Twitter Facebook Google Plus Linkedin email Print Pdf


Big Data for DNA Sequencing

Posted on 28 March 2012 by Pierre Picard

Leids Universitair Medisch Centrum (LUMC) in the Netherlands retained Bull to help design a Big Data storage environment

Unravelling the human DNA is a compute and data intensive matter.  Every human being has about three million DNA sequences, all of which need to be uncovered, verified and processed.  For this research, speed is of the essence and fast I/O is crucial in attaining the required results in an adequate timeframe.  The Leids Universitair Medisch Centrum (LUMC) retained Bull to help design a Big Data storage environment that could meet these needs and requirements.

After an extensive and complex selection process, whereby Bull assisted LUMC in finding, designing and testing the best storage architecture: the Isilon storage systems, now part of EMC. Isilon has a solid reputation in medical research because of its superior performance on data throughput.  Capacity and performance were crucial components in the selection process.  However, LUMC required two other vital components: flexibility and management. Isilon met these conditions, allowing LUMC to create and manage data sets in excess of 1 Petabyte.

Bull and LUMC deployed the Isilon cluster,
which consists of four 72NL-series nodes.  This configuration allows LUMC to address almost 200TB of net storage capacity. By using SnapshotIQ and SmartConnect software for load balancing and failover, LUMC is assured of full data redundancy and data recovery functionality.  The complete environment is managed by OneFS, Isilon’s integrated management suite.  The biggest benefit of the Isilon storage system for LUMC is that its research department now features a storage environment that fully adheres to the needs and requirements of DNA research.


More information about Extreme Computing solutions from Bull

Comments are closed.