Heterogeneous network-based drug repurposing for COVID-19

TL;DR

This paper presents a heterogeneous network-based deep learning approach to identify potential drug candidates for COVID-19 by leveraging existing data on HCoV-related proteins, aiming to accelerate drug repurposing efforts.

Contribution

It introduces a novel application of a heterogeneous network combined with deep learning for COVID-19 drug repurposing, demonstrating high predictive performance.

Findings

High accuracy in predicting COVID-19 related drugs

Effective identification of potential drug candidates

Utilization of a comprehensive heterogeneous network

Abstract

The Corona Virus Disease 2019 (COVID-19) belongs to human coronaviruses (HCoVs), which spreads rapidly around the world. Compared with new drug development, drug repurposing may be the best shortcut for treating COVID-19. Therefore, we constructed a comprehensive heterogeneous network based on the HCoVs-related target proteins and use the previously proposed deepDTnet, to discover potential drug candidates for COVID-19. We obtain high performance in predicting the possible drugs effective for COVID-19 related proteins. In summary, this work utilizes a powerful heterogeneous network-based deep learning method, which may be beneficial to quickly identify candidate repurposable drugs toward future clinical trials for COVID-19. The code and data are available at https://github.com/stjin-XMU/HnDR-COVID.