Follow Datanami:
November 29, 2011

Scale-Out NAS Powering Genomics Business

Datanami Staff

Ambry Genetics, which provides advanced genetic sequencing, testing and genome-based diagnostic services, is not unlike other life science companies in terms of the challenges it faces on the data front. The amount of information generated by sequencing machines is staggering, and accordingly, this has been a hot market for vendors pitching scalable storage.

This week EMC announced that it had found an in at Ambry with its EMC Isilon scale-out NAS, which has been tasked with managing the 100 percent annual data growth the genetics company is addressing.  As EMC noted in their release today, Ambry Genetics was seeking to tackle “big data management challenges and storage administration costs, while accelerating data transfer rates and improving reliability for its genetic sequencing project pipeline.”

Specifically, the company is using EMC Isilon’s X-Series paired with the Isiloin SnapShotIQ, SmartConnect and SmartQuotas applications. As EMC stated today, the scale-out NAS system is storing sequence data that comes off the Illumina sequencing platform. The genomics platform and EMC Isilon offering are integrated together for this use case, which has worked well, according to Chris Medley who directs IT at Ambry Genetics. Medley said that the new installation allowed his compant to take advantage of new techniques, including data tiering, that wouldn’t have been possible before.

Prior to the EMC installation, the genetics company had been using a traditional rack server with blades dedicated exclusively to swallowing the sequence and bioinformatics data. Ambry, in an effort to keep up with data demands, kept filling the racks with more blades, but this wasn’t the answer to their problem, particularly since they required both scalability and high performance.

EMC has been making big news lately with its Isilon division. Earlier this month they announced a win at the University of Utah, which selected its scale-out NAS to power big data medical and geophysical research.

Just as with Ambry Genetics, the University of Utah’s Scientific Computing and Imaging Institute (SCI) was quickly outgrowing its infrastructure as data sizes continued to mount. This was slowing both data access and productivity as well. However, the university was able to have SCI put together under a unified strategy, bringing imaging and research applications under one banner and putting the entire network of users’ home directories on a single shared storage platform.

EMC Isilon are all over the big data movement—this is one of many videos they’ve produced that highlight the role of storage and scale-out NAS for big data workloads.