Back

Drug repurposing for rare diseases via a gene-bridged heterogeneous knowledge graph and graph attention network

Ramani, D.

2026-06-21 Systems Biology
10.64898/2026.06.16.732556 bioRxiv
Show abstract

Rare diseases are severely underserved by pharmacological treatments, and computational drug repurposing offers a cost-effective alternative to de novo discovery. We present a reproducible end-to-end pipeline integrating 3,961 rare disease-gene associations from Orphadata with 98,239 gene-drug records from DisGeNET through a multi-stage harmonization pipeline (HGNC symbol standardization and RapidFuzz fuzzy matching), yielding a large-scale gene-bridged rare disease tripartite knowledge graph -- to our knowledge the largest such graph constructed exclusively from Orphadata and DisGeNET-- comprising 15,454 nodes and 35,131 edges spanning 2,249 clinically distinct rare diseases. A Graph Attention Network (GAT) trained on node-type classification as a pretext task achieves macro F1 = 0.651 and ROC-AUC = 0.818 on a stratified held-out test set, with stable performance across five evaluation partitions (SD [&le;] 0.007). Drug candidate retrieval via cosine similarity in the GAT embedding space achieves Hits@10 = 0.400 across 200 evaluated disorders (vs. < 0.001 random baseline), with the clinically validated drug NITISINONE recovered at rank 4 for a tyrosine catabolism pathway disorder without pathway annotations. A deployment-ready interface is publicly available on HuggingFace Spaces.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.