Data Sources

SgTxGNN integrates data from multiple authoritative sources to provide comprehensive drug repurposing predictions and evidence.

---

Primary Sources

TxGNN Model

Source: Harvard Medical School, Zitnik Lab

The core prediction engine, published in Nature Medicine (2023).

• Project Page
• Paper
• Dataset

Singapore HSA

Source: Health Sciences Authority, Singapore

Drug registration data for Singapore-approved medications.

• HSA Website
• data.gov.sg

---

Evidence Sources

ClinicalTrials.gov

Source: U.S. National Library of Medicine

Global registry of clinical trials.

• Website
• API Documentation

PubMed

Source: U.S. National Library of Medicine

Biomedical literature database.

• Website
• API Documentation

DrugBank

Source: University of Alberta

Comprehensive drug and target database.

• Website
• Data used under academic license

---

Data Processing

Drug Mapping

1. HSA drug names extracted from registration data
2. Normalized using chemical name standardization
3. Mapped to DrugBank identifiers
4. Successfully mapped: 745 drugs

Prediction Generation

1. DrugBank IDs matched to TxGNN knowledge graph
2. Knowledge Graph predictions generated
3. Deep Learning predictions generated
4. Results combined and deduplicated

---

Update Schedule

Source	Last Updated	Frequency
TxGNN Model	2023	As published
HSA Data	March 2026	Quarterly
DrugBank	2025	Annual

---

Licensing

• TxGNN: Academic use permitted
• HSA Data: Open Government License
• DrugBank: Academic license
• PubMed/ClinicalTrials: Public domain

---

Citation

When using SgTxGNN data, please cite:

1. This platform (see About for citation format)
2. Original TxGNN paper (Huang et al., Nature Medicine 2023)
3. Relevant data sources as appropriate