KG-Bench: Benchmarking Graph Neural Network Algorithms for Drug Repurposing
Wei, S.; Sasi, C.; Piepenbrock, J.; Huynen, M.; 't Hoen, P. A. C.
Show abstract
MotivationDrug 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 benchmarking framework for 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. ResultsBenchmarking several graph neural network (GNN) architectures, TransformerConv achieved the highest performance (APR: 0.87). 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 ImplementationData and codes are available at https://github.com/cmbi/Benchmark_GNN_OpenTargets.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Looking at the BiG picture: Incorporating bipartite graphs in drug response prediction 98%
- DTI-Voodoo: machine learning over interaction networks and ontology-based background knowledge predicts drug-target interactions 97%
- GraphDTA: Predicting drug-target binding affinity with graph neural networks 97%
Similar papers in this journal
- Controlling astrocyte-mediated synaptic pruning signals for schizophrenia drug repurposing with Deep Graph Networks 96%
- Causal reasoning over knowledge graphs leveraging drug-perturbed and disease-specific transcriptomic signatures for drug discovery 95%
- Tissue-guided LASSO for prediction of clinical drug response using preclinical samples 94%
Similar papers in this journal
- Evaluation of network architecture and data augmentation methods for deep learning in chemogenomics 95%
- DrugDiff - small molecule diffusion model with flexible guidance towards molecular properties 95%
- DeepGraphMol, a multi-objective, computational strategy for generating molecules with desirable properties: a graph convolution and reinforcement learning approach 95%
"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.