NVIDIA Clara Parabricks
NVIDIA Clara Parabricks
NVIDIA Clara™ Parabricks is a computational framework supporting genomics applications from DNA to RNA. It employs NVIDIA’s CUDA, HPC, AI, and data analytics stacks to build GPU accelerated libraries, pipelines, and reference application workflows for primary, secondary, and tertiary analysis. Clara Parabricks is a complete portfolio of off-the-shelf solutions coupled with a toolkit to support new application development to address the needs of genomic labs.
The NVIDIA Clara Parabricks application framework includes:
- Clara Parabricks Pipelines: Designed for high throughput labs, this suite of enterprise-grade, turnkey software runs GPU-accelerated pipelines for DNA Germline variant calling for population genomics, DNA Somatic variant calling for cancer genomics, and RNA sequencing projects from whole transcriptome to single cell analysis.
- Clara Parabricks Toolkit: A technology stack of CUDA accelerated libraries and deep learning modules, C++ and Python APIs, reference applications and integrations with 3rd party applications and workflows to develop powerful compute tools.
NVIDIA Clara Parabricks Pipelines
Fast | Accurate | Scalable
Based on the Broad Institute’s Genome Analysis Toolkit (GATK), Clara Parabricks Pipelines enable GPU-accelerated GATK along with other third party tools, like Google’s DeepVariant caller. Currently, GATK v4.1 is supported and Best Practices are enabled. Starting with DNA sequencing reads, Clara Parabricks Pipelines map, align, filter and call variants for either germline or somatic variant detection. For RNA based projects, both STAR and STAR-Fusion align sequencing reads allowing for reads to be split to account for exon/intron boundaries, followed by variant calling.
Clara Parabricks Pipelines were built to optimize acceleration, accuracy and scalability. Users can achieve a 35-50X acceleration and 99.99% accuracy for variant calling when comparing against CPU-only BWA-GATK4 pipelines. It can run the full GATK4 Best Practices, and is also fully configurable. As a result, you can choose which steps, parameter settings, and versions of the pipeline to run.
Standard Evaluation License
Get full access to Clara Parabricks Pipelines for one month with unlimited GPU compute for evaluation purposes.
Purchase Clara Parabricks
Contact a sales representative for pricing.
Clara Parabricks Pipelines Software Overview
Clara Parabricks Pipelines deliver major improvements in throughput for common analytical tasks in genomics, including DNA Germline, DNA Somatic variant calling and RNA-Seq analysis. The core of Clara Parabricks Pipelines is the capability to take raw data and transform it according to the users requirements. A user can choose to run specific accelerated tools or full, commonly used pipelines.
New Features of Clara Parabricks Pipelines v3.0:
- A 2X performance increase for DNA Germline variant calling running on NVIDIA A100 tensor core GPU, cutting analysis time down to 20 minutes.
- Software optimizations to reduce cloud computing costs by 30% when running on NVIDIA V100 and NVIDIA T4
- New RNA-Seq Single Cell Pipeline, delivering 10X performance over GATK4.1 Best Practices on GPUs.
- DeepGermline Pipeline updated and optimized to Google’s DeepVariant v0.10, reducing runtime from 5 hours to 40 minutes.
Germline End to End Secondary Analysis Performance
On-Demand Cloud Computing Cost (Price) Per Hour*Based on estimated costs of 8X V100
Clara Parabricks Pipelines Resources
Analyzing COVID-19 Short Read Sequencing Data
Decrease the time it takes to analyze sequencing data coming out of short read sequencers. Learn how Clara Parabricks Pipelines can be applied to genomic workflows in viral pandemics.
How-To Get Started With Clara Parabricks Pipelines
Use this step-by-step instructional video to learn how to get up and running on Clara Parabricks Pipelines.
The Clara Parabricks Toolkit is a collection of edge libraries, reference workflows and open source applications being supported by NVIDIA and tested by our industry collaborators to accelerate the application of high performance computing, deep learning, and data analytics in genomics.
Use the Clara Parabricks Toolkit to develop AI-assisted workflows, to optimize mapping, aligning, and polishing for de novo genome assembly, and enhance the resolution of single cell epigenomics.
NVIDIA CLARA PARABRICKS TOOLKIT
Libraries -- python APIs
- CUDA Mapper - CUDA accelerated all-to-all mapping of sequencing reads, used for genome assembly workflows.
- CUDA Aligner - CUDA based library with accelerated algorithms for sequencing read alignment, used for genome assembly applications such as Racon and for variant calling.
- CUDA POA - CUDA library for accelerated partial order alignment, used for genome assembly and basecalling.
- Atac-Seq Deep Learning Denoising - a deep learning application to improve coverage track denoising and peak calling from low-coverage or low-quality ATAC-Seq data. Outputs are in the standard file format.
- RNA-Seq Analytics - an interactive notebook for single cell RNA-Seq data.
- DL Variant Caller - a deep learning based variant caller that outputs in the standard file format.
- Long Read Mapping - based on the minimap2 software, this application maps long sequencing read data and outputs in the standard file format.
3rd Party Applications
- Racon - consensus application for de novo genome assembly that utilizes cudaAligner for accelerated alignment and cudaPOA for accelerated polishing
- Raven - application for de novo genome assembly of long uncorrected reads that utilizes cudaAligner for accelerated alignment and cudaPOA for accelerated polishing.li>
- Bonito - basecaller for Oxford Nanopore reads that utilizes cudaPOA for accelerated consensus.
- Medaka - a deep learning consensus application for de novo genome assembly.
Access the full Clara Parabricks Toolkit
Clara Parabricks Toolkit Resources
De Novo Genome Assembly from Long Uncorrected Reads
Racon, a consensus module for genome assembly, enables consensus genomes with similar or better quality than state-of-the-art methods with greater speed.
Using the Clara Parabricks Toolkit Against COVID-19
Use this get started guide for long read basecalling, short read alignment, and long read polishing on github.
Join the NVIDIA Developer Program