Characterization and acceleration for genomic sequencing and analysis

The advance of next-generation sequencing (NGS) technology has dramatically reduced the cost of genome sequencing, which is a key technology to enable precision medicine. However, processing and analyzing the huge amount of data collected from NGS sequencers introduces significant computation challenges, and has become the bottleneck in many research and clinical applications. This has become a major workload for the Center for Domain-Specific Computing (CDSC) for acceleration in the past three years. In this talk, I shall present our ongoing study on characterizing and accelerating the best practice pipeline for genomic sequencing and analysis recommended by the Broad Institute. Our study includes the use of SSD and hardware accelerators on individual workstations, local computing clusters, and public clouds, such as Amazon AWS and Google Compute Engine.