Drug Repurposing: From AI to Evidence
EuTxGNN uses the Harvard TxGNN model to predict drug repurposing candidates for 642 EMA-approved drugs, generating 1,491 potential new therapeutic uses.
Browse Drug Reports Learn Methodology
Drug Search
Enter a drug name or disease name to find repurposing predictions. Supports generic names, brand names, and disease keywords.
Key Features
Each report integrates clinical trial IDs (NCT), literature references (PMID), and EMA approval information for complete traceability.
L1 (Multiple Phase 3 RCTs) to L5 (AI prediction only) classification helps prioritize candidates for validation.
Focused on 642 EMA centrally-authorized medicines with 1,491 repurposing predictions ready for research.
FHIR R4 compliant API and SMART on FHIR app for seamless EHR integration.
Evidence Level Distribution
Quick Navigation
| Category | Description | Link |
|---|---|---|
| High Evidence | L1-L2, priority for clinical evaluation | View 50 drugs |
| Medium Evidence | L3-L4, requires additional validation | View 4 drugs |
| AI Predictions | L5, research direction reference | View 588 drugs |
| Full Drug List | All 642 drugs (searchable) | Drug List |
| Health News | Automated EU health news monitoring | View News |
| Data Downloads | CSV / JSON formats | Downloads |
| FHIR API | Integration endpoints | FHIR Metadata |
About This Project
EuTxGNN uses the TxGNN deep learning model published by Harvard’s Zitnik Lab in Nature Medicine to predict potential new therapeutic uses for EMA-approved medications.
“TxGNN is the first foundation model designed for clinician-centered drug repurposing, integrating knowledge graphs with deep learning to predict drug efficacy for rare diseases.” — Huang et al., Nature Medicine (2023)
Statistics
| Item | Count |
|---|---|
| Drug Reports | 642 |
| Repurposing Predictions | 1,491 |
| Unique Indications | 4,570 |
Data Sources
This report is for research purposes only and does not constitute medical advice. Drug use should follow physician guidance. Any drug repurposing decisions require complete clinical validation and regulatory review.
Last updated: 2026-03-05 | Maintainer: 藥提醒科技有限公司 (yao.care)
About the Developer
This platform is developed and operated by 藥提醒科技有限公司 (yao.care, company registration number 83620786, 12F, No. 220, Sec. 2, Taiwan Blvd., West Dist., Taichung City, Taiwan).
EuTxGNN is the the European Union site of the company’s “TxGNN Drug Repurposing” product line.
The same system is deployed across 30 countries and regions, each named {CC}TxGNN
(JpTxGNN, UsTxGNN, DETxGNN, and so on) at {cc}txgnn.yao.care.
Product overview: https://www.yao.care/medical/txgnn/.
The TxGNN model itself was developed by the Zitnik Lab at Harvard Medical School and published in Nature Medicine. This platform is the production system 藥提醒科技有限公司 built on top of that model, covering national drug-registration data integration, dual knowledge-graph and deep-learning prediction, PubMed / ClinicalTrials evidence grading, and SMART on FHIR electronic health record integration.