ChemRxiv
These are preliminary reports that have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. For more information, please see our FAQs.
COVID19.pdf (9.47 MB)

Ro5 Bioactivity Lab: Identification of Drug Candidates for COVID-19

preprint
submitted on 08.05.2020, 23:17 and posted on 12.05.2020, 06:48 by Zeyu Yang, Orestis Bastas, Mikhail Demtchenko, Aurimas Pabrinkis, Cooper Stergis Jamieson, Danius Bačkis, Charles Dazler Knuff, Žygimantas Jočys, Roy Tal
The public health emergency known as the coronavirus disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has led to a large number of deaths worldwide and major socioeconomic disruption. To date, no broadly effective antiviral treatment or vaccine has been developed for COVID-19. In response to this dire situation, Ro5 deployed its AI Lab to accelerate the search for potential treatments. This report focuses on our use of the Ro5 Bioactivity model, which has been designed to predict the inhibitory activity of small molecules against protein targets. The model screened a vast range of compounds in silico to uncover potential inhibitors of the SARS-CoV-2 3CL protease. We hereby present the most propitious candidates from this screen. The highest-ranking molecules include Nelfinavir, Saquinavir, Itacitinib, Kynostatin-272, BOG-INS-6c2-1, and BEN-VAN-d2b-11. Subsequent docking simulations corroborate their plausibility as 3CLpro inhibitors. Nelfinavir and Itacitinib hold the most promise for drug repurposing, among all the molecules proposed herein, due to their high predicted inhibition and affinity against the 3CL protease, favourable pharmacokinetics, and encouraging experimental data for treating viral replication and hyperinflammation, respectively.

Funding

Ro5

History

Email Address of Submitting Author

rtal@ro5.ai

Institution

Ro5

Country

United Kingdom

ORCID For Submitting Author

0000-0001-8551-2547

Declaration of Conflict of Interest

All authors are affiliated with Ro5, a company developing an AI-based platform for drug discovery and development, as well as clinical trial analytics. Ro5 funded all of the research present in this study. As employees of Ro5, the authors own stock and/or stock options in the company. Each coauthor approved a near-final version of the manuscript.

Exports