Scaling life sciences research by deploying AWS ParallelCluster and AWS DataSync

This article describes how JSR Corporation transformed their life sciences research infrastructure using AWS ParallelCluster and AWS DataSync, achieving significant efficiency gains.

• Reduced on-premises CPU usage by 33% and storage requirements by 85%
• AWS ParallelCluster enables flexible compute scaling for sporadic large-scale genomics and medical research workloads
• GPU procurement time reduced from one year to minutes using on-demand instances
• AWS DataSync automates experimental data transfers to S3 during off-peak hours
• Hybrid architecture uses S3 Glacier Deep Archive for backups and S3 Intelligent-Tiering for analysis data
• Eliminated six months of infrastructure planning and deployment overhead
• Automated data management saves researchers up to one week per experiment

JSR's case study demonstrates how cloud HPC services can eliminate on-premises bottlenecks, accelerate GPU access, and streamline data management for life sciences research organizations.