University of Toronto Wins Research Grant to Compute the Cure

Print Friendly, PDF & Email
Depiction of an RNA molecule being transcribed from DNA, juxtaposed with an artificial neural network interpreting the genomic sequence. The computations performed by the neural network run inside NVIDIA GPUs.

Depiction of an RNA molecule being transcribed from DNA, juxtaposed with an artificial neural network interpreting the genomic sequence. The computations performed by the neural network run inside NVIDIA GPUs.

The University of Toronto is the official winner of Nvidia’s Compute the Cure initiative for 2015. Compute the Cure is a strategic philanthropic initiative of the Nvidia Foundation that aims to advance the fight against cancer. Through grants and employee fundraising efforts, Nvidia has donated more than $2,000,000 to cancer causes since 2011.

Researchers from the University of Toronto are advancing computational cancer research by developing a “genetic interpretation engine” – a GPU-powered, deep learning method for identifying cancer-causing mutations. Under its Compute the Cure initiative, the NVIDIA Foundation awarded the team a $200,000 research grant to further that work — and help them usher in an era of personal and effective cancer care.

“To make a big difference in genomic medicine, we’ve developed GPU-accelerated technologies for the computationally intensive work,” said the lead researcher Dr. Brendan Frey. “Now, we’re focused on the next step — to change the lives of patients stricken with cancer — by experimentally validating our technologies using data from these patients.”

On addition to demonstrating the utility of the tools in cancer biology, the team will ensure that libraries are freely available for use by other biomedical researchers working on cancer and other genetic diseases, according to Delong.

The university team used servers with eight each of Nvidia Tesla K80, K40 and K20 GPU accelerators, plus several desktop machines with Nvidia GeForce GTX TITAN X graphics cards.