NVIDIA Clara Parabricks for Genomics:
Experience high-throughput, high-accuracy
DNA and RNA sequencing with GPU-accelerated analysis.
OCF’s expert team has worked together with NVIDIA to deliver a reference architecture capable of carrying out end-to-end genomic analysis faster than ever before.
NVIDIA Clara™ Parabricks® is the only GPU-accelerated computational genomics toolkit that delivers fast and accurate analysis for sequencing centers, clinical teams, genomics researchers, and next-generation sequencing instrument developers.
NVIDIA Clara™ Parabricks®, an accelerated computing framework for next-generation sequencing data(NGS), is at the heart of the solution, enabling end-to-end data analysis workflows for DNA and RNA applications. The Clara Parabricks application for NGS has a wealth of benefits, including:
- Enhancing throughput on a single server by up to 60 whole genomes per day, with guaranteed accuracy.
- Allowing users to create pipelines by configuring over 50 tools for any specific application or pipeline.
- Reducing computing costs by up to 50% by running 30-60 times faster than CPU-only solutions.
- Accelerating analysis workflows, from alignment to sorting to variant calling. When more GPUs are used, computing times see near-linear scaling (80 times faster) compared to CPU-only systems.
Consolidating all self-developed reference sequences in one place, rather than scattered around the entire cluster. As next-generation sequencing communities generally run on open-source software, libraries can become difficult to manage due to the different software versions and/or multiple versions of the same dataset.
Take advantage of accelerated tooling for gold-standard germline, somatic, and RNA analysis.
Experience up to 80X faster performance than CPU-only solutions, reducing computing costs by 50%.
Bring the power of deep learning to your genomic analysis with Clara Parabricks and GPUs.
Create powerful, customized workflows by configuring accelerated tools in WDL and NextFlow.
NVIDIA Clara™ Parabricks® provides GPU-accelerated versions of tools used every day by computational biologists and bioinformaticians—enabling significantly faster runtimes, workflow scalability, and lower compute costs.
The toolkit includes full compatibility with workflow languages and managers (WDL, NextFlow, Cromwell) to easily intertwine GPU- and CPU-powered tasks, as well as support for easy cloud deployment (AWS, GCP, Terra, and DNAnexus).
From FastQ to Variant Call Format (VCF), NVIDIA Clara™ Parabricks® accelerates runtimes across a series of hardware configurations with NVIDIA A100 Tensor Core GPUs. Genomic researchers can experience acceleration across every step of their analysis workflows, from alignment to sorting to variant calling. When more GPUs are used, a near-linear scaling in compute times is observed compared to CPU-only systems, allowing over 80X acceleration.
As NVIDIA 's Elite Partner, we officially delivering NVIDIA Clara Parabricks to the Life Sciences industry. We offer experienced, trusted advice on all aspects of AI applications for Life Sciences. Whatever your queries is, just have a conversation with an OCF's expert!
Derive more insights with faster analysis
Starting with FASTQ files, Clara Parabricks uses the GPU architecture to accelerate genomic data analysis, delivering the flexibility researchers require to meet the specific needs of their projects.
Reduce computing costs
With only one GPU server, Clara Parabricks can provide throughput comparable to more than 50 CPU servers, reducing IT management overhead and operating costs (including power and cooling).
Achieve the same results as CPU-only solutions
The output binary alignment map (BAM) file after alignment, sorting, marking duplicates, and applying base quality score recalibration (BQSR) is identical to the baseline CPU equivalent
The UK Biobank is the world’s most comprehensive biomedical data resource, including de-identified medical, health, and lifestyle records from more than
500,000 volunteer participants in the UK. The UK Biobank undergoes ongoing data collection, coupled with electronic health records, that has generated over 800,000 data files and more than 10 million genetic variants.
The Clara™ Parabricks Solution on DNAnexus
The UK Biobank has made NVIDIA Clara™ Parabricks on DNAnexus available to their researchers in support of the latest release of a 450,000 whole exome data
set. This solution allows any UKB registered researcher to analyse the exomes at a high speed with the same custom DeepVariant model used by Regeneron Genetics center. Researchers can use the protocol for their own projects, or verify the exome variants found by Regeneron.
Accelerating Analysis to Improve Outcomes
GPUs can accelerate the entire analytics workflow, allowing more data to be collected and analysed more accurately in a shorter amount of time.
Long-Read Sequencing
NVIDIA Parabricks—the only GPU-accelerated suite of secondary analysis tools, including the Genome Analysis Toolkit (GATK) and DeepVariant, among others—can be used for both short- read and long-read data analysis.
An Example of Mutational Signatures
The Cancer Grand Challenges’ Mutographs team, an international research group funded by Cancer Research UK, is using NVIDIA GPU-accelerated machine learning models to study DNA from the tumours of 5,000 patients with five different cancer types: pancreatic, kidney, colorectal, and two kinds of oesophageal cancer.
To experience NVIDIA Clara Parabricks, complete the form and our experts will reach out with the next steps. If approved, you’ll get access to a virtual instance that includes everything you need to explore the library of hands-on labs.