News Archive

Supercomputers Pave the Way for New Machine Learning Approach

San Diego Supercomputer Center and Los Alamos National Laboratory Aid in Transfer Learning

Published August 28, 2019

New deep learning models predict the interactions between atoms in organic molecules. These models, which were generated using supercomputers at the San Diego Supercomputer Center and the Los Alamos National Laboratory, help computational biologists and drug development researchers better understand and treat disease.  Credit: Los Alamos National Laboratory

By Kimberly Mann Bruch, SDSC Communications; based on a press release by Nancy Ambrosiano, Los Alamos National Laboratory

According to a release issued earlier this month by the Los Alamos National Laboratory (LANL), researchers have developed a machine learning approach called transfer learning that lets them model novel materials by learning from data collected about millions of other compounds. The new approach can be applied to new molecules in milliseconds, enabling research into a far greater number of compounds over much longer timescales.

The new technique, called ANI-1ccx potential, promises to advance the capabilities of researchers in many fields and improve the accuracy of machine learning-based potentials in future studies of metal alloys and detonation physics.

“Our quantum mechanical calculations to create ANI-1ccx potential were conducted over two years with time split on the Comet supercomputer at the San Diego Supercomputer Center and the ­­­Badger supercomputer at LANL,” said Olexandr Isayev, paper author and a pharmacy professor at the University of North Carolina at Chapel Hill. “We chose these two supercomputers to train our neural networks as there are few machines that can run these – due to the high memory and core requirements.”

Isayev and colleagues from University of Florida and LANL recently published their research in a Nature Communications paper called Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning. The paper details how quantum mechanical (QM) algorithms, used on classical computers, can accurately describe the mechanical motions of a compound in its operational environment.

However, QM scales very poorly with varying molecular sizes, severely limiting the scope of possible simulations. Even a slight increase in molecular size within a simulation can dramatically increase the computational burden. So practitioners often resort to using empirical information, which describes the motion of atoms in terms of classical physics and Newton’s Laws, enabling simulations that scale to billions of atoms or millions of chemical compounds.

Traditionally, similar models have had to strike a tradeoff between accuracy and transferability. When the many parameters of the potential are finely tuned for one compound, the accuracy decreases on other compounds.

“This means we can now model materials and molecular dynamics billions of times faster compared to conventional quantum methods, while retaining the same level of accuracy,” explained Justin Smith, LANL Physicist and Metropolis Fellow in the laboratory’s Theoretical Division. Understanding how molecules move is critical to tapping their potential value for drug development, protein simulations and reactive chemistry, for example, and both quantum mechanics and experimental (empirical) methods feed into the simulations.

The researchers acknowledge support of the U.S. Department of Energy (DOE) and the National Science Foundation (NSF) grants CHE-1802789 and CHE-1802831. The authors also acknowledge Extreme Science and Engineering Discovery Environment (XSEDE) award DMR110088, which is supported by NSF grant ACI-1053575. This research in part was done using resources provided by the Open Science Grid, which is supported by NSF award 1148698 and the U.S. DOE Office of Science.

About SDSC

Located on the University of California San Diego campus, SDSC is considered a leader in data-intensive computing and cyberinfrastructure, providing resources, services, and expertise to the national research community, including industry and academia. Cyberinfrastructure refers to an accessible, integrated network of computer-based resources and expertise, focused on accelerating scientific inquiry and discovery. SDSC supports hundreds of multidisciplinary programs spanning a wide variety of domains, from earth sciences and biology to astrophysics, bioinformatics, and health IT. SDSC’s petascale Comet supercomputer is a key resource within the National Science Foundation’s XSEDE (eXtreme Science and Engineering Discovery Environment) program.