANAMI provides a computational framework for interpreting complex biomedical interactions, offering a scalable foundation to accelerate drug repurposing and therapeutic innovation.
Related
- Legal judgment prediction via dynamic task graph and keyword-aware contrastive learning
- Predicting miRNA–Disease Associations Based on Contrastive Learning of Linear and Nonlinear Features
- How effective are contrastive learning-based approaches for activity-cliff prediction?
- Enhancing structural to functional brain network prediction using topological graph learning
- Mitigating Class Imbalance in Graph-Structured Data via Hierarchical Learning: Insights from Protein Binding Site Prediction
BibTeX
@misc{xie2026heterogeneous,
title = {{Heterogeneous Graph Contrastive Learning for Drug-Gene-Disease Motif Prediction}},
author = {H. Xie and Y. Gao and S. Ke and C. Chen},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.21.752883},
url = {https://www.biorxiv.org/content/10.64898/2026.09.21.752883v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Heterogeneous Graph Contrastive Learning for Drug-Gene-Disease Motif Prediction
AU - H. Xie
AU - Y. Gao
AU - S. Ke
AU - C. Chen
PY - 2026
DA - 2026/09/21
PB - bioRxiv
DO - 10.64898/2026.09.21.752883
UR - https://www.biorxiv.org/content/10.64898/2026.09.21.752883v1
AB - Drug repurposing and target discovery offer critical strategies for advancing therapeutic development by uncovering the potential biological pathways and novel associations among drugs, genes, and diseases. However, experimental discovery remains expensive and time-consuming, which limits the scalability of large-scale studies. In addition, existing computational approaches often struggle to effectively integrate heterogeneous biomedical data, capture the complex higher-order topological signatures of biological interactomes, and generalize to unseen entities. Here, we present HANAMI (Heterogeneous grAph coNtrastive leArning for drug-gene-disease Motif predIction), a multi-view deep graph learning framework designed to model complex interactions among drugs, genes, and diseases. HANAMI integrates diverse heterogeneous biomedical knowledge, including chemical structures, genomic sequences, and clinical phenotypes, and leverages relation-aware topology encoding, structure-aware aggregation, and contrastive learning to enable accurate motif prediction with biological context from the network. Systematic evaluation on benchmark datasets shows that HANAMI achieves up to 6% improvements over existing state-of-the-art methods in predicting drug-gene-disease motifs. The framework further demonstrates strong inductive generalization, maintaining an [~]18% performance advantage in zero-shot settings involving previously unseen entities. Beyond predictive performance, HANAMI effectively prioritizes drug-disease relationships investigated in Phase II or III trials while identifying candidate genes that suggest plausible mechanistic links. Together, HANAMI provides a computational framework for interpreting complex biomedical interactions, offering a scalable foundation to accelerate drug repurposing and therapeutic innovation.
ER -