A Multi-Scale Graph Neural Process with Cross-Drug Co-Attention for Drug-Drug Interactions Prediction

2025-09-18

AI Summary

Existing DDI prediction methods struggle to jointly model local functional groups and global topological structures of molecules, while lacking the capability to quantify prediction confidence. To address these limitations, we propose a multi-scale graph neural network framework: (1) a multi-scale message-passing mechanism captures structural information at varying granularities; (2) cross-drug collaborative attention fuses heterogeneous molecular representations; and (3) neural processes are incorporated into DDI prediction for the first time, enabling end-to-end uncertainty estimation. Evaluated on multiple benchmark datasets, our method significantly outperforms state-of-the-art models in both accuracy and generalization. It achieves superior predictive performance while providing calibrated confidence estimates—thereby offering high-precision, high-reliability computational support for drug safety monitoring and personalized pharmacotherapy.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Graphical Models
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Accurate prediction of drug-drug interactions (DDI) is crucial for medication safety and effective drug development. However, existing methods often struggle to capture structural information across different scales, from local functional groups to global molecular topology, and typically lack mechanisms to quantify prediction confidence. To address these limitations, we propose MPNP-DDI, a novel Multi-scale Graph Neural Process framework. The core of MPNP-DDI is a unique message-passing scheme that, by being iteratively applied, learns a hierarchy of graph representations at multiple scales. Crucially, a cross-drug co-attention mechanism then dynamically fuses these multi-scale representations to generate context-aware embeddings for interacting drug pairs, while an integrated neural process module provides principled uncertainty estimation. Extensive experiments demonstrate that MPNP-DDI significantly outperforms state-of-the-art baselines on benchmark datasets. By providing accurate, generalizable, and uncertainty-aware predictions built upon multi-scale structural features, MPNP-DDI represents a powerful computational tool for pharmacovigilance, polypharmacy risk assessment, and precision medicine.

Problem

• Predicting drug-drug interactions across molecular scales
• Capturing structural information from local to global levels
• Quantifying prediction confidence for medication safety

Innovation

• Multi-scale graph neural process framework
• Cross-drug co-attention mechanism fusion
• Neural process module uncertainty estimation