Erdafitinib

Evidence Level: L5 Predicted Indications: 50

Quick Overview

Item Value
Drug Name Erdafitinib
DrugBank ID DB12147
Brand Names (EU) Balversa
Evidence Level L5
Predicted Indications 50
Top Prediction Score 99.38%

Approved Indication (EMA)

Balversa as monotherapy is indicated for the treatment of adult patients with unresectable or metastatic urothelial carcinoma (UC), harbouring susceptible FGFR3 genetic alterations who have previously received at least one line of therapy containing a PD-1 or PD-L1 inhibitor in the unresectable or metastatic treatment setting (see section 5.1).


Predicted New Indications

TxGNN model predictions for potential drug repurposing:

Rank Indication Score Source
1 pulmonary hypertension 99.38% DL
2 kyphoscoliotic heart disease 99.27% DL
3 amenorrhea (disease) 99.26% DL
4 rheumatoid arthritis 99.25% DL
5 amyotrophic lateral sclerosis 99.06% DL
6 brachydactyly-syndactyly syndrome 99.03% DL
7 amyotrohpic lateral sclerosis type 22 98.91% DL
8 amyotrophic lateral sclerosis, susceptibility to 98.88% DL
9 axial spondylometaphyseal dysplasia 98.83% DL
10 Mills syndrome 98.78% DL
11 multiple endocrine neoplasia 98.75% DL
12 colobomatous microphthalmia-rhizomelic dysplasia syndrome 98.73% DL
13 trichomegaly-retina pigmentary degeneration-dwarfism syndrome 98.72% DL
14 bilateral parasagittal parieto-occipital polymicrogyria 98.64% DL
15 lethal arthrogryposis-anterior horn cell disease syndrome 98.58% DL
16 lower motor neuron syndrome with late-adult onset 98.47% DL
17 monomelic amyotrophy 98.39% DL
18 hypoalphalipoproteinemia 98.25% DL
19 infectious bovine rhinotracheitis 98.25% DL
20 malignant catarrh 98.25% DL

Showing top 20 of 50 predictions.


About TxGNN Predictions

Prediction Sources

Source Description
KG Knowledge Graph - Network topology-based associations
DL Deep Learning - Neural network score prediction

Evidence Levels

Level Definition
L1 Multiple Phase 3 RCTs / Systematic Reviews
L2 Single RCT or multiple Phase 2 trials
L3 Observational studies / Large case series
L4 Preclinical / Mechanistic / Case reports
L5 AI prediction only (current)

Clinical Validation Needed

Research Use Only: These predictions are computational hypotheses that require clinical validation. They should NOT be used for clinical decision-making.

Next Steps for Validation

  1. Literature Review: Search PubMed for existing evidence
  2. Clinical Trial Search: Check ClinicalTrials.gov for ongoing studies
  3. Mechanistic Analysis: Evaluate biological plausibility
  4. Preclinical Studies: Conduct in vitro/in vivo validation
  5. Clinical Trials: Design and conduct human studies

Data Access


Citation

If using this data, please cite:

@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}
}

Disclaimer: This report is for research purposes only and does not constitute medical advice. Drug repurposing predictions require rigorous clinical validation before any therapeutic application.

Copyright © 2026 EuTxGNN Project. For research purposes only. Not medical advice.