EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

KG-Bench: Benchmarking Graph Neural Network Algorithms for Drug Repurposing

Siqi Wei iD, Christo Sasi, Jelle Piepenbrock iD, Martijn A Huynen iD, Peter A C 't Hoen iD, SIMPATHIC Consortium

Bioinformatics · 08.05.2026

DOI: 10.1093/bioinformatics/btag159 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 08.05.2026. Verfasst von Siqi Wei und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department Medical BioSciences, Radboud University Medical Center, Nijmegen 6525 GA, The Netherlands. Hauptthemen laut MEDLINE: Graph Neural Networks, Drug Repositioning, Computational Biology. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union's Horizon Europe research and innovation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Drug repurposing leverages existing drugs for new indications, accelerating drug development. Computational methods integrating diverse biological and chemical data can systematically prioritize repurposing candidates, but standardized benchmarks for deep learning evaluation are lacking. We present KG-Bench, a GNN benchmarking framework designed to systematically compare the performance of different graph neural network (GNN) architectures on drug-disease association prediction using the Open Targets dataset. We constructed a knowledge graph (KG) of drugs, diseases, and targets, including annotations such as therapeutic area and molecular pathway, and ensured retrospective validation by leveraging regular dataset updates. To avoid data leakage, we removed redundant entities across splits. Results Benchmarking six GNN architectures, RGCN achieved the highest ranking performance (AUC: 0.91), while TransformerConv showed superior robustness under class imbalance (F1: 0.28 at 1:100 positive: negative ratio), characteristic of real drug repurposing datasets. KG-Bench also assesses bias, node/feature importance, and uses GNNExplainer for interpretability. Our open-source framework enables fair, reproducible evaluation of graph-based drug repurposing algorithms. Availability and Implementation Data and codes are available at https://github.com/cmbi/Benchmark_GNN_OpenTargets. Supplementary Information Supplementary data are available at Bioinformatics online.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Graph Neural NetworksDrug RepositioningComputational BiologyAlgorithmsBenchmarkingHumans

Autor:innen und Institutionen

  • Department Medical BioSciences, Radboud University Medical Center, Nijmegen 6525 GA, The Netherlands.
  • Institute for Computing and Information Sciences, Radboud University, Nijmegen 6525 XZ, The Netherlands.

ORCID-Profile: Siqi Wei, Jelle Piepenbrock, Martijn A Huynen, Peter A C 't Hoen

Förderung

  • European Union's Horizon Europe research and innovation

Zitieren

APA

Wei, S., Sasi, C., Piepenbrock, J., Huynen, M. A., 't Hoen, P. A. C., & SIMPATHIC Consortium (2026). KG-Bench: Benchmarking Graph Neural Network Algorithms for Drug Repurposing. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag159

Vancouver

Wei S, Sasi C, Piepenbrock J, Huynen MA, 't Hoen PAC, SIMPATHIC Consortium. KG-Bench: Benchmarking Graph Neural Network Algorithms for Drug Repurposing. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag159

BibTeX
@article{Wei2026,
  author = {Wei, Siqi and Sasi, Christo and Piepenbrock, Jelle and Huynen, Martijn A and 't Hoen, Peter A C and SIMPATHIC Consortium, SIMPATHIC Consortium},
  title = {KG-Bench: Benchmarking Graph Neural Network Algorithms for Drug Repurposing},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag159}
}
Kostenlos starten →