As soon as the COVID-19 pandemic erupted in early 2020, scientists found themselves racing against time to find an antiviral medication that could treat the disease. With billions upon billions of potential drug candidates to sort through, researchers needed a way to dramatically speed their search. The answer, they found, lay in Artificial Intelligence (AI).
Since the beginning of the pandemic, researchers at the U.S. Department of Energy’s (DOE) Argonne National Laboratory have been using AI to search through a vast number of small molecules to find usable drug candidates. Recently, they have utilised new computing hardware to speed the process, reducing searches that might have originally taken years to mere minutes.
To determine whether a small molecule can form the basis of a useful antiviral medication, researchers need to compute how well it binds to different pockets on one of the viral proteins of SARS-CoV-2, which causes COVID-19.
Computing the binding energy of small molecules starts by analysing them one at a time with physics-based codes on leadership-class supercomputers, including Argonne’s Theta, which is part of the Argonne Leadership Computing Facility (ALCF). These binding scores are then used to train an AI algorithm to look for the molecules with the lowest binding energies. With AI, the researchers went from doing one compound per second to 1,000 compounds per second and ultimately to 50,000 compounds per second.
The advantage of using AI, according to Brettin, is that it can quickly adapt to and accommodate chemical structures that it has never seen and that have never been synthesised and do not exist in nature. Artificial intelligence gives us both the speed and flexibility that pure physics-based computation would have a very hard time achieving.
– Tom Brettin, Argonne Computational Scientist
Another benefit of AI lies in the fact that it generates the minimum possible binding energy for each candidate immediately, rather than needing to perform a large number of trial-and-error computations for different configurations of molecules as they attach to a protein site.
Although 50,000 predictions a second may seem like a rapid rate, the researchers were still interested in speeding up the computations even more. They turned to the ALCF’s AI testbed, a growing collection of some of the world’s most advanced AI platforms, including the GroqChip accelerator.
In tests on a large dataset of small molecules, the researchers found they could achieve 20 million predictions, or inferences, a second, vastly reducing the time needed for each search. Once the best candidates were found, the researchers identified which ones could be obtained commercially and had them tested on human cells.
As reported by OpenGov Asia, DOE’s Argonne National Laboratory has received nearly $3 million in funding for two interdisciplinary projects that will further develop artificial intelligence (AI) and machine learning technology.
The two grants were presented by the DOE’s Office of Advanced Scientific Computing Research (ASCR). They will aid Argonne scientists and collaborators to seek AI and machine learning work in the development of approaches to handle enormous data sets or develop better outcomes where minimal data exists.
One project is an alliance with partners from the DOE’s Los Alamos National Laboratory, Johns Hopkins University, and the Illinois Institute of Technology in Chicago. For this project, Argonne scientists will formulate techniques and methods to run with huge dynamical systems.
By integrating mathematics and scientific principles, they will construct strong and accurate surrogate models. These types of models can greatly reduce the time and cost of working complex simulations, such as those used to forecast the climate or weather.
These two projects are part of five the DOE recently awarded for interdisciplinary work using AI to advance the science conducted in the national labs. All five are focused on developing reliable and efficient AI and machine learning methods to address a broad range of science needs.