Drug Repurposing: From Data to Evidence
SgTxGNN is a drug repurposing prediction platform based on Harvard's TxGNN model. We use AI to predict 18,069 drug repurposing candidates and provide evidence-based validation reports for 745 Singapore HSA-approved medications.
Browse High Evidence Drugs Learn Methodology
Drug Search
Enter a drug name or disease name to search for repurposing possibilities and clinical evidence. Supports generic names, brand names, and disease keywords.
What Makes Us Different
Most drug repurposing tools only provide "possibly effective" scores. SgTxGNN integrates ClinicalTrials.gov, PubMed literature, drug interactions, and more — with L1-L5 evidence classification to show which predictions are worth pursuing.
Each report integrates clinical trial IDs (NCT), literature indices (PMID), and Singapore HSA license information with complete evidence traceability.
L1 (Multiple Phase 3 RCTs) to L5 (Model prediction only) with Go / Proceed / Hold recommendations for quick candidate screening.
Focused on HSA-registered medications covering 745 drugs and 4,589 predicted indications. Reports include Singapore license status.
1,217 predictions validated by both Knowledge Graph and Deep Learning methods, providing higher confidence for prioritization.
Key Statistics
Prediction Sources
| Source | Count | Description |
|---|---|---|
| KG+DL | 1,217 | Both Knowledge Graph and Deep Learning agree — highest confidence |
| DL | 27,883 | Deep Learning predictions with confidence scores |
| KG | 2,443 | Knowledge Graph predictions based on biological relationships |
Quick Navigation
| Category | Description | Link |
|---|---|---|
| High Evidence | L1-L2, prioritize for evaluation | View Drugs |
| Medium Evidence | L3-L4, needs additional evidence | View Drugs |
| Predictions Only | L5, research direction reference | View Drugs |
| Full Drug List | All 745 drugs (searchable) | Drug List |
| Methodology | How predictions are made | Methodology |
| Downloads | CSV / JSON formats | Downloads |
About This Project
This system uses Harvard Zitnik Lab's TxGNN deep learning model published in Nature Medicine to predict potential new indications for Singapore HSA-approved medications.
"TxGNN is the first foundation model designed for clinician-centered drug repurposing, integrating knowledge graphs and deep learning to predict drug efficacy for rare diseases." — Huang et al., Nature Medicine (2023)
Data Sources
This report is for academic research purposes only and does not constitute medical advice. Please follow physician instructions for medication use. Any drug repurposing decisions require complete clinical validation and regulatory approval.
Last Review: 2026-03-03 | Reviewer: 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).
SgTxGNN is the Singapore 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.