LLNL cancer research goes exascale

Researchers at Lawrence Livermore National Laboratory will use their recently awarded cycles on the world’s first exascale system – Frontier at Oak Ridge National Laboratory – to advance their work by applying their machine-learned multi-scale modeling infrastructure computing framework and l intelligence to model and predict how RAS and RAF proteins interact with each other and with lipids on a realistic cell membrane.

A team from Lawrence Livermore National Laboratory (LLNL) will be among the first researchers to perform work on the world’s first exascale supercomputer – Oak Ridge National Laboratory’s Frontier – when they use the system to model mutations in cancer-causing proteins.

Led by Harsh Bhatia, a computer scientist at LLNL’s Center of Applied Computing (CASC), the team was granted limited access to Frontier through the Department of Energy’s (DOE) Advanced Scientific Research Center’s Leadership Computing Challenge (ALCC) program ( ASCR). .

The program recently announced new funding for 45 science projects across universities, industry and government agencies, totaling 18 million knot-hours. Projects will use compute cycles at the National Energy Research Scientific Computing Center (NERSC) at Lawrence Berkeley National Laboratory and the Leadership Computing Facilities at Argonne and Oak Ridge National Laboratories, including early access to a few select projects on Frontier . The projects, with applications ranging from advanced energy systems to climate change and cancer research, will use DOE supercomputers to uncover unique insights into scientific problems that would otherwise be impossible to solve using experimental approaches, according to a researcher. DOE announcement.

Over the next year, Bhatia and his team will use cycles to advance their previous work, applying their machine-learned multi-scale modeling (MuMMI) and artificial intelligence (AI) computing infrastructure to model and predict. how RAS and RAF proteins interact with each other. another and with lipids on a realistic cell membrane. Through the ADMIRRAL (AI-Driven Multiscale Investigation of RAS-RAF Activation Lifecycle) project, researchers hope to understand how proteins mutate and cause tumor formation. RAS mutations are linked to about a third of all cancers, including pancreatic, colorectal and lung cancers.

The lab’s researchers said exascale computing will have a huge impact on understanding cancer mechanisms at scales and details not possible before, ultimately helping the cancer research community counter these mechanisms through new efforts. of drug discovery.

“Cancers are among the major threats to human life, and for cancer research to be among the first scientific applications on the first exascale machine is both necessary and appropriate,” Bhatia said. “We are grateful for the opportunity to use the greatest tool in the arsenal for one of the most difficult problems of our time.”

LLNL Computational Biologist Helgi Ingólfsson added that the team is excited to extend and demonstrate their MUMMI framework on Frontier.

“Meeting the needs of exascale – scalability and throughput, efficient use of heterogeneous resources, and AI-based simulations – are all challenges that will be useful even beyond our current work in cancer research and may translate into other important applications,” Ingólfsson said.

The ongoing research is part of a pilot project of the collaboration between the DOE, the Frederick National Laboratory for Cancer Research (FNLCR) of the National Cancer Institute (NCI), and the Cancer Moonshot. The team’s previous work using LLNL’s entire Sierra system to model micro- and macro-scale protein-lipid interactions, won them the Best Paper Award at the Supercomputing 2019 conference. Using a previous ALCC grant on Summit, the team published a more detailed multidimensional model, revealing the importance of lipids in RAS signaling dynamics.

The LLNL project was one of only two given early access to Frontier — the other being General Electric, for a project on turbomachinery simulations to advance clean energy, according to the DOE.

One of many allocation programs for ASCR, the ALCC program will account for up to 25% of the total compute time available over the next year on a limited number of cycles on Frontier, as well as on platforms DOE HPC at all three ASCR supercomputing facilities, including Summit and Theta at ORNL, Polaris at Argonne, and Perlmutter at NERSC. The program supports ASCR’s efforts to advance DOE mission science, respond to national emergencies, or expand community access to leadership computing facilities, according to the website.

“Using in the era of exascale, Department of Energy supercomputers provide cutting-edge scientific tools that advance American science. Our supercomputers allow scientific problems to be explored in new ways, modeling quickly and safely experiments that would otherwise be too dangerous, bulky, or expensive,” said Barb Helland, DOE Associate Director for Advanced Scientific Computing Research, in a press release. “These ALCC awards allow researchers across the country to use our supercomputers to advance our global scientific competitiveness, accelerate clean energy options, and better understand and mitigate the impacts of climate change.”

/Public release. This material from the original organization/authors may be ad hoc in nature, edited for clarity, style and length. The views and opinions expressed are those of the author or authors. See in full here.

About Mariel Baker

Check Also

How they could drastically increase energy efficiency

Traditionally, “quantum supremacy” is sought from the point of view of raw computing power: we …