Seven Bridges, a biomedical data analysis company, has signed a Collaborative Research and Development Agreement (CRADA) with the U.S. Department of Veteran Affairs (VA) to support two key research initiatives for the VA’s Million Veteran Program (MVP). The MVP is a national, voluntary research program funded by the VA’s Office of R&D, with the goal of partnering with Veterans receiving their care from the VA Healthcare System to study how genes affect health. Seven Bridges will serve as an industrial collaborator on the MVP, supporting the development of a hybrid cloud for large-scale data analysis, and a genotype-phenotype graph analysis engine.

With the help of one million Veteran volunteers, the MVP is building one of the world’s largest medical databases for research on diseases like diabetes and cancer, and military-related illnesses, such as post-traumatic stress disorder. The two current CRADAs, which include Seven Bridges and Lockheed Martin as industrial collaborators, will lay the foundation to address needs described in the White House Precision Medicine Initiative and the National Cancer Moonshot.

The aim of the Hybrid Cloud project outlined in the CRADA is to establish an automated execution framework that has the ability to distribute data, metadata and compute jobs across on-premise and remote resources, on the basis of access permissions, resource availability and specific datasets involved.

“Some MVP data will always need to be on local infrastructure, while some can be processed remotely for faster and more cost-effective analysis,” said Jennifer Moser, program manager at the U.S. Department of Veterans Affairs. “Seven Bridges is building the software to link these two environments, so that researchers can ask biological questions and perform reproducible and shareable analysis as rapidly as possible.”

The aim of the Genotype-Phenotype Graph Analysis Engine is to provide software and algorithms to synthesize existing genomic data sources and phenotype information into a unified graph data structure.

“With this engine, we’re expanding on the expertise we built with the U.K.’s 100,000 Genomes Project, with a cohort that will grow to an order of magnitude larger,” said James Sietstra, president of Seven Bridges. “To work with data this large, new analysis structures like our graph-based suite of tools are needed. We are thrilled to have been chosen for this important initiative, and look forward to collaborating with the VA to develop better and faster ways to process, analyze and learn from the wealth of genomic data being collected from participating Veterans.”