MolBridge: Atom-Level Joint Graph Refinement for Robust Drug-Drug Interaction Event Prediction

2025-10-23

AI Summary

Existing DDI prediction methods rely on isolated drug representations, limiting their ability to model atom-level intermolecular interactions and resulting in poor generalization to complex molecular structures, long-tailed DDI types, and inductive settings. To address this, we propose MolBridge—a framework that constructs joint atomic graphs for drug pairs to explicitly encode intermolecular atomic interactions. It introduces a structural consistency regularization module to mitigate over-smoothing in graph neural networks, enabling synergistic learning of fine-grained local interactions and global topological patterns. Furthermore, MolBridge integrates multi-scale molecular contextual information and employs an iterative feature refinement mechanism. Evaluated on two benchmark datasets, MolBridge significantly outperforms state-of-the-art methods, particularly in identifying rare DDI types and performing inductive predictions. It achieves strong generalization capability while maintaining mechanistic interpretability.

Technology Category

• Machine Learning: Structured Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Drug combinations offer therapeutic benefits but also carry the risk of adverse drug-drug interactions (DDIs), especially under complex molecular structures. Accurate DDI event prediction requires capturing fine-grained inter-drug relationships, which are critical for modeling metabolic mechanisms such as enzyme-mediated competition. However, existing approaches typically rely on isolated drug representations and fail to explicitly model atom-level cross-molecular interactions, limiting their effectiveness across diverse molecular complexities and DDI type distributions. To address these limitations, we propose MolBridge, a novel atom-level joint graph refinement framework for robust DDI event prediction. MolBridge constructs a joint graph that integrates atomic structures of drug pairs, enabling direct modeling of inter-drug associations. A central challenge in such joint graph settings is the potential loss of information caused by over-smoothing when modeling long-range atomic dependencies. To overcome this, we introduce a structure consistency module that iteratively refines node features while preserving the global structural context. This joint design allows MolBridge to effectively learn both local and global interaction outperforms state-of-the-art baselines, achieving superior performance across long-tail and inductive scenarios. patterns, yielding robust representations across both frequent and rare DDI types. Extensive experiments on two benchmark datasets show that MolBridge consistently. These results demonstrate the advantages of fine-grained graph refinement in improving the accuracy, robustness, and mechanistic interpretability of DDI event prediction.This work contributes to Web Mining and Content Analysis by developing graph-based methods for mining and analyzing drug-drug interaction networks.

Problem

• Predicting drug-drug interaction events using atom-level molecular graph modeling
• Addressing limitations in capturing fine-grained inter-drug relationships
• Overcoming information loss in joint graph structures through refinement

Innovation

• Atom-level joint graph refinement for DDI prediction
• Structure consistency module preserves global structural context
• Fine-grained graph refinement improves accuracy and robustness