NVIDIA helps the US build an AI for cancer research

CANDLE's machine learning should accelerate the search for crucial genetic data.

Steve Gschmeissner/Science Photo Library via Getty Images

Microsoft isn't the only big-name tech company using AI to fight cancer. NVIDIA is partnering with the US Department of Energy and the National Cancer Institute to develop CANDLE (Cancer Distributed Learning Environment), an AI-based "common discovery platform" that aims for 10 times faster cancer research on modern supercomputers with graphics processors. The hardware promises to rapidly accelerate neural networks that can both spot crucial data and speed up simulations.

CANDLE will tackle three core problems. It'll sift through genomic data to find the genetic signatures in cancer DNA and RNA that predict their response to treatments. The AI will also automatically extract and study "millions" of patient records to understand how cancer spreads and reoccurs, and accelerate the simulation of protein interactions to see how they create the conditions for cancer.

The partners haven't said when they expect CANDLE to be ready, and it could be a while after that happens before you see the practical results. As with other AI-based medical research (including Microsoft's), its effectiveness still depends on humans -- they have to ask the right questions and collect the right data. If everything goes as intended, however, scientists could spend less time waiting for key observations and more time treating diseases.