Case Study: Guardant Health achieves scalable genomic data processing with Alluxio

Guardant Health scales genomic data with Alluxio to 1.2PB+ archival storage

Guardant Health, a world leader in comprehensive liquid biopsy, faced the challenge of processing exabytes of genomic data from its blood tests. They required a data-processing solution that was flexible to deploy on-premise and in the cloud, scalable to massive data volumes, and performant enough to provide timely results to healthcare providers. Their previous disk-based storage system was a significant performance bottleneck.

Alluxio provided a unified storage layer to solve this by creating an on-demand pipeline from disparate storage systems to the compute nodes. The solution implemented Alluxio with Minio as the under store and Apache Spark as the compute engine. This architecture delivered orders of magnitude higher performance, decoupled compute from storage for independent scaling, and provided a cost-optimal, cloud-native system. With Alluxio, Guardant Health achieved a robust and scalable data processing pipeline to support their rapidly growing data needs.

Guardant Health