UsTxGNN Drug Repurposing Reports

AI-powered drug repurposing predictions for US FDA approved drugs using the TxGNN knowledge graph.

Research Use Only: The predictions on this site are for research purposes only and do not constitute medical advice. All drug repurposing candidates require clinical validation before any therapeutic application.

Overview

UsTxGNN leverages the TxGNN knowledge graph to identify potential new therapeutic uses for existing FDA-approved drugs. This approach, known as drug repurposing or drug repositioning, can accelerate the discovery of new treatments by building on established safety profiles.

Key Features

104,000+ FDA Drugs: Comprehensive coverage of US FDA approved medications
Knowledge Graph Predictions: Powered by TxGNN’s biomedical knowledge graph
Evidence Integration: Links to ClinicalTrials.gov, PubMed, and DrugBank
FHIR R4 Compatible: Standardized healthcare data exchange
SMART on FHIR: EHR integration ready

Data Sources

Source	Description
US FDA NDC	National Drug Code Directory
TxGNN	Therapeutic knowledge graph
DrugBank	Drug and target information
ClinicalTrials.gov	Clinical trial evidence
PubMed	Biomedical literature

API Access

FHIR R4 Endpoint

GET https://ustxgnn.yao.care/fhir/metadata

Available resources:

MedicationKnowledge - Drug information
ClinicalUseDefinition - Repurposing predictions

SMART on FHIR

Launch the SMART app from your EHR system:

https://ustxgnn.yao.care/smart/launch.html

Statistics

Metric	Value
Total FDA Drugs	104,047
DrugBank Mappings	7,958
Disease Ontology	17,081
Drug-Disease Relations	80,127

Citation

If you use UsTxGNN in your research, please cite:

@article{huang2023txgnn,
  title={A foundation model for clinician-centered drug repurposing},
  author={Huang, Kexin and others},
  journal={Nature Medicine},
  year={2023},
  publisher={Nature Publishing Group}
}

Disclaimer

This website provides computational predictions for research purposes only. The information presented here:

Does NOT constitute medical advice

Should NOT be used for clinical decision-making without proper validation

Requires independent clinical trial verification before any therapeutic application

Always consult qualified healthcare professionals for medical decisions.

Last updated: 2026-08-24

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).

UsTxGNN is the the United States 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.