New Initiative Uses Supercomputing, AI to Advance Cancer Treatments

October 19, 2016

Oct. 19 — Data is pouring into the hands of cancer researchers, thanks to improvements in imaging, models and understanding of genetics. Today the data from a single patient’s tumor in a clinical trial can add up to one terabyte—the equivalent of 130,000 books.

But we don’t yet have the tools to efficiently process the mountain of genetic data to make more precise predictions for therapy. And it’s needed: treating cancer remains a complex moving target. We can’t yet say precisely how a specific tumor will react to any given drug, and as a patient is treated, cancer cells can continue to evolve, making the initial therapy less effective.

Toward this goal, the U.S. Department of Energy (DOE) is partnering with the National Cancer Institute in an “all-government” approach to fighting cancer. Part of this partnership is a three-year pilot project called the Joint Design of Advanced Computing Solutions for Cancer (JDACSC), which will use DOE supercomputing to build sophisticated computational models to facilitate breakthroughs in the fight against cancer on the molecular, patient and population levels.

The pilot builds on President Obama’s Precision Medicine Initiative and Vice President Biden’s recent “Cancer Moonshot” to transition cancer therapy away from a “one-size-fits-all” approach. Instead, the goal is to move toward individualized diagnosis and treatment that accommodates a patient’s unique body chemistry and genetics.

“Cancer researchers are very good at generating all types of data, from genomic data, proteomic data and imaging data,” said Warren Kibbe, director of the Center for Biomedical Informatics and Information Technology at the National Cancer Institute. “What we’re not really good at yet is integrating all that information into a consistent model and making predictions on how a tumor will respond to a given treatment.”

CANDLE 

Key to this collaboration is a computational framework called the CANcer Distributed Learning Environment (CANDLE). Over the years, many projects have amassed a huge volume of cancer data, including tumor genomes, patient data and experiments on potential drugs. CANDLE is designed to use machine-learning algorithms to find patterns in large datasets. Machine learning is a type of artificial intelligence that focuses on developing programs that can teach themselves to grow and change when presented with new data. These patterns offer insights that may ultimately result in improved treatment or guidance on new experiments.

To date, machine learning studies have produced computational models that estimate drug response for a singular data point—say, a certain mutation. Researchers working with CANDLE, however, envision a higher degree of complexity that integrates many types of information, such as drug interactions and specifics about a patient’s genealogy, as well as the tumor’s molecular characteristics and how its protein expression varies over time.

“The research community has collected thousands of experiments with hundreds of thousands of data points characterizing tumors and their response to the drugs,” said Rick Stevens, an associate laboratory director at the DOE’s Argonne National Laboratory and professor of computer science at the University of Chicago. “By working with the national laboratories, the National Cancer Institute can now finally scale and quantify the cancer problem.”

Using this computational architecture, participating labs—Argonne, Lawrence Livermore, Los Alamos and Oak Ridge national laboratories—will focus on three problems singled out by the National Cancer Institute as the biggest bottlenecks to advancing cancer research by launching three pilots. These are: understanding key protein interactions, predicting drug response and automating patient information extraction to inform treatment strategies.

Each pilot looks at cancer from a different scale. Lawrence Livermore drives the molecular-level pilot, Argonne leads the patient-level pilot, Oak Ridge undertakes the population-level pilot and Los Alamos looks at uncertainty quantification across all three pilots.

Molecular level

Thirty percent of all cancers exhibit mutations in the Ras family—a collection of proteins that help trigger cellular machinery to make new cells or kill old ones.

The molecular-level pilot work being led by Lawrence Livermore will use the CANDLE architecture to predict how these proteins behave on the top of cell membranes. Then they will apply this knowledge to what researchers describe as the “Ras pathway problem,” where glitches cause genes to remain stuck in the “on” position, leading to cancerous tumors.

Researchers want to produce highly complex simulations that describe how a protein moves and binds to specific locations on the cell membrane. They hope such insights can be applied to the millions of Ras pathways and dramatically enhance our understanding of how they work by predicting the likelihood that a signal will take a certain path.  

