AI simulations hone in on promising COVID-19-fighting molecules, lab says

A large collaborative effort led by researchers at Argonne National Laboratory has combined artificial intelligence with physics-based drug docking and molecular dynamics simulations to rapidly hone in on the most promising COVID-19-fighting molecules to test in the lab, scientists announced.
Although AI has played little part in the fight against the virus up until now, researchers at Argonne National Laboratory think they are on to something new.
The project uses several of the most powerful supercomputers on the planet — including the Frontera and Longhorn supercomputers at TACC — to run millions of simulations, train the machine learning system to identify good candidates, and do further explorations on the most promising results, the lab announced.
They say their team recently shared their initial results of molecules that interact with ADRP (adenosine diphosphate ribose 1" phosphatase), one of the 24 proteins that COVID-19 produces, with experimental collaborators to test in the lab.
The lab says results from the experiments will further inform the deep learning models, helping fine-tune predictions for future protein-drug interactions.
PHOTOS: Your coronavirus photos