Enhanced Drug-drug Interaction Prediction Using Adaptive Knowledge Integration

2026-03-13

AI Summary

This work addresses key challenges in drug–drug interaction prediction—namely data imbalance, mechanistic complexity, and poor generalization to unseen drug combinations—by proposing an adaptive knowledge fusion framework. The approach integrates prior pharmacological knowledge into a large language model and employs reinforcement learning to optimize strategies for knowledge extraction and synthesis. By aligning the model’s reasoning with established scientific principles, the framework enables highly effective few-shot learning grounded in domain knowledge. Experimental results demonstrate that the method significantly outperforms existing baselines under few-shot settings, achieving notable improvements in both prediction accuracy and generalization capability across diverse drug interaction scenarios.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Mixture of Experts (MoE)
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Drug-drug interaction event (DDIE) prediction is crucial for preventing adverse reactions and ensuring optimal therapeutic outcomes. However, existing methods often face challenges with imbalanced datasets, complex interaction mechanisms, and poor generalization to unknown drug combinations. To address these challenges, we propose a knowledge augmentation framework that adaptively infuses prior drug knowledge into a large language model (LLM). This framework utilizes reinforcement learning techniques to facilitate adaptive knowledge extraction and synthesis, thereby efficiently optimizing the strategy space to enhance the accuracy of LLMs for DDIE predictions. As a result of few-shot learning, we achieved a notable improvement compared to the baseline. This approach establishes an effective framework for scientific knowledge learning for DDIE predictions.

Problem

• Drug-drug interaction
• Imbalanced datasets
• Generalization
• Interaction mechanisms
• Prediction accuracy

Innovation

• adaptive knowledge integration
• drug-drug interaction prediction
• large language model
• reinforcement learning
• few-shot learning