OpenDDI: A Comprehensive Benchmark for DDI Prediction

2026-01-31

AI Summary

Drug–drug interaction (DDI) prediction has long been hindered by the scarcity of high-quality data and the lack of standardized evaluation protocols. To address these challenges, this work introduces OpenDDI, a comprehensive benchmark that integrates six existing DDI datasets and two drug representations, augmented with three large language model (LLM)-enhanced datasets and a novel multimodal drug representation spanning five modalities. A unified, standardized evaluation protocol is established to systematically assess 20 state-of-the-art models across three downstream tasks. This study presents the first systematic unification of DDI prediction in terms of data, representation, and evaluation, revealing ten critical limitations of current approaches and providing the field with a rigorous framework and empirical guidance for future research.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Reasoning under Uncertainty: Uncertainty Representations

Application Category

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

Abstract

Drug-Drug Interactions (DDIs) significantly influence therapeutic efficacy and patient safety. As experimental discovery is resource-intensive and time-consuming, efficient computational methodologies have become essential. The predominant paradigm formulates DDI prediction as a drug graph-based link prediction task. However, further progress is hindered by two fundamental challenges: (1) lack of high-quality data: most studies rely on small-scale DDI datasets and single-modal drug representations; (2) lack of standardized evaluation: inconsistent scenarios, varied metrics, and diverse baselines. To address the above issues, we propose OpenDDI, a comprehensive benchmark for DDI prediction. Specifically, (1) from the data perspective, OpenDDI unifies 6 widely used DDI datasets and 2 existing forms of drug representation, while additionally contributing 3 new large-scale LLM-augmented datasets and a new multimodal drug representation covering 5 modalities. (2) From the evaluation perspective, OpenDDI unifies 20 SOTA model baselines across 3 downstream tasks, with standardized protocols for data quality, effectiveness, generalization, robustness, and efficiency. Based on OpenDDI, we conduct a comprehensive evaluation and derive 10 valuable insights for DDI prediction while exposing current limitations to provide critical guidance for this rapidly evolving field. Our code is available at https://github.com/xiaoriwuguang/OpenDDI

Problem

• Drug-Drug Interactions
• DDI prediction
• benchmark
• multimodal representation
• standardized evaluation

Innovation

• DDI prediction
• multimodal drug representation
• large language model
• standardized benchmark
• link prediction