Drug Repurposing: From AI to Evidence
DkTxGNN uses the Harvard TxGNN model to predict drug repurposing candidates for 501 DKMA-approved drugs, identifying potential new therapeutic uses.
Browse Drug Reports Learn Methodology
Drug Search
Enter a drug name or disease name to find repurposing predictions. Supports generic names, brand names, and disease keywords.
Key Features
Each report integrates clinical trial IDs (NCT), literature references (PMID), and DKMA approval information for complete traceability.
L1 (Multiple Phase 3 RCTs) to L5 (AI prediction only) classification helps prioritize candidates for validation.
Focused on 501 DKMA-approved medicines with repurposing predictions ready for research.
FHIR R4 compliant API and SMART on FHIR app for seamless EHR integration.
Quick Navigation
| Category | Description | Link |
|---|---|---|
| High Evidence | L1-L2, priority for clinical evaluation | View drugs |
| Medium Evidence | L3-L4, requires additional validation | View drugs |
| AI Predictions | L5, research direction reference | View drugs |
| Full Drug List | All 501 drugs (searchable) | Drug List |
| Health News | Automated health news monitoring | View News |
| FHIR API | Integration endpoints | FHIR Metadata |
About This Project
DkTxGNN uses the TxGNN deep learning model published by Harvard’s Zitnik Lab in Nature Medicine to predict potential new therapeutic uses for DKMA-approved medications.
“TxGNN is the first foundation model designed for clinician-centered drug repurposing, integrating knowledge graphs with deep learning to predict drug efficacy for rare diseases.” — Huang et al., Nature Medicine (2023)
Statistics
| Item | Count |
|---|---|
| Drug Reports | 501 |
| Regulatory Agency | Danish Medicines Agency (DKMA) |
Data Sources
This report is for research purposes only and does not constitute medical advice. Drug use should follow physician guidance. Any drug repurposing decisions require complete clinical validation and regulatory review.
Last updated: 2026-03-10 | Maintainer: 藥提醒科技有限公司 (yao.care)
Om udvikleren
Denne platform er udviklet og drives af 藥提醒科技有限公司 (yao.care, virksomhedsregistreringsnummer 83620786, 12F, No. 220, Sec. 2, Taiwan Blvd., West Dist., Taichung City, Taiwan).
DkTxGNN er Danmarks-sitet i virksomhedens produktlinje “TxGNN Drug Repurposing”.
Det samme system er udrullet i 30 lande og regioner, hver med navnet {CC}TxGNN
(JpTxGNN, UsTxGNN, DETxGNN og så videre) på {cc}txgnn.yao.care.
Produktoversigt: https://www.yao.care/medical/txgnn/.
Selve TxGNN-modellen er udviklet af Zitnik Lab ved Harvard Medical School og offentliggjort i Nature Medicine. Denne platform er det produktionssystem, 藥提醒科技有限公司 har bygget oven på den model, og dækker integration af nationale lægemiddelregistreringsdata, dobbelt forudsigelse med videngraf og deep learning, evidensgradering ud fra PubMed / ClinicalTrials samt SMART on FHIR-integration med elektroniske patientjournaler.