Download PDF
Altair > Case Studies > AI-Driven Virus Variant Tracking: A Case Study of Argonne National Laboratory
Altair Logo

AI-Driven Virus Variant Tracking: A Case Study of Argonne National Laboratory

Technology Category
  • Analytics & Modeling - Machine Learning
  • Infrastructure as a Service (IaaS) - Cloud Computing
Applicable Industries
  • Education
  • Equipment & Machinery
Applicable Functions
  • Product Research & Development
Use Cases
  • Predictive Maintenance
  • Virtual Training
Services
  • Data Science Services
  • Training
The Challenge
Argonne National Laboratory, a U.S. Department of Energy multidisciplinary science and engineering research center, was faced with the challenge of tracking the rapidly evolving SARS-CoV-2 virus and its variants during the COVID-19 pandemic. The rapid evolution of the virus, sometimes becoming deadlier and more transmissible, necessitated the quick identification of variants of concern (VOCs). The early discovery of VOCs is crucial in saving lives by providing scientists with the time to develop effective vaccines and treatments. However, the existing methods of tracking these variants were slow and inefficient, posing a significant challenge to the research team.
About The Customer
Argonne National Laboratory is a multidisciplinary science and engineering research center under the U.S. Department of Energy. The laboratory is home to talented researchers who collaborate to answer some of humanity's biggest questions. The Aurora exascale computer, which is scheduled to be operational at the Argonne Leadership Computing Facility (ALCF) in 2023, will support cutting-edge machine learning and data science workloads alongside more traditional modeling and simulation. In the lead-up to exascale with Aurora, Argonne’s Polaris system is already facilitating advances in various scientific and research projects.
The Solution
To tackle the challenge of tracking virus variants, a team of researchers at Argonne National Laboratory, in collaboration with university and industry partners, utilized artificial intelligence (AI). They leveraged the power of the ALCF’s Polaris supercomputer, Cerebras’ AI-hardware accelerator, and NVIDIA’s GPU-accelerated Selene system. Polaris, equipped with GPUs and workload orchestration by Altair® PBS Professional®, was able to handle large, complex workloads, including a year’s worth of genome data used for the project. The team trained large language models (LLMs) for the task, which has implications beyond COVID-19. They developed the first genome-scale language model (GenSLM), which streamlined the process of analyzing 1.5 million complete, high-quality SARS-CoV-2 genome sequences.
Operational Impact
  • The research conducted by the Argonne team and their collaborators has set the stage for faster, more detailed insights into the virus mutation process. This enables scientists worldwide to respond to emerging variants and develop strategies to reduce severity and slow the spread, ultimately saving lives. The team's work has been recognized at SC22 in Dallas, and their paper will be published in the International Journal of High-Performance Computing Applications (IJHPCA). The team believes that the full potential of their effort on large biological data is yet to be realized, indicating the potential for further advancements in this field.
Quantitative Benefit
  • The team was able to analyze 1.5 million complete, high-quality SARS-CoV-2 genome sequences.
  • The Polaris supercomputer was able to handle a year's worth of genome data for the project.
  • The team's work won the ACM’s prestigious 2022 Gordon Bell Special Prize for High Performance Computing-Based COVID-19 Research.

Related Case Studies.

Contact us

Let's talk!

* Required
* Required
* Required
* Invalid email address
By submitting this form, you agree that IoT ONE may contact you with insights and marketing messaging.
No thanks, I don't want to receive any marketing emails from IoT ONE.
Submit

Thank you for your message!
We will contact you soon.