With big data will come big responsibility for the 11 Centers of Excellence to be created at UCLA, USC and seven other universities nationwide, the National Institutes of Health announced Thursday.
The NIH’s Big Data to Knowledge (BD2K) initiative will grant nearly $32 million this year and $656 million through 2020 to institutions working to improve use, sharing and analysis of biomedical data sets, also known as “big data.”
Big data includes everything from basic patient histories to imaging projects, like the USC Institute for Neuroimaging’s collection of brain scans, to myriad medical studies conducted worldwide. To put it into scale, physically storing this data would take 400 million four-drawer filing cabinets, according to the NIH.
“Data creation in today’s research is exponentially more rapid than anything we anticipated even a decade ago,” said NIH Director Francis S. Collins in a statement. “Mammoth data sets are emerging at an accelerated pace in today’s biomedical research and these funds will help us overcome the obstacles to maximizing their utility.”
UCLA’s Center of Excellence for Big Data will be granted $11 million to tackle cloud-based methods for data integration and analysis, specifically in research on protein markers linked to cardiovascular disease.
“Data is stored in diverse formats, making it difficult to compare and analyze,” Peipei Ping, the UCLA center’s principal investigator and a professor at UCLA’s David Geffen School of Medicine, said in an official statement. “Researchers need a way to easily access and make sense of these gold mines of information to benefit patients.”
Working with researchers at five organizations — the European Bioinformatics Institute, the Scripps Research Institute, the Scripps Translational Science Institute, the University of Mississippi Medical Center and Sage Bionetworks — the center will develop tools to pull fragments of data on one subject or patient from multiple sources, essentially “crowdsourcing” to create a coherent summary from what could be hundreds of pages worth information and history.
“Our…tools [will] extract keywords and summarize the most critical medical information for physicians,” Ping said. “This will streamline digital access to patient files and allow clinicians to quickly grasp the most relevant details.”
Eventually, the center aims to standardize patient data in electronic health records.
Scientists at USC will have more than one avenue for big data research as one of two schools — the other is Stanford University — to receive four-year funding for two separate centers. Arthur Toga will head the Big Data for Discovery Science center (BDDS) with a $12 million grant, while Paul Thompson helms the ENIGMA Center for Worldwide Medicine, Imaging and Genomics with $11 million in funding. Both neuroscientists will work with data about the brain, but with different concentrations.
“The unifying focus of the BDDS Center is to promote a ‘science of discovery,’” Toga said in an official statement from USC. “We are proposing to create the framework that is essential to truly understand how the brain works and functions.”
While Toga’s center researches the organ itself, Thompson’s ENIGMA Center will employ global collaboration with more than 300 researchers to study nine major brain diseases and “discover predictive factors in the genome that affect brain development and disease.”
“ENIGMA is the largest alliance in the world studying factors that help or harm the brain,” Thompson said in the release. “We will develop new computational algorithms to integrate this vast array of data available to us to find biomarkers of mental illness and brain diseases, allowing for better diagnostics and more personalized medical treatment. In a way, we are extending the mathematics currently used for code-breaking and pattern recognition to find patterns in the brain.”
Other Centers of Excellence will be based at University of Pittsburgh, University of Wisconsin-Madison, University of Illinois Urbana-Champaign, UC Santa Cruz, Harvard University Medical Center, University of Memphis.
— Colleen Park