Clara Genomics was created to address the growing size and complexity of genomics sequencing & analysis with accelerated and intelligent computing.

Clara Genomics Analysis SDK

Clara Genomics Analysis SDK is now available under Open Source terms to provide developers free and open access, please click below to access the release through GitHub.This release includes:

  • CUDA libraries for accelerated mapping, alignment, partial order alignment of sequencing reads: cudaMapper, cudaAligner, and cudaPOA
  • C++ and Python APIs for cudaAligner and cudaPOA
  • Debian, RPM, and PyPI packaging
  • Integration into 3rd party applications, including the Racon consensus module for genome assembly, the Raven genome assembler, and the Bonito basecaller

AtacWorks SDK

AtacWorks SDK is now available under Open Source terms, please click below to access the release through GitHub.
The latest release includes:

  • I/O tools for BED, BEDGRAPH, and BigWig file formats
  • Training deep learning models using a customizable resent architecture
  • Pre-trained models that can be applied to new data
  • Inference using a newly trained or a provided model to produce denoised ATAC-seq signal and peak calls

The field of Genomics has several transformative trends that put computing at the forefront of progress: increasing instrument throughput, AI enabled analysis applications and reduction in cost of sequencing to study large populations.

NVIDIA’s GPU Accelerated Computing platform enables real-time genomics workflows with high performance computing, deep learning and analytics on a single architecture that lives on the edge in the sequencer to the datacenter and every public cloud.

A high-level workflow from sample prep to final analysis that starts with isolating the DNA of an organism. This isolated sample is then loaded on a sequencing instrument, where embedded GPUs are used to accelerate primary analysis and enable next-generation base calling using deep neural networks (DNNs).

Secondary analysis or sequence analysis uses NVIDIA GPU computing for the Genome Analysis Toolkit (GATK), DNN-based variant calling, and de novo genome assembly.

Clara Genomics includes CUDA accelerated libraries and deep learning modules, C++ and Python APIs, reference applications, and integrations with 3rd party applications and workflows. The latest release focuses on basecalling, genome assembly, and AI-denoised ATAC-seq data processing.

Clara Genomics Technology Stack

Clara Genomics Technology Stack includes the AtacWorks toolkit for the development of AI-assisted workflows to reduce sequencing costs, improve data quality, and increase the resolution of single-cell epigenomics. A detailed description and results for these use cases are provided in the AtacWorks preprint.

Clara Genomics Technology Stack includes CUDA accelerated software system libraries that form the foundation of GPU computing.

  • 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.

These system libraries form the compute foundation and enable the GPU acceleration of the following applications:

  • Racon - consensus module for de novo genome assembly that utilizes cudaAligner for accelerated alignment and cudaPOA for accelerated polishing.
  • Raven - tool for de novo genome assembly of long uncorrected reads that utilizes cudaAligner for accelerated alignment and cudaPOA for accelerated polishing.
  • Bonito - basecaller for Oxford Nanopore reads that utilizes cudaPOA for accelerated consensus.

For questions, please reach out to us on: Forums


(Click logos to learn more)

Oxford Nanopore

Oxford Nanopore Technologies is speeding the discovery of pathogens with its edge device, a portable, low-cost, real-time DNA and RNA sequencer. This edge device connects to the recently-introduced MinIT hand-held AI supercomputer, powered by NVIDIA, and runs sequence analysis in real time, anywhere — even in the field.

Learn how Oxford Nanopore has accelerated the entire Genomics Workflow on GPUs.

Read More

Oak Ridge National Comet

Researchers at the US Department of Energy’s Oak Ridge National Laboratory broke the exascale barrier, achieving a peak throughput of 1.88 exaops—faster than any previously reported science application—while analyzing genomic data on the Summit supercomputer powered by NVIDIA GPUs.

Read more about Oak Ridge


Anyone with a hundred bucks and a saliva sample can get some intriguing genetic insights by mail-order. But using DNA for research or clinical purposes requires the whole genome and analysing that is computationally intensive. NVIDIA’s Inception partner Parabricks is shrinking computational analysis time from days to hours.

Read more about Parabricks

ThermoFisher Scientific

Low Cost, Simple, Scalable, Real Time Sequencing enabled by ThermoFischer Scientific on NVIDIA GPUs.

Learn More from this GTC Presentation

Disclaimer: Clara SDKs and samples are for developmental purposes only and cannot be used directly for clinical procedures.