Deep Learning-based Network Pharmacology for Exploring the Mechanism of Licorice for the Treatment of COVID-19 (preprint)

ABSTRACT

Licorice, a traditional Chinese medicine, has been widely used for the treatment of COVID-19, but all active compounds and the corresponding targets are still not clear. Therefore, this study proposed a deep learning-based network pharmacology approach to identify more potential active compounds and targets of licorice and to collect information regarding different representative compounds. A graph convolutional neural network was used to construct a molecular map and a convolutional neural network was used to develop a Morgan fingerprint. Twenty core compounds and 6 core targets were predicted, among which 4 compounds (quercetin, naringenin, liquiritigenin, and licoisoflavanone), 2 targets (SYK and JAK2) and the relevant pathways (P53, cAMP, and NF-kB) were associated with SARS-CoV-2-infection, which were confirmed by previous studies. In addition, 2 new active compounds (glabrone and vestitol) and 2 new targets (PTEN and MAP3K8) were further validated by molecular docking, and the results showed that these active compounds bound to SARS-CoV-2 related targets, including the main protease (Mpro, also called 3CLpro), the spike protein (S protein), and the angiotensin-converting enzyme 2 (ACE2). Overall, we conclude that the findings of this study has the value of further exploration in the following experiment and clinical application.