Fifteen years ago, the first human genome was sequenced. It had taken 20 years and had cost almost $3 billion. Today it’s possible to sequence 3 billion base pairs in under a day and for less than $1,000, making it feasible to use whole genome sequencing for research and clinical applications.
As the demand for genome sequencing grows, researchers are generating a tidal wave of data that doubles in size every year. The data that’s generated by whole genome sequencing requires massive amounts of compute power, storage, and data management that can easily become a bottleneck. To keep up with the increased demand for sequencing, organizations like yours must be able to complete more sequencing jobs in less time without sacrificing accuracy or security.
NetApp partner Parabricks has high-performance GPU-accelerated genomic analysis software that speeds up the processing time of genomic pipelines. With standard CPU-based approaches, processing can take days, but with Parabricks, it takes only minutes. Parabricks software in combination with the NetApp® ONTAP® AI proven architecture, powered by NVIDIA DGX supercomputers and NetApp cloud-connected storage, enables you to deploy a fully integrated, end-to-end AI solution that’s tuned for compute- and data-intensive genomic workloads.
With this joint solution, you can:
- Accelerate genome sequencing by an average of 50 times compared with CPU-only solutions.
- Perform more genomic analysis operations in less time with industry-leading cloud connected all-flash storage from NetApp and NVIDIA DGX servers.
- Protect sensitive genomic data while you improve test accuracy for AI-powered precision calculations.
- Lower your TCO with industry-leading data-efficiency technologies and the advantage of 25 times greater capacity than with competitive systems.
- Accelerate your return on investment with simplified integration, automation, and orchestration of data in clouds and on the premises.
The following graph shows the speed-up in whole genome sequencing (WGS) that the Parabricks and NetApp solution achieved in testing compared with a CPU-only solution. This test included ONTAP AI with a NetApp AFF A800 storage controller, eight NVIDIA Tesla V100 SXM2 32GB GPUs, Ubuntu 16.04, and 526GB of memory.
With Parabricks on ONTAP AI, you can optimize throughput to complete more genomic processing jobs in less time. This integrated solution gives you the flexibility to scale to accommodate more genomic tasks and to meet increased customer demand. You can also eliminate guesswork and get started faster with a validated reference architecture that detangles design complexity.
Start accelerating your genome sequencing workflows, improving test accuracy, and lowering your TCO today. For more information about the Parabricks and NetApp joint solution, read the white paper.