LEMONT, Ill.--(BUSINESS WIRE)--Supporting a large collaboration of research organizations, the U.S. Department of Energy’s (DOE) Argonne National Laboratory is exploring the use of artificial intelligence (AI) and high-performance computing resources to study, in great detail, the complex dynamics of the spike protein, one of the key proteins that allows the SARS-CoV-2 virus to infiltrate the human immune system.
The collaboration’s work earned the 2020 Gordon Bell Special Prize for High Performance Computing-Based COVID-19 Research, sponsored by the Association for Computing Machinery. The award was announced November 19 at SC20, the International Conference for High Performance Computing, Networking, Storage and Analysis, held virtually this year.
“We are excited to have won this prestigious award,” says Arvind Ramanathan, an Argonne computational biologist and co-principal investigator on the project. “The whole point is to push the boundaries of what we can do with AI. The ability to scale such a huge set of simulations and use AI to drive some factors was key to this work.”
The team, comprised of nearly 30 researchers across 10 organizations, is trying to understand how the spike protein binds to and interacts with the human cell’s ACE2-receptor protein and eventually allows SARS-CoV-2 to infect the host.
Developing a reasonable simulation of the spike protein can create a huge system consisting of approximately 1.8 million atoms and simulations can consist of enormous datasets. To make that data more accessible for interpretation, the team developed a machine learning method that can summarize large volumes of data.
“This method allowed us to find points of interest that were not obvious to the human eye,” says Ramanathan. “So, when you look deeper using the simulations, you see significant changes in the protein structure, which told us something about how the spike protein opens up such that it can interact with the ACE2 receptor.”
The team’s success involved its partnership with NVIDIA, a leader in GPU and AI design, and the utilization of top U.S. supercomputers, including Summit, at the DOE’s Oak Ridge National Laboratory; Theta at Argonne; Frontera/Longhorn at Texas Advanced Computing Center; Comet at San Diego Supercomputing Center; and Lassen at DOE’s Lawrence Livermore National Laboratory.
Eventually, these kinds of insights derived from the highly conjoined combination of machine learning and simulation will help facilitate antibody or vaccine discoveries.
The team’s article, “AI-Driven Multiscale Simulations Illuminate Mechanisms of SARS-CoV-2 Spike Dynamics,” will appear in International Journal of High Performance Computing Applications, 2020.
