About This Project

Accelerating drug repurposing evidence validation with AI — from prediction to evidence at a glance.

Project Background

SgTxGNN is a drug repurposing research platform based on Harvard's TxGNN model published in Nature Medicine. Unlike other prediction tools, this platform not only provides AI prediction scores but also integrates clinical evidence from ClinicalTrials.gov, PubMed, and other sources, enabling researchers to quickly assess prediction credibility.


Team

Item Information
Project Maintainer Yao.Care
Model Basis Harvard TxGNN (Zitnik Lab)
Last Updated March 2026

Academic Foundation

This project’s AI prediction model is based on:

Huang, K., et al. (2023). A foundation model for clinician-centered drug repurposing. Nature Medicine. DOI: 10.1038/s41591-023-02233-x


What is Drug Repurposing?

Drug Repurposing is discovering new therapeutic uses for existing drugs. Compared to developing new drugs (10-15 years, $1-2 billion), drug repurposing takes only 3-5 years and $100-300 million, with existing human safety data and lower failure risk.

Comparison New Drug Development Drug Repurposing
Development Time 10-15 years 3-5 years
Development Cost $1-2 billion $100-300 million
Safety Data Must establish new Existing human data
Failure Risk Very high (>90%) Lower
The advantage of drug repurposing: drug safety, pharmacokinetics, and manufacturing processes are already validated, allowing direct entry into clinical efficacy trials.

What is TxGNN?

TxGNN is a deep learning model developed by Harvard Medical School's Zitnik Lab team, published in Nature Medicine. It is the first foundation model designed for clinician-centered drug repurposing.

"TxGNN integrates a knowledge graph of 17,080 biomedical entities, using graph neural networks to learn complex relationships between nodes and predict drug efficacy for rare diseases." — Huang et al., Nature Medicine (2023)

Technical Features

  1. Knowledge Graph: Integrates 17,080 nodes including drugs, diseases, genes, and proteins
  2. Graph Neural Network: Learns complex relationships between nodes
  3. Prediction Capability: Predicts which diseases a drug might be effective for

Data Sources

This platform integrates multiple authoritative public data sources including AI predictions, clinical trials, academic literature, drug information, Singapore market information, and drug interaction data.

Data Type Source Description
AI Prediction TxGNN Harvard knowledge graph prediction model
Clinical Trials ClinicalTrials.gov Global clinical trial registry
Academic Literature PubMed Biomedical literature database
Drug Information DrugBank Drug and target database
Singapore Market HSA Health Sciences Authority

Project Scale

Item Count
Drug Reports 745
Repurposing Candidates 31,543
Diseases Covered 4,589
Dual Validated (KG+DL) 1,217

How to Cite

If you use data from this platform, please use the following format:

APA Format

Yao.Care. (2026). SgTxGNN: Drug Repurposing Validation Reports for Singapore HSA Drugs (v1.0.0). https://sgtxgnn.yao.care/

Citing the Original Model

If using TxGNN prediction results, please also cite the original paper:

@article{huang2023txgnn,
  title={A foundation model for clinician-centered drug repurposing},
  author={Huang, Kexin and others},
  journal={Nature Medicine},
  year={2023},
  doi={10.1038/s41591-023-02233-x}
}

Contact & Feedback

For questions or suggestions, please contact us through:


Disclaimer
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: SgTxGNN Research Team

Copyright © 2026 Yao.Care. For research purposes only. Not medical advice.