Using a combination of AI and supercomputing resources, Argonne researchers are examining the dynamics of the SARS-CoV-2 spike protein to determine how it fuses with the human host cell, advancing the search for drug treatments.
The research is focused on using a high-performance, iterative reconstruction system for noninvasive imaging at synchrotron facilities.
The new projects will use DOE’s leadership-class supercomputers to pursue transformational advances in science and engineering.
This visualization is a first look at data from the final cosmological simulations carried out on the Argonne Leadership Computing Facility’s recently retired Mira supercomputer.
Rick Stevens, Associate Laboratory Director for Argonne’s Computing, Environment and Life Sciences (CELS) Directorate, will take part in a panel discussion that highlights how the scientific computing community is using HPC to advance COVID-19 research.
Argonne researchers will present a technical paper detailing the development of a scalable neural architecture search to forecast sea surface temperatures using a dataset from the National Oceanic and Atmospheric Administration.
A finalist for the conference’s Best Paper Award, this study, co-authored by Argonne researchers, introduces a novel method for recovering high-quality 3D volumetric images from 2D X-ray images generated at experimental synchrotron facilities.
Argonne researchers co-authored a paper that introduces CAB-MPI, an implementation of Message Passing Interface (MPI), as a tool for designing communication-balanced applications.
Researchers from Argonne and Texas A&M University will present a technical paper on a new data-driven diagnostic tool called Gauge that can be used to explore the latent space of supercomputing job features, understand behaviors of clusters of jobs and identify and assess I/O bottlenecks.
At the Workshop on Artificial Intelligence and Machine Learning for Scientific Applications, researchers from Argonne and Virginia Tech will present a paper on a deep learning framework that can be applied to tomography reconstruction and other X-ray imaging techniques for enhanced analysis of dose-sensitive samples.