Case Study: BMI Group achieves faster large-scale DNA data processing with Google Cloud Platform

ETH Zurich Deciphering life with the largest-ever DNA search engine

The BMI Group was processing 4 petabytes of sequencing data to build the world’s largest DNA search index, but its on-premises setup couldn’t keep up with the scale. Downloading and processing such massive datasets was slow and costly, forcing the team to work with much smaller data volumes and limiting research progress.

With Google Cloud Platform, the BMI Group moved its sequencing workflows to the cloud, streaming data directly to VM memory and using flexible Compute Engine resources to parallelize processing. Google Cloud Platform enabled them to process 10 terabytes in hours instead of a week, more than 10x faster, while also scaling to 4,000 CPUs and 15 TB of RAM on demand and avoiding storage bottlenecks.

BMI Group

Andre Kahles

Senior Researcher