Email
Password
Remember meForgot password?
    Log in with Twitter

article imageNVIDIA AI helps the U.S. research cancer treatments

By James Walker     Nov 15, 2016 in Technology
NVIDIA has announced a new partnership with the National Cancer Institute and the U.S. Department of Energy. The company will supply artificial intelligence software that it hopes will accelerate cancer research and "deliver a decade of advances."
The project is known as the Cancer Moonshot. It was introduced by U.S. President Barack Obama during his 2016 State of the Union Address and is currently led by Vice President Joseph Biden. Alongside lab research and development, Cancer Moonshot includes a special focus on building artificial intelligence software to power a "common discovery platform."
The Cancer Distributed Learning Environment (CANDLE) is currently in development. A range of institutions are involved, assisting NVIDIA engineers in developing the framework. NVIDIA hopes its combination of deep learning-capable hardware with a new software platform will achieve 10x annual increases in productivity for cancer researchers.
CANDLE will be aimed at three primary tasks. Initially, it will be used to help discover the genetic signatures present in the DNA and RNA of common cancers. These signatures could help predict a patient's response to treatment but are currently buried within data collected by the NCI genomic data commons. CANDLE will use neural networks to process the wealth of material available, completing the task faster than computer systems which don't feature AI.
CANDLE will also help to accelerate protein interaction simulations. These simulations help researchers to understand the biological mechanisms that can lead to cancer development. Finally, CANDLE will facilitate automation of the extraction and analysis of millions of clinical patient records. It will use a "semi-supervised" learning model to create a comprehensive cancer surveillance database that will help researchers focus their work.
The project is being welcomed by cancer labs across the country. It could lead to improvements in efficiency that will develop new treatments and help to save lives, significantly impacting society.
"AI will be essential to achieve the objectives of the Cancer Moonshot," said 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."
NVIDIA isn't the only company using artificial intelligence to aid cancer research. In September, Microsoft detailed how it's using its cloud computing platforms to "solve" cancer. It compares cancer to a code that can be cracked using computer science. IBM is working on a similar system called Watson Oncology.
NVIDIA described its partnership with the National Cancer Institute as an "ambitious collaboration" that could be a milestone in cancer research. Several national laboratories are involved in Cancer Moonshot and will be using CANDLE to streamline their workflows and make breakthrough discoveries. The platform will be underpinned by NVIDIA's Pascal-based graphics cards and its DGX-1 scalable AI architecture. The time frame for development remains unclear.
"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," said Jen-Hsun Huang, founder and CEO of 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."
More about Nvidia, Artificial intelligence, machine learning, neural networks, Candle