Computer Vision / Video Analytics

NVIDIA Parabricks: Accelerating Genomic Analysis from Days to an Hour

Sequencing costs have plummeted with the help of new medical instruments:  almost every 6 months we see new instrument with higher throughput like BGI’s DNBSEQ-T7 at 60 genomes per day. At the world’s rate of sequencing, we’ll generate 20 ExaBytes of data by 2025 – more than Twitter, Youtube and astronomy combined. In fact, it would take all the CPUs in every cloud and more than 200 days to run genome analysis.  

Parabricks, an Ann Arbor, Michigan-based startup, developed a GPU-based solution that speeds up the process of analyzing whole genomes–all 3 billion base pairs in human chromosomes–from days to under an hour. As the platforms generate more data, data analysis has become a major bottleneck in both time and cost perspectives and Parabricks’ solution addresses both of these barriers.

Today, Parabricks officially joins the NVIDIA Healthcare team to continue to advance GPU-accelerated genomic analysis.

“Next generation sequencing is in high demand with national sequencing programs, clinical genomics and is driving personalized medicine,” said Kimberly Powell, NVIDIA Vice President of Healthcare. “We are excited to have the Parabricks team join NVIDIA and double down on providing fast and accurate genome analysis tools to take genomics to the next level.”

Parabricks’ portfolio of GPU-accelerated pipelines span popular use cases such as GATK Germline, GATK Somatic, Deep Learning-based variant calling and Copy Number Analysis.  Users experience orders of magnitude faster analysis for the whole pipeline, while generating 100% equivalent results as standard tools. All the tools are containerized and available on major public clouds or on-premise for wide availability. Furthermore, Parabricks will release its solution for single cell and RNA pipelines in 2020. As Parabricks has seen great adoption in the clinical space, it will build upon these existing products to provide clinical grade software where turnaround time is critical.

“Our focus has been on speeding up these applications and making them enterprise grade, push button solutions,”  Ankit Sethia, Parabricks co-founder and CTO said. “Integrating with NVIDIA will enable us to leverage world leaders in AI to transform traditional analyses such as variant calling and others in the overall sequencing workflow.”

Parabricks is built using NVIDIA CUDA-X and benefits from CUDA, cuDNN and TensorRT inference software and runs on NVIDIA entire computing platform from NVIDIA T4 to DGX to cloud GPU instances. 

“We plan to provide accelerated tools for major established genomic analyses, continue supporting all major versions of these packages in the long term,  and include invaluable enterprise grade support to many major institutions,” said Mehrzad Samadi, Parabricks co-founder and CEO. “Now, as part of NVIDIA, we can scale our efforts to provide these analyses to everyone looking to explore new and impactful ways of analyzing genomic data to find new insights.”

Parabricks is now available on NGC.

Learn more about NVIDIA Clara.

Discuss (0)