Allen Institute teams up with AWS to build first-ever map of the brain

Just as the periodic table is foundational to chemistry and the Human Genome Project revolutionized modern genetics, researchers at the Allen Institute for Brain Science have teamed up with Amazon Web Services to create what could become a “transformative” new resource for the field of neuroscience. 

AWS on Wednesday announced its technology will support the Allen Institute as it builds a map of the human brain, called the Brain Knowledge Platform. This platform, the first of its kind, is designed to be a complete reference of individual cells in the brain, and should eventually serve as the world’s largest open source brain cell database. 

To build the new platform, the Allen Institute is using single cell genomics technologies. Researchers measure the genes used by individual brain cells to create a “cell fingerprint,” and cells with similar fingerprints will be grouped into “cell types,” resulting in a high-resolution map of the entire brain. 

Once the reference is complete, scientists should better understand links between genetics and different cognitive functions. Researchers believe the platform could provide insights into why diseases like Alzheimer’s and Parkinson’s occur. 

“This really is like the periodic table for the brain,” Dr. Ed Lein, senior investigator at the Allen Institute for Brain Science, said Wednesday during a presentation about the platform in Washington, D.C. “It’s revealed in dramatically higher complexity than we’ve ever had access to before.”

The Allen Institute is a nonprofit research institute based in Seattle, Washington. It’s made up of a number of different institutes, including one that focuses on neuroscience, and is perhaps best known for creating a number of different large-scale data resources.  

But even though the Allen Institute is no stranger to data, there are hundreds of billions of cells in the brain — so creating a reference like the Brain Knowledge Platform means researchers will have to contend with massive amounts of data. 

“We’re just running into these enormous, enormous problems of data size,” Lein said during a briefing with reporters Wednesday. “The scale of data just keeps getting bigger and bigger.”

As such, the Allen Institute is leveraging AWS’ cloud computing and machine learning to standardize and consolidate complex brain data into one place. 

When carrying out research involving genetics and imaging, scientists are often working with petabytes and even exabytes of data. Dr. Rowland Illing, director of international public sector health at AWS, said at the briefing that consuming 40 petabytes of data would require someone to watch 4k video for 24 hours a day, seven days a week, for 100 years. 

The amount of data available to researchers is expected to keep growing in coming years, but Lein said there is also a lot of existing brain data in the neuroscience field. The problem, he said, is that much of it is disorganized and decentralized, which makes it difficult for researchers to access. 

The Allen Institute plans to use AWS’ technology to successfully interpret this disparate data even if it’s stored across different formats and locations, which Lein said will hopefully further democratize access to knowledge and bring parts of the neuroscience community together. 

“While this is really in its early phases now, the goal of the Brain Knowledge Platform is to transform this fragmented landscape of neuroscience information into a unified ecosystem,” he said.

The Allen Institute will work to build the Brain Knowledge Platform over the next five years. Lein said it is still in its early phases, but the potential for the tech is immense. 

“If we can do this, imagine the impact on the field,” he said. “We can unify the disparate parts of the field that can’t talk to one another at the moment. We can accelerate our understanding of brain function, as well as new approaches for treating diseases.”