CANDLE will be the first AI framework designed to change the way we understand cancer, providing data scientists around the world with a powerful tool against this disease.
Teams collaborating on CANDLE include researchers at the National Cancer Institute (NCI), Frederick National Laboratory for Cancer Research and DOE, as well as at Argonne, Oak Ridge, Livermore and Los Alamos National Laboratories. NVIDIA engineers and computational scientists will contribute to all elements of this framework by jointly developing an AI software platform optimized for the latest supercomputing infrastructure, with the goal of achieving 10x annual increases in productivity for cancer researchers.
"AI will be essential to achieve the objectives of the Cancer Moonshot", stated Rick Stevens, associate laboratory director for Computing, Environment and Life Sciences at Argonne National Laboratory. "New computing architectures have accelerated the training of neural networks by 50 times in just three years, and we expect more dramatic gains ahead."
"GPU deep learning has given us a new tool to tackle grand challenges that have, up to now, been too complex for even the most powerful supercomputers", stated Jen-Hsun Huang, founder and chief executive officer, NVIDIA. "Together with the Department of Energy and the National Cancer Institute, we are creating an AI supercomputing platform for cancer research. This ambitious collaboration is a giant leap in accelerating one of our nation's greatest undertakings, the fight against cancer."
The Cancer Moonshot strategic computing partnership between the DOE and NCI to accelerate precision oncology includes three precision medicine pilot projects that aim to provide a better understanding of how cancer grows; discover more effective, less toxic therapies than existing ones; and understand key drivers of their effectiveness outside the clinical trial setting, at the population level. Deep learning techniques are essential for each of these projects.
First, CANDLE will be used to help discover the underlying genetic signatures present in DNA and RNA of common cancers that are predictive of treatment response from the mass of molecular data collected by the NCI genomic data commons. Second, CANDLE will accelerate the molecular dynamic simulations of key protein interactions to understand the underlying biological mechanisms creating conditions for cancer. Third, through semi-supervised learning, CANDLE will automate information extraction and analysis of millions of clinical patient records to build a comprehensive cancer surveillance database of disease metastasis and recurrence.
"Large-scale data analytics - and particularly deep learning - are central to LLNL's growing missions in areas ranging from precision medicine to assuring nuclear nonproliferation", stated James M. Brase, Deputy Associate Director for Computation, Lawrence Livermore National Laboratory. "NVIDIA is at the forefront of accelerated machine learning, and the new CORAL/Sierra architectures are critical to developing the next generation of scalable deep learning algorithms. Combining NVLink-enabled Pascal GPU architectures will allow accelerated training of the largest neural networks."
Georgia Tourassi, Director of the Health Data Sciences Institute at Oak Ridge National Laboratory, stated: "Today cancer surveillance relies on manual analysis of clinical reports to extract important biomarkers of cancer progression and outcomes. By applying high performance computing and AI on scalable solutions like NVIDIA's DGX-1, we can automate and more readily extract important clinical information, greatly improving our population cancer health understanding."