Network Representation Learning-Based Drug Mechanism Discovery and Anti-Inflammatory Response Against COVID-19

24 June 2020, Version 1
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

Recent studies have been demonstrated that host immune imbalance is an important factors leading to acute respiratory distress syndrome (ARDS) in COVID-19 patients. Therefore, discovery of potential drugs and identification of their mechanisms of action for the prevention of immune imbalance in COVID-19 patients are urgently needed. In this study, we proposed a network representation learning-based methodology, termed AIdrug2cov, to discover drug mechanism and anti-inflammatory response for patients with COVID19. In AIdrug2cov, a deep bidirectional Transformer encoder network representation approach is developed to automatically learn lowdimensional vector of heterogeneous network. Using the representation vectors, AIdrug2cov identifies 40 potential targets and 24 high-confidence drugs that bind to tumor necrosis factor(TNF)-α or interleukin(IL)-6 to prevent excessive inflammatory responses in COVID-19 patients. In particular, AIdrug2cov indicated that chloroquine and hydroxychloroquine are able to reduce fatality of COVID-19 patients, and that their mechanisms of action are likely mediated through their inhibition of inflammatory cytokines on top of their antiviral ability, consistent with the findings of clinical studies. In addition, the results in 5 pharmacological application suggested that AIdrug2cov significantly outperforms 5 other state-of-the-art network representation approaches, future demonstrating the availability of AIdrug2cov in drug development field. In summary, AIdrug2cov is practically useful for accelerating COVID-19 therapeutic development. The source code and data can be downloaded from https://github.com/pengsl-lab/AIdrug2cov.git

Keywords

heterogeneous networks
representation learning
deep bidirectional Transformer
COVID-19
drug mechanism
anti-inflammatory response

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.