DeepDR: an integrated deep-learning model web server for drug repositioning

2025-11-12

AI Summary

Drug repurposing faces challenges including high domain expertise requirements, labor-intensive workflows, and difficulties in model deployment. To address these, we present the first open-source, web-based platform supporting disease- and target-specific prediction. It integrates graph neural networks with multimodal biomedical data—encompassing drugs, diseases, genes, and pathways—and NLP-derived semantic features from 24 million PubMed abstracts. The platform uniquely unifies multiple deep learning architectures with a large-scale knowledge graph comprising 5.9 million edges, 107 relation types, and 15 categories of semantic associations. It delivers end-to-end automated predictions, high-accuracy recommendations, and interpretable visual analytics—freely accessible without registration. Its core innovation is a tripartite synergistic modeling framework jointly leveraging deep learning, knowledge graphs, and literature-derived semantics, substantially improving both predictive accuracy and biological interpretability. This provides computational and experimental researchers with an out-of-the-box tool for novel indication discovery.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Background: Identifying new indications for approved drugs is a complex and time-consuming process that requires extensive knowledge of pharmacology, clinical data, and advanced computational methods. Recently, deep learning (DL) methods have shown their capability for the accurate prediction of drug repositioning. However, implementing DL-based modeling requires in-depth domain knowledge and proficient programming skills. Results: In this application, we introduce DeepDR, the first integrated platform that combines a variety of established DL-based models for disease- and target-specific drug repositioning tasks. DeepDR leverages invaluable experience to recommend candidate drugs, which covers more than 15 networks and a comprehensive knowledge graph that includes 5.9 million edges across 107 types of relationships connecting drugs, diseases, proteins/genes, pathways, and expression from six existing databases and a large scientific corpus of 24 million PubMed publications. Additionally, the recommended results include detailed descriptions of the recommended drugs and visualize key patterns with interpretability through a knowledge graph. Conclusion: DeepDR is free and open to all users without the requirement of registration. We believe it can provide an easy-to-use, systematic, highly accurate, and computationally automated platform for both experimental and computational scientists.

Problem

• Predicting new drug indications using deep learning models
• Overcoming the need for domain expertise in drug repositioning
• Providing an automated platform for computational drug discovery

Innovation

• Integrated deep-learning platform for drug repositioning
• Leverages knowledge graph with 5.9 million relationships
• Provides interpretable visualizations through knowledge graphs