Wellcome Trust maps big data genetics with DDN HPC storage

Inside the labs at the Sanger Institute. Required processing and storage throughput fluctuates depending on the analysis, which is difficult to predict and varies by workload and project. For a cancer genome sequence, for example, the institute produces two-to-five times more data than average during analysis that must be stored, managed, accessed and archived. “Today we produce more sequences in one hour than we did in our first 10 years,” said Phil Butcher. HPC storage, such as that supplied by DDN to the Sanger Institute is high performance file access storage hardware upon which is built a scale-out parallel file system that can handle billions of files without performance degradation.