COVID-19 HPC Consortium Aids Use of Machine Learning and Molecular Modelling to Improve Drug Discovery

The COVID-19 HPC Consortium is a unique private-public effort spearheaded by the White House Office of Science and Technology Policy, the US Department of Energy and IBM to bring together federal government, industry, and academic leaders who are volunteering free compute time and resources on their world-class machines. The consortium helps aggregate computing capabilities from the world's most powerful and advanced computers to help COVID-19 researchers execute complex computational research programs to help fight the virus.

Consortium members and affiliates manage a range of computing capabilities: from small clusters to some of the largest supercomputers in the world. They offer not only computational resources, but also software, services, and deep technical expertise to help COVID-19 researchers execute complex computational research programs. Collectively, the consortium offers access to 485 petaflops, five million CPUs, and 50,000 GPUs. Most of the collective power is delivered via supercomputers based on Intel technology. The consortium includes some of the world’s top-performing supercomputing centers, such as the Texas Advanced Computer Center (TACC) at The University of Texas, Department of Energy’s Argonne National Laboratory, and the Pittsburgh Supercomputing Center, among others.

Taking advantage of Intel technologies, scientists are advancing their algorithms and software in ways that are crucial for understanding COVID-19. For instance, scientists aim to combine machine learning (ML) and molecular modelling to improve virtual screening and drug discovery applications targeting COVID-19. They have developed a genetic algorithm capable of searching chemical space surrounding existing antiviral drugs and a deep learning based classification model based on existing public coronavirus binding data (for the SARS-CoV-2 main protease). The scientists plan to combine and extend these tools through a combination of docking and simulation which we can use as inputs to a regression based deep learning model. A key component of their approach will be to use an enhanced version of the out of distribution classification algorithms created previously to design novel kinase (CDK9) inhibitors to identify molecules which have maximum value in terms of expanding the validity of their model. Enhancing their model from a classification model to one capable of regression in this way should provide greatly enhanced capabilities to identify both existing drugs with potential to treat COVID-19 (virtual screening) as well as the discovery of new active compounds.