Rethinking Drug-Drug Interaction Modeling as Generalizable Relation Learning

TL;DR

This paper introduces GenRel-DDI, a relation-centric learning framework for drug-drug interaction prediction that improves generalization to unseen drugs and pairs by learning transferable interaction patterns.

Contribution

It reformulates DDI prediction as a relation learning problem, enabling better generalization compared to existing molecule-centric models.

Findings

GenRel-DDI outperforms state-of-the-art methods on benchmarks.

Significant improvements in entity-disjoint evaluation scenarios.

Relation-level abstraction captures transferable interaction patterns.

Abstract

Drug-drug interaction (DDI) prediction is central to drug discovery and clinical development, particularly in the context of increasingly prevalent polypharmacy. Although existing computational methods achieve strong performance on standard benchmarks, they often fail to generalize to realistic deployment scenarios, where most candidate drug pairs involve previously unseen drugs and validated interactions are scarce. We demonstrate that proximity in the embedding spaces of prevailing molecule-centric DDI models does not reliably correspond to interaction labels, and that simply scaling up model capacity therefore fails to improve generalization. To address these limitations, we propose GenRel-DDI, a generalizable relation learning framework that reformulates DDI prediction as a relation-centric learning problem, in which interaction representations are learned independently of drug identities. This relation-level abstraction enables the capture of transferable interaction patterns that generalize to unseen drugs and novel drug pairs. Extensive experiments across multiple benchmark demonstrate that GenRel-DDI consistently and significantly outperforms state-of-the-art methods, with particularly large gains on strict entity-disjoint evaluations, highlighting the effectiveness and practical utility of relation learning for robust DDI prediction. The code is available at https://github.com/SZU-ADDG/GenRel-DDI.