Patient level 

Cancer encompasses hundreds of diseases, each with thousands of possible causes. Thus, bringing precision to therapy selection for a specific patient is the goal of the Argonne-led patient-level pilot.

With the CANDLE platform, researchers at the Argonne Leadership Computing Facility, a DOE Office of Science User Facility, will develop predictive models that guide drug treatment choices for tumors based on a much wider assortment of data than currently used.

To do this, they will merge one type of computational model that uses data to predict phenomena with another model that uses data to explain them. The hope is that by merging these two methods, they will be able to migrate lessons learned from computer simulations to the research laboratory, where researchers test mice to verify the computer’s prediction of how a tumor will respond to a given therapy.

Researchers will also try to find mechanisms for how a particular tumor evades a therapy or develops resistance.

“Conceptually, that’s how we’re thinking the future of cancer therapies is going to move. Right now we don’t understand the biological implications of resistance well enough for any particular therapy to do a good job at predicting combinatorial therapies,” said Kibbe. “We think that simulation will allow us to do a much better job of predicting which combination of therapies would be most effective for a specific patient.”

Population level

At any one point in time, three to five percent of patients with cancer participate in a cancer clinical trial. And cataloguing all this data is still a manual task.

Oak Ridge will help the National Cancer Institute to scale its ability to monitor cancer patients across the country by automating the process of entering and extracting information. By applying natural language processing and machine learning algorithms to these millions of clinical reports, computers will be able to derive meaning from the notes that doctors and nurses write in their reports.

Once completed, this system would automatically analyze and extract information so that researchers can monitor country-wide outcomes, which can then inform treatment strategies for patients of different lifestyles, environments and cancer types.

Steps are being taken to de-identify data before population-level pilot data is shared with participating labs, Stevens said.

Next Steps

Over the next three years, both the National Cancer Institute and DOE have a monumental task; but they have a plan.

The first year will focus on merging statistical models and building machine-learning methods that make the best of their ability to explain and predict phenomena. In the second year, computer scientists will have to computationally estimate how confident they are in those predictions, and in the final year, researchers will put all of these pieces together and integrate experimental design.

“I really think we are at a unique place right now. There are some unbelievably great conversations happening across government right now about how we work together and integrate these brand new tools to enable understanding of these basic processes,” said Kibbe. “And if we can really understand the interplay of mutations, normal biological processes and cancer, we have a much better chance of being able to interfere with—and end—cancer.”

As the pilots progress from the building and merging of computational models to testing them in the laboratory, Stevens admits that you’d have to be a little fearless to go after a problem like this.

“In my nearly 20 years of working in computational biology, I can say that this is a really hard problem and it’s not clear if we know how to do this,” said Stevens. “But what the Cancer Moonshot gives us all is the ability to show the world how DOE labs can work in collaboration with the National Cancer Institute in a way that hasn’t been done before.”

“With that level of collaboration, it starts to look like less of a far-off moonshot,” he said, “and more a problem that we have a real shot at addressing.”

Support for the initiative is provided by the U.S. Department of Energy’s Office of Science, the National Institutes of Health and the National Nuclear Security Administration.

About Argonne National Laboratory

Argonne National Laboratory seeks solutions to pressing national problems in science and technology. The nation’s first national laboratory, Argonne conducts leading-edge basic and applied scientific research in virtually every scientific discipline. Argonne researchers work closely with researchers from hundreds of companies, universities, and federal, state and municipal agencies to help them solve their specific problems, advance America’s scientific leadership and prepare the nation for a better future. With employees from more than 60 nations, Argonne is managed by UChicago Argonne, LLC for the U.S. Department of Energy’s Office of Science.


Source: Argonne National Laboratory

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

Nvidia Appoints Andy Grant as EMEA Director of Supercomputing, Higher Education, and AI

March 22, 2024

Nvidia recently appointed Andy Grant as Director, Supercomputing, Higher Education, and AI for Europe, the Middle East, and Africa (EMEA). With over 25 years of high-performance computing (HPC) experience, Grant brings a Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Houston We Have a Solution: Addressing the HPC and Tech Talent Gap

March 15, 2024

Generations of Houstonian teachers, counselors, and parents have either worked in the aerospace industry or know people who do - the prospect of entering the fi Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire