A Hybrid Computational Intelligence Framework with Metaheuristic Optimization for Drug-Drug Interaction Prediction

2025-10-08

AI Summary

Drug–drug interactions (DDIs) are a leading cause of preventable adverse drug events, making accurate DDI prediction critical for clinical medication safety. To address this, we propose a high-accuracy, interpretable DDI prediction framework: (1) dual molecular embeddings are constructed by integrating Mol2Vec and SMILES-BERT; (2) a rule-based clinical scoring metric (RBScore) is designed—requiring no interaction labels—to explicitly incorporate pharmacological knowledge; and (3) a three-stage metaheuristic optimization algorithm (RSmpl-ACO-PSO) automatically tunes hyperparameters of a lightweight classifier. Evaluated on the DrugBank dataset, our model achieves 0.911 ROC-AUC and 0.867 PR-AUC. Furthermore, it demonstrates strong generalizability in a real-world cohort of type 2 diabetes patients, validating its clinical applicability and robustness.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Search and Optimization: Metareasoning and Metaheuristics
• Machine Learning: Transparent, Interpretable, Explainable ML

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Drug-drug interactions (DDIs) are a leading cause of preventable adverse events, often complicating treatment and increasing healthcare costs. At the same time, knowing which drugs do not interact is equally important, as such knowledge supports safer prescriptions and better patient outcomes. In this study, we propose an interpretable and efficient framework that blends modern machine learning with domain knowledge to improve DDI prediction. Our approach combines two complementary molecular embeddings - Mol2Vec, which captures fragment-level structural patterns, and SMILES-BERT, which learns contextual chemical features - together with a leakage-free, rule-based clinical score (RBScore) that injects pharmacological knowledge without relying on interaction labels. A lightweight neural classifier is then optimized using a novel three-stage metaheuristic strategy (RSmpl-ACO-PSO), which balances global exploration and local refinement for stable performance. Experiments on real-world datasets demonstrate that the model achieves high predictive accuracy (ROC-AUC 0.911, PR-AUC 0.867 on DrugBank) and generalizes well to a clinically relevant Type 2 Diabetes Mellitus cohort. Beyond raw performance, studies show how embedding fusion, RBScore, and the optimizer each contribute to precision and robustness. Together, these results highlight a practical pathway for building reliable, interpretable, and computationally efficient models that can support safer drug therapies and clinical decision-making.

Problem

• Predicting drug-drug interactions to prevent adverse events
• Combining molecular embeddings with clinical knowledge
• Optimizing neural classifiers using metaheuristic strategies

Innovation

• Hybrid molecular embeddings combine structural and chemical features
• Rule-based clinical score injects pharmacological knowledge without labels
• Three-stage metaheuristic optimization balances exploration and refinement