Predicting Potential SARS-COV-2 Drugs - In Depth Drug Database Screening Using Deep Neural Network Framework SSnet, Classical Virtual Screening and Docking

Abstract

Severe Acute Respiratory Syndrome Corona Virus 2 has altered life on a global scale. Currently, research labs around the world are looking for new pharmaceutical treatments by repurposing existing drugs, identifying potential antibody-based therapeutics, as well as the design of new pharmaceutical products and vaccines. To be able to rapidly identify potentional new treatments we require global cooperation and an enhanced open-access research model to distribute new ideas and leads. Herein, we employ a combined machine learning and drug docking approach to evaluate the potential efficacy of existing FDA and World approved drugs to impact the ACE2-Spike complex necessary for viral entry and replication. Further, we extend the machine learning approach to databases containing between 700,000-1 billion compounds. The results of large library screens are incorporated into a open-access web interface to allow researchers from diverse fields to target molecules of interest. Our combined approach allows for both the identification of existing drugs that may be able to be repurposed, and de novo design of ACE2-regulatory compounds. Through these efforts we identify intriguing links between COVID-19 pathologies, particularly in regard to possible sex-differences in disease outcomes.

Version notes

First Version

Content

Supplementary material

COVID 19 SI final
text files

Supplementary weblinks