The Department of Energy has some of the best supercomputers in the world. Now, they’re joining the fight against cancer.
Cancer is a worldwide public health problem, and the second leading cause of death in the United States. Although cancer mortality has declined in recent years, there is no one who hasn’t been touched by cancer personally. So when President Obama announced that Vice President Biden would lead the Cancer Moonshot during his State of the Union address, and asked for all hands on deck, I was eager to join the Cancer Moonshot Task Force and lend the support of the Department of Energy and our 17 National Laboratories.
The National Labs are world-class research institutions that are used to tackling complex problems with a multidisciplinary approach — from climate change, to clean energy technology development, to the human genome project. The Labs are also home to some of the fastest and most powerful supercomputers in the world.
Supercomputers are key to the Cancer Moonshot. These exceptionally high-powered machines have the potential to greatly accelerate the development of cancer therapies by finding patterns in massive datasets too large for human analysis. Supercomputers can help us better understand the complexity of cancer development, identify novel and effective treatments, and help elucidate patterns in vast and complex data sets that advance our understanding of cancer.
WHY IS THE ENERGY DEPARTMENT INVOLVED?
Our commitment to the Cancer Moonshot builds on the Department’s longstanding contributions to biomedical research, from radiation biology to genomics. In fact, it was Energy Department supercomputers that mapped the human genome. While these research areas may seem outside of our mission space, we inherited knowledge of and responsibility for radiation biology research from the Atomic Energy Agency. Still today, understanding how radiation affects biological systems is critical to our missions around nuclear security and safety, and genomics is essential in bioenergy research.
Moreover, the National Lab system was built for tackling the toughest science and technology challenges facing our nation, and cancer — one of the leading causes of death worldwide — is no exception. Here’s how Vice President Joe Biden phrased it in January:
“The truth is that this disease spares no one. It doesn’t care about how much money you make, what your profession is, or how many loved ones surround you.”
— Vice President Joe Biden
We have much to gain in the fight against cancer if we bring our full technological capabilities and expertise to the table.
To find a cure, we need to find patterns we haven’t seen before. The challenge is not a lack of relevant data — we have more than ever before. The challenge is accessing that data, and processing it to find patterns that tell us something about what causes cancer, or how to fight it more effectively. With supercomputers, we can find answers to questions that are practically impossible to solve with the human eye. In this case, supercomputers are excellent tools for analyzing genomic and molecular datasets, patient records, family histories and other complex information related to cancer.
Energy Department supercomputing is pushing the intersection of big data analytics, machine learning and modeling and simulation. Today our top supercomputers can make over 20 million billion calculations per second. Over the past 20 years, our determination to maintain our nuclear weapons stockpile without testing drove the Energy Department to develop computers that could model nuclear processes down to tiny fractions of a second. That meant raising the processing speed of the world’s best computers by a factor of 10,000. Last year we invested $550 million into new high-performance computing centers, bringing multiple National Labs together to increase our computing capabilities a further five- to seven-fold.
These future computers will be an entirely new breed. Not only are they fast, they handle big data in entirely new ways. They open avenues for techniques in artificial intelligence, data science and simulations that can tease out new insights. These centers lay the groundwork for advanced “exascale” computing, which can perform a billion billion calculations per second — 20 to 40 times what we’re talking about today. And that will be necessary to adequately understand the complexities of cancer.
The Energy Department brings unparalleled facilities and expertise in large-scale modeling and prediction of complex behaviors, but we can’t do it alone. Finding breakthroughs in cancer prevention and treatment requires collaboration. We’re getting started by teaming up with the National Cancer Institute — tackling their mountain of genomic data — and the Department of Veterans Affairs, analyzing millions of patient records. We’re also meeting with potential pharmaceutical and technology partners to develop pilot projects along the path to exascale computing.
Breaking down silos will also help accelerate progress on cancer research. Thanks to the Cancer Moonshot, data are being shared across government agencies and research institutions. For example, the National Cancer Institute’s Genomic Data Commons promotes sharing of genomic and clinical data between researchers.
WE CAN DO THIS
The United States leads the world in supercomputing, thanks to our integration of supercomputing speed and power with the algorithms and software to make them useful. These unparalleled computational abilities hold the potential to transform the Cancer Moonshot, and we’re not wasting any time getting started. The supercomputing systems designed and built to simulate atomic fusion have already taken on such varied and complex projects as the first sequencing of the human genome, modeling of turbulence around wind turbines, and improving the fuel efficiency of long-haul trucks.
I’m pleased the Energy Department can join this fight, and we’re excited to get to work to transform not only our understanding of cancer — but what a cancer diagnosis means for patients and their families.