Skip to content
Supercomputers Mimic Brain Activity, Seeking COVID Cures

October 15, 2021 – Machine learning has come a long way in the quarter century since a computer dubbed Deep Blue shocked the world by beating chess champion Garry Kasparov. Today, as our smartphones have a lot more computing power than Deep Blue, scientists have turned to even bigger adversaries, including life-threatening diseases like cancer, heart disease, and COVID-19.

When supercomputers search for new drug cocktails to treat these conditions, scientists can feed the machines into mountains of data from decades of study to help inform analysis. But the coronavirus is still too new and too rapidly changing for scientists to turn to these usual strategies.

Researchers at the Massachusetts Institute of Technology have a new way to address the lack of data on the new virus. They train computers to run algorithms inspired by signaling networks in the human brain. Like the brain, these neural networks can “learn” and adapt to rapidly changing information, forging new connections on the fly.

To identify drug combinations that might work against COVID-19, investigators ask their computer neural network to assess two things at once.

One is to look for pairs of drugs that will be stronger antivirals together than either drug alone. This concept that two drugs work best together is known as “drug synergy”.

The computer also looks for parts of a disease targeted by drugs, such as proteins or genetic mutations linked to a disease. The idea behind both of these approaches is that machines can “learn” which drug cocktails might have the most antiviral power.

In their study,published in the Proceedings of the National Academy of Sciences, MIT scientists reveal two potential drug cocktails they found using this approach. One combines remdesivir, which the FDA has already approved to treat COVID-19, and reserpine, a blood pressure medication. The other combination is remdesivir and an investigational drug called IQ-1S, which is in a family of drugs used to treat autoimmune diseases like rheumatoid arthritis.

These drug cocktails have yet to be proven effective against COVID-19 in human trials. But the study’s results can help drug developers identify the most sensible combinations to test when researching new treatments.


Not all news on the site expresses the point of view of the site, but we transmit this news automatically and translate it through programmatic technology on the site and not from a human editor.