Knowledge-Graph-Based Drug Repositioning against COVID-19 by Graph Convolutional Network with Attention Mechanism
Open Access
- 7 January 2021
- journal article
- research article
- Published by MDPI AG in Future Internet
- Vol. 13 (1) , 13
Abstract
The current global crisis caused by COVID-19 almost halted normal life in most parts of the world. Due to the long development cycle for new drugs, drug repositioning becomes an effective method of screening drugs for COVID-19. To find suitable drugs for COVID-19, we add COVID-19-related information into our medical knowledge graph and utilize a knowledge-graph-based drug repositioning method to screen potential therapeutic drugs for COVID-19. Specific steps are as follows. Firstly, the information about COVID-19 is collected from the latest published literature, and gene targets of COVID-19 are added to the knowledge graph. Then, the information of COVID-19 of the knowledge graph is extracted and a drug–disease interaction prediction model based on Graph Convolutional Network with Attention (Att-GCN) is established. Att-GCN is used to extract features from the knowledge graph and the prediction matrix reconstructed through matrix operation. We evaluate the model by predicting drugs for both ordinary diseases and COVID-19. The model can achieve area under curve (AUC) of 0.954 and area under the precise recall area curve (AUPR) of 0.851 for ordinary diseases. On the drug repositioning experiment for COVID-19, five drugs predicted by the models have proved effective in clinical treatment. The experimental results confirm that the model can predict drug–disease interaction effectively for both normal diseases and COVID-19.Keywords
Funding Information
- National Natural Science Foundation of China (62076045)
- Liaoning Natural Science Foundation (2019-ZD-0569)
This publication has 33 references indexed in Scilit:
- Machine-learning approaches in drug discovery: methods and applicationsDrug Discovery Today, 2015
- Systems Biology Brings New Dimensions for Structure-Based Drug DesignJournal of the American Chemical Society, 2014
- Drug repositioning by integrating target information through a heterogeneous network modelBioinformatics, 2014
- DrugBank 4.0: shedding new light on drug metabolismNucleic Acids Research, 2013
- Drug–target interaction prediction by learning from local information and neighborsBioinformatics, 2012
- Pharmacogenomics Knowledge for Personalized MedicineClinical Pharmacology & Therapeutics, 2012
- Chem2Bio2RDF: a semantic framework for linking and data mining chemogenomic and systems chemical biology dataBMC Bioinformatics, 2010
- KEGG for linking genomes to life and the environmentNucleic Acids Research, 2007
- A probabilistic model for mining implicit ‘chemical compound–gene’ relations from literatureBioinformatics, 2005
- PharmGKB: the Pharmacogenetics Knowledge BaseNucleic Acids Research, 2002