BioPharma, Artificial Intelligence

IBM, Energy Department researchers tap supercomputer in fight against coronavirus

While the lead author of the study, at the Oak Ridge National Laboratory, cautioned that the researchers had not found a cure for the virus that causes COVID-19, they were able to identify 77 compounds after screening more than 8,000 in a matter of days.

AI, machine learning

The number of people infected with the novel coronavirus is now past 100,000, leaving thousands dead and fueling fear and anxiety around the globe. Amid efforts to develop drugs and vaccines, the Department of Energy is hoping to use a supercomputer to help find compounds that might work against the virus.

Technology giant IBM and the Energy Department’s Oak Ridge National Laboratory said Thursday that they had used IBM’s Summit supercomputer to screen more than 8,000 compounds and identify 77 small-molecule drugs that might warrant study as potential treatments for SARS-CoV-2, the virus that causes the COVID-19 disease. The researchers used Summit to simulate the compounds in a matter of days and modeled which ones might affect the process by which it infects cells – using a spike to inject them with its genetic material, similar to the SARS coronavirus that caused the 2002-2003 outbreak. Results of the study were published in the journal ChemRxiv.

sponsored content

A Deep-dive Into Specialty Pharma

A specialty drug is a class of prescription medications used to treat complex, chronic or rare medical conditions. Although this classification was originally intended to define the treatment of rare, also termed “orphan” diseases, affecting fewer than 200,000 people in the US, more recently, specialty drugs have emerged as the cornerstone of treatment for chronic and complex diseases such as cancer, autoimmune conditions, diabetes, hepatitis C, and HIV/AIDS.

“Summit was needed to rapidly get the simulation results we needed,” principal researcher Jeremy Smith, director of the University of Tennessee and Oak Ridge lab’s Center for Molecular Biophysics, said in a statement. “Our results don’t mean that we have found a cure or treatment for the Wuhan coronavirus. We are very hopeful, though, that our computational findings will both inform future studies and provide a framework that experimentalists will use to further investigate these compounds.”

The study represents one of several efforts to use computer technology to screen potential compounds for activity against various diseases. Recently, researchers at MIT identified a drug formerly developed for diabetes as a potentially powerful antibiotic that they named halicin, after the HAL-9000 computer in “2001: A Space Odyssey.”

Several companies are in the process of developing vaccines or antiviral therapies against the virus, which was first identified in the central Chinese city of Wuhan in December. Moderna has a vaccine in Phase I development called mRNA-1273, while Gilead Sciences’ remdesivir – originally developed to treat Ebola virus – is in Phase II development.

As of Sunday, there were 105,586 confirmed cases of coronavirus around the world, with nearly 3,600 patients having died, according to the World Health Organization. According to the Centers for Disease Control and Prevention, there were 423 cases in the U.S., with Washington, California, New York and Massachusetts accounting for the largest number of infectious. The biotechnology company Biogen directed all the 175 attendees of a management meeting that took place in Boston the week before last to quarantine themselves after several tested positive for the virus.

presented by

Photo: ANDRZEJ WOJCICKI, Getty Images