PepGB: Facilitating peptide drug discovery via graph neural networks
This work addresses the problem of accelerating peptide drug discovery for biomedical researchers by improving prediction accuracy and generalizability, though it appears incremental as it builds on existing graph neural network methods with specific enhancements.
The study tackled the challenge of predicting peptide-protein interactions (PepPIs) for drug discovery by proposing PepGB, a graph neural network framework that incorporates a fine-grained perturbation module and dual-view objective with contrastive learning, which greatly outperformed baselines and accurately identified PepPIs for novel targets and peptides. An extended version, diPepGB, addressed data imbalance in lead generation by using directed edges to represent binding strength, achieving superior performance in real-world assays.
Peptides offer great biomedical potential and serve as promising drug candidates. Currently, the majority of approved peptide drugs are directly derived from well-explored natural human peptides. It is quite necessary to utilize advanced deep learning techniques to identify novel peptide drugs in the vast, unexplored biochemical space. Despite various in silico methods having been developed to accelerate peptide early drug discovery, existing models face challenges of overfitting and lacking generalizability due to the limited size, imbalanced distribution and inconsistent quality of experimental data. In this study, we propose PepGB, a deep learning framework to facilitate peptide early drug discovery by predicting peptide-protein interactions (PepPIs). Employing graph neural networks, PepGB incorporates a fine-grained perturbation module and a dual-view objective with contrastive learning-based peptide pre-trained representation to predict PepPIs. Through rigorous evaluations, we demonstrated that PepGB greatly outperforms baselines and can accurately identify PepPIs for novel targets and peptide hits, thereby contributing to the target identification and hit discovery processes. Next, we derive an extended version, diPepGB, to tackle the bottleneck of modeling highly imbalanced data prevalent in lead generation and optimization processes. Utilizing directed edges to represent relative binding strength between two peptide nodes, diPepGB achieves superior performance in real-world assays. In summary, our proposed frameworks can serve as potent tools to facilitate peptide early drug discovery.