Researchers at the University of California, Riverside (UCR) have used machine learning to identify hundreds of new potential drugs that could help treat Covid-19.
The team used small numbers of previously known ligands for 65 human proteins that are known to interact with SARS-CoV-2 proteins, and generated machine learning models for each of the proteins. This was then used to create a database of chemicals whose structures were predicated as interactors of the 65 targets.
The machine learning model was then used to screen more than 10 million commercially available small molecules from a database comprised of 200 million chemicals. It identified the best-in-class hits for the 65 human proteins that interact with SARS-CoV-2 proteins, then identified compounds among these that have already received approval from the US Food and Drug Administration (FDA).
The UCR project also used the machine learning models to compute toxicity, which helped the team reject potentially toxic candidates.
UCR professor of molecular, cell, and systems biology Anandasankar Ray said: "Our database can serve as a resource for rapidly identifying and testing novel, safe treatment strategies for Covid-19 and other diseases where the same 65 target proteins are relevant. While the Covid-19 pandemic was what motivated us, we expect our predictions from more than 10 million chemicals will accelerate drug discovery in the fight against not only Covid-19 but also a number of other diseases."