LSU’s DeepDrug AI is being trained to analyze possible anti-viral drugs or drug combinations that could be used to treat COVID-19 patients.

LSU Computer Science Professor Supratik Mukhopadhyay, one of the scientists on the DeepDrug project, says drugs like hydroxychloroquine appear promising, but cardiac patients shouldn’t take the anti-malarial because of its cardiac toxicity.

“We need an array of drugs that can be used on a case by case basis for different types of patients,” says Mukhopadhyay.

Before turning its attention to the coronavirus, DeepDrug was being used to analyze potential antibiotic and antimicrobial treatments.

The FDA has approved about 90 antiviral treatments for general use, and Mukhopadyay says each will be simulated to see how it would potentially treat COVID patients.

“We will find a list of ten to 15 drugs and then we are going to test them,” says Mukhopadhyay.

Once the ten to fifteen possibilities are discovered, Mukhopadyay says LSU will move to test them in more traditional clinical and lab settings.

“We are almost there, it will come up with its predictions very soon, maybe by the end of this week,” says Mukhopadhyay.

DeepDrug is a current semifinalist for the IBM Watson AI X-PRIZE.

(Story written by Matt Doyle/Louisiana Radio Network)