St. Jude Puts a Huge Pediatric Cancer Genomics Dataset in the Cloud

Photo courtesy St. Jude Children's Research Hospital press release. Image has been cropped for size.

"St. Jude has shared data and resources since its founding,” St. Jude Children’s Research Hospital president and CEO James R. Downing, MD, said while introducing St. Jude Cloud. Of course, the pediatric hospital was founded in 1962, long before the data, or the means by which they’ll be sharing it, would have made sense to anyone.

If it wasn’t obvious from the name, St. Jude’s Cloud is a cloud-based database meant to connect researchers worldwide with pediatric cancer genomics data—and it’s already the world’s largest. It’s an interactive platform with over 5,000 whole-genome sequence, 5,000 whole-exome sequence, and 1,200 RNA sequence datasets. That number is expected to grow, too: St. Jude’s is hoping to double the number of whole-genome sequence datasets by next year.

>>READ: Can Google's Cloud API Solve Healthcare's Disparate Data Problem?

The data comes from 3 different genomic initiatives: St. Jude—Washington University Pediatric Cancer Genome Project; the Genomes for Kids clinical trial; and the St. Jude Lifetime Cohort study (St. Jude LIFE).

The new platform is meant to be easy to access—"Sharing research and scientific discoveries is vital to advancing cures and saving lives, especially in rare diseases like pediatric cancer," Downing said. The new service, according to him, is close to the core of the hospital’s mission.

In addition to a secure storage infrastructure and some truly large genomic datasets, St. Jude’s Cloud also features a series of tools and visualizations to allow researchers to navigate through the genome and identify mutations. Other researchers will also be able to upload their own data.

"Health and technology partnerships are central to the advancement of scientific breakthroughs; allowing great minds and passionate hearts to work together with the common goal of ensuring one day, life-threating diseases in children are no longer a reality," Peter Lee, PhD, said in the program’s announcement. He’s corporate vice president of AI and Research at Microsoft—their Azure suite serves as the cloud platform for St. Jude’s Cloud.

DNAnexus, which specializes in handling digitized genomic information, also helped build the program. "Whether you are working together across hallways or international borders, researchers need a secure space to foster collaboration and share data and tools,” its CEO, Richard Daly, said. “We are proud to serve as the technology platform bringing together St. Jude researchers and their partners to advance cures for pediatric life-threatening diseases."

Related Coverage:

Singlera Genomics Adds Another $60 Million

Contextual Genomics Gets $12M From Hong Kong Investor

The Digitized, Cloud-Dependent Smart Hospitals of the Future