Northrop Grumman leads personalized medicine breakthroughs with Google Genomics
Experts at Northrop Grumman believe traditional healthcare is reactive, and that a shift to tailored treatment could significantly improve medical outcomes. The Northrop Grumman team uses Google Genomics to provide insights from genome sequence, environment, family medical history, socioeconomic factors and more that will lead to better diagnosis and prognosis decisions.
The quest for personalized healthcare
“Doctors need new technologies to provide individualized care,” says Leon Li, future technical leader and systems engineer at Northrop Grumman. “Researchers devoted to personalized medicine can now use big data tools to analyze clinical records, genomic sequences and laboratory data. All of this valuable data may reveal how differences in an individual’s genetics, lifestyle and environment influence reactions to disease.”
But reaching that point will require overcoming the challenges of processing and manipulating enormous datasets. “The raw information for a single human genome is over 100 gigabytes spanning more than 20,000 genes,” Li says. Another issue is culling useful data from non-electronic sources. “Doctors’ handwritten notes are hard for computers to make sense of,” he adds.
Real-time results change what’s possible
Northrop Grumman plans to help researchers and clinicians clear that hurdle with a personalized health analytics platform. Li and his colleagues recently designed a prototype of this platform, using Google Genomics and Google Cloud Platform to facilitate massive data analysis and processing.
The health analytics platform was built in layers, with data storage for genome information and electronic health records serving as the base. An annotation layer provides tools to pull clinical information from those health records and a database of aggregated phenotypic and disease association data. The analytics layer, built on Google BigQuery and Google Compute Engine, models and analyzes data to provide a rapid gauge of genomic risk.
“Our platform aims to improve patient health by expanding the knowledge base for personalized medicine with discovery of complex hidden patterns across long time periods and among large study populations,” Li says, noting that an analysis of genomic data from 1,000 patients across more than 200 diseases generated near real-time results. “With Google Genomics and Google BigQuery, terabytes of genomics information can be analyzed in only a few seconds.”
The platform is geared to improve knowledge extraction from health data and to facilitate personalized medicine research. It could dramatically shorten a researcher’s time to receive answers for questions that are currently difficult to ask, such as which gene variants are linked to a particular medical condition. A final layer of the platform provides a framework for tools to collaborate, visualize data and perform high-level analytics.
Along with being scalable and providing real-time insights, Google Genomics is affordable and secure. Li says: “The scalable storage and analysis tools provided by Google Cloud Platform and Google Genomics reduce costs and increase security when compared to in-house IT systems.”