The U.S. Department of Energy’s (DOE) Argonne National Laboratory is leading efforts to combine artificial intelligence (AI) and cutting-edge simulation workflows to better understand biological observations and accelerate drug discovery in its ongoing campaign to reveal the inner workings of the Sar-CoV-2 virus.
Argonne started working with academic and commercial research partners to achieve near real-time feedback between simulation and AI approaches in order to better understand how two proteins in the SARS-CoV-2 viral genome, nsp10 and nsp16, interact to help the virus replicate and evade the host’s immune system.
The team accomplished this feat by combining two distinct hardware platforms: Cerebras CS-1, a processor-packed silicon wafer deep learning accelerator, and ThetaGPU, an AI- and simulation-enabled extension of the Theta supercomputer, which is housed at the Argonne Leadership Computing Facility, a DOE Office of Science User Facility. To accomplish this, the researchers created Stream-AI-MD, a unique use of the AI approach known as deep learning to drive adaptive molecular dynamics (MD) simulations in a streaming fashion. Data from simulations is sent from ThetaGPU to the Cerebras CS-1 platform in order to examine how the two proteins interact at the same time.
The research was published in the proceedings from the Platform for Advanced Scientific Computing Conference
