MUDI: A Multimodal Biomedical Dataset for Understanding Pharmacodynamic Drug-Drug Interactions

2025/06/02 by Ba-Hoang Tran, Ngo, Tung-Lam, Duy-Cat Can +8
Biochemistry, Genetics and Molecular Biology · Computer Science · #Biomedical Text Mining and Ontologies #Computation and Language (cs.CL) #Computational Drug Discovery Methods #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimedia (cs.MM) #Quantitative Methods (q-bio.QM)

paper · pdf · doi:10.48550/arxiv.2506.01478

openalex publication_date 2025/06/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Understanding the interaction between different drugs (drug-drug interaction or DDI) is critical for ensuring patient safety and optimizing therapeutic outcomes. Existing DDI datasets primarily focus on textual information, overlooking multimodal data that reflect complex drug mechanisms. In this paper, we (1) introduce MUDI, a large-scale Multimodal biomedical dataset for Understanding pharmacodynamic Drug-drug Interactions, and (2) benchmark learning methods to study it. In brief, MUDI provides a comprehensive multimodal representation of drugs by combining pharmacological text, chemical formulas, molecular structure graphs, and images across 310,532 annotated drug pairs labeled as Synergism, Antagonism, or New Effect. Crucially, to effectively evaluate machine-learning based generalization, MUDI consists of unseen drug pairs in the test set. We evaluate benchmark models using both late fusion voting and intermediate fusion strategies. All data, annotations, evaluation scripts, and baselines are released under an open research license.

Citations

• HODDI: A Dataset of High-Order Drug-Drug Interactions for Computational Pharmacovigilance
• Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development
• BERTChem-DDI : Improved Drug-Drug Interaction Prediction from text using Chemical Structure Information
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing
• DrugBank 5.0: a major update to the DrugBank database for 2018
• Drug-Drug Interaction Extraction from Biomedical Text Using Long Short Term Memory Network
• Provenance-Centered Dataset of Drug-Drug Interactions
• Adam: A Method for Stochastic Optimization
• Novel Data-Mining Methodologies for Adverse Drug Event Discovery and Analysis

Related

• AttentionDDI: Siamese Attention-based Deep Learning method for drug-drug\n interaction predictions
• Predicting Drug-Drug Interactions from Heterogeneous Data: An Embedding\n Approach
• PKAG-DDI: Pairwise Knowledge-Augmented Language Model for Drug-Drug Interaction Event Text Generation
• Predicting Rich Drug-Drug Interactions via Biomedical Knowledge Graphs and Text Jointly Embedding
• Devil in the Tail: A Multi-Modal Framework for Drug-Drug Interaction Prediction in Long Tail Distinction