AIM-DDI: A Model-Agnostic Multimodal Integration Module for Drug-Drug Interaction Prediction

TL;DR

AIM-DDI introduces a flexible, architecture-independent module for integrating diverse drug data modalities, significantly enhancing unseen-drug drug-drug interaction prediction performance.

Contribution

It proposes a model-agnostic multimodal integration module that improves unseen-drug DDI prediction by representing heterogeneous data as shared tokens and modeling their dependencies.

Findings

AIM-DDI consistently improves DDI prediction across models.

Strongest gains observed in the most challenging unseen-drug setting.

The module enhances robustness and generalization in DDI prediction.

Abstract

Drug-drug interaction (DDI) prediction is a critical task in computational biomedicine, as adverse interactions between co-administered drugs can cause severe side effects and clinical risks. A key challenge is unseen-drug generalization, where interactions must be predicted for drugs not observed during training. Although multimodal DDI models exploit diverse drug-related information, their fusion mechanisms are often tied to specific prediction architectures, limiting their reuse across models. To address this, we propose AIM-DDI, an architecture-independent multimodal integration module that represents heterogeneous modality information as tokens in a shared latent space. By modeling dependencies across modality tokens through a unified fusion module, AIM-DDI enables model-agnostic integration of structural, chemical, and semantic drug signals across different DDI prediction architectures. Extensive evaluations across diverse DDI models and DrugBank-based settings show that AIM-DDI consistently improves prediction performance, with the strongest gains under the most challenging both-unseen setting where neither drug in a test pair is observed during training. These results suggest that treating multimodal integration as a reusable module, rather than a model-specific fusion component, is an effective strategy for robust unseen-drug DDI prediction.