# Knowledge-graph-enhanced multi-scale modeling for drug-drug interaction prediction

## TL;DR

ALG-DDI is a new model that uses drug features and a knowledge graph to predict drug interactions more accurately than previous methods.

## Contribution

ALG-DDI introduces a multi-scale modeling approach that integrates drug attributes, local correlations, and global knowledge graph semantics for DDI prediction.

## Key findings

- ALG-DDI outperforms existing state-of-the-art methods in drug-drug interaction prediction.
- The model integrates attribute, local, and global drug information using a transformer-based fusion mechanism.
- Extensive evaluations on multiple datasets confirm the model's superior performance and generalization.

## Abstract

Drug-drug interaction (DDI) prediction is crucial for understanding combined medication effects and preventing adverse reactions. Traditional machine learning methods rely on handcrafted features and lack generalization, while existing deep learning approaches often fail to capture global and multi-scale drug relationships. To overcome these limitations, we propose ALG-DDI, a multi-scale feature fusion model that integrates three types of drug information: attribute (intrinsic drug structure), local correlations (with proteins and diseases), and global semantic information from the medical knowledge graph PrimeKG. We encode these using attribute masking, the idea of RGCN and GraphSAGE, and ComplEx, respectively. A transformer encoder with attention mechanism then fuses these multi-scale representations. The resulting drug pair vector is fed into a fully connected network for DDI prediction, which we also extend to DDI event prediction. Extensive evaluations on three datasets—including comparative experiments, cross-validation, retrospective analysis, and case studies—demonstrate that ALG-DDI outperforms existing state-of-the-art methods.

ALG-DDI integrates multi-scale drug features—from structural attributes to global knowledge graph semantics—using a transformer to predict drug-drug interactions. The model outperforms existing methods, offering a generalized, accurate tool for understanding combined medication effects and improving clinical safety.