With the on-going COVID-19 pandemic, drug repurposing, also known as repositioning or rediscovery, is pursued to advance patient therapies to accelerate the identification of drugs that can cure or prevent COVID-19. For example, Remdesivir was initially developed for treating Ebola and hepatitis C, however over the course of the pandemic, it has been repurposed as a COVID-19 therapy. Drug repurposing helps to speed up the drug discovery process by identifying new clinical uses for drugs that have already proven to be safe and effective in humans and may be approved for new indications like COVID-19.
Prof. Anandasankar Ray’s lab at the University of California, Riverside (UCR) has developed machine learning models to predict the inhibitory activity of molecules that bind to potential and actual SARS-CoV-2 interacting human proteins as targets.
An important target is the human ACE2 receptor which is used for viral entry. A recent and published systems-level analysis of protein-protein interactions with peptides encoded in the SARS-CoV-2 genome identified ~66 additional human proteins were considered suitable candidates for the identification of COVID-19 therapeutics. This information was used to train machine learning models and then used to screen most FDA registered chemicals and approved drugs (~100,000) and an additional ~14 million chemicals. Predictions were filtered according to estimated mammalian toxicity and vapor pressure. Prospective volatile candidates identified may be used as novel inhaled therapeutics since the nasal cavity and respiratory tracts are early bottlenecks for infection.
Fig. 1 Overview of the pipeline to predict chemicals for 65 SARS-CoV-2 human targets and using bioassay data from publicly available databases