GraphDPA: Predicting drug-pathway associations by graph convolutional networks

Zhong-Rui Zhang; Zhen-Ran Jiang

doi:10.1016/j.compbiolchem.2022.107719

GraphDPA: Predicting drug-pathway associations by graph convolutional networks

Comput Biol Chem. 2022 Aug:99:107719. doi: 10.1016/j.compbiolchem.2022.107719. Epub 2022 Jun 24.

Authors

Zhong-Rui Zhang¹, Zhen-Ran Jiang²

Affiliations

¹ School of Computer Science and Technology, East China Normal University, Shanghai 200062, China.
² School of Computer Science and Technology, East China Normal University, Shanghai 200062, China. Electronic address: zrjiang@cs.ecnu.edu.cn.

PMID: 35785627
DOI: 10.1016/j.compbiolchem.2022.107719

Abstract

Pathway-based drug discovery is a promising strategy for the discovery of drugs with low toxicity and side effects. However, identifying the associations between drug and targeting pathways is challenging for this method. The formation of various biomolecular interaction databases and the development of neural network technology provide new ways for the large-scale prediction of drug-pathway associations. This article proposes a new model called GraphDPA, which represents the drug and pathway-gene association as a graph. We use graph convolutional networks (GCN) to learn the features of the drug and pathway and predict the drug-pathway association. The results show that GraphDPA can predict drug-pathway associations with high accuracy, which verify the potential of the GCN in drug discovery.

Keywords: Drug-pathway association; Feature fusion; Graph convolutional networks.

MeSH terms

Drug Discovery*
Neural Networks, Computer*