yao-care/ZaTxGNN

ZaTxGNN — Drug repurposing prediction and evidence validation platform for SAHPRA-approved medicines in South Africa. Developed by 藥提醒科技有限公司 (yao.care) # ZaTxGNN - South Africa: Drug Repurposing > 本專案由 **藥提醒科技有限公司**（yao.care）開發與維運。 > ZaTxGNN 站台： ｜產品總覽： Drug repurposing predictions for South Africa SAHPRA-approved drugs using the TxGNN model. ## Disclaimer - The results of this project are for research purposes only and do not constitute medical advice. - Drug repurposing candidates require clinical validation before application. ## Project Overview ### Report Statistics | Item | Count | |------|------| | **Drug Reports** | 455 | | **Total Predictions** | 7,786,582 | | **Unique Drugs** | 455 | | **Unique Indications** | 17,081 | | **DDI Data** | 302,516 | | **DFI Data** | 857 | | **DHI Data** | 35 | | **DDSI Data** | 8,359 | | **FHIR Resources** | 455 MK / 50,000 CUD | ### Evidence Level Distribution | Evidence Level | Report Count | Description | |---------|-------|------| | **L1** | 0 | Multiple Phase 3 RCTs | | **L2** | 0 | Single RCT or multiple Phase 2 | | **L3** | 0 | Observational studies | | **L4** | 0 | Preclinical / mechanistic studies | | **L5** | 455 | Computational prediction only | ### By Source | Source | Predictions | |------|------| | KG | 7,017,754 | | KG + DL | 737,866 | | DL | 30,962 | ### By Confidence | Confidence | Predictions | |------|------| | very_high | 30,401 | | high | 723,690 | | medium | 7,024,859 | | low | 7,632 | --- ## Prediction Methods | Method | Speed | Accuracy | Requirements | |------|------|--------|----------| | Knowledge Graph | Fast (seconds) | Lower | No special requirements | | Deep Learning | Slow (hours) | Higher | Conda + PyTorch + DGL | ### Knowledge Graph Method ```bash uv run python scripts/run_kg_prediction.py ``` | Metric | Value | |------|------| | SAHPRA Total Drugs | 4,206 | | Repurposing Candidates | 7,755,620 | ### Deep Learning Method ```bash conda activate txgnn PYTHONPATH=src python -m zatxgnn.predict.txgnn_model ``` | Metric | Value | |------|------| | Total DL Predictions | 741,593 | | Unique Drugs | 455 | | Unique Indications | …