nvidia / deepvariant

Run Google's DeepVariant optimized for GPU. Switch models for high accuracy on all major sequencers.

Model Overview


DeepVariant (the Parabricks tool behind the Universal Variant Calling Microservice) is a deep learning model that can help identify variants in short- and long-read sequencing datasets.
This model is ready for commercial use.

DeepVariant works by taking aligned sequencing reads in BAM/CRAM format and utilizes a convolutional neural network (CNN) to classify the locus into true underlying genomic variation or sequencing error. DeepVariant can therefore call single nucleotide variants (SNVs) and insertions/deletions (InDels) from sequencing data at high accuracy in germline samples.

Parabricks DeepVariant is a highly optimized implementation of the DeepVariant pipeline that dramatically improves variant calling runtimes.

This model supports read sets from Illumina, Oxford Nanopore, and Pacific Biosciences natively; supports both whole-genome and whole-exome sequencing; and can output either Variant Call Format (VCF) or genomic VCF.

The Universal Variant Calling NIM can:

  • Process short-read whole exome data
  • Process short-read and long-read whole genome data
  • Perform inference locally or on NVIDIA GPU Cloud
  • Output VCF or gVCF.

Third-Party Community Consideration

This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case; see link to GitHub.


Parabricks Latest Documentation

Terms of use

By using this software or model, you are agreeing to the NVIDIA Parabricks Terms of Use

Model Architecture

Architecture Type: Convolution Neural Network (CNN)

Network Architecture: Inceptionv2

For more information, see the Parabricks documentation.


Input Type(s): Indices (Text, Binary)
Input Format(s): Tarball
Input Parameters: One Dimensional (1D)

  • A reference genome tarball that contains a reference genome and the indices generated by samtools and bwa. This can be generated by running:
samtools faidx <reference genome>
bwa index <reference genome>
tar cvf <reference genome>.tar <reference genome>*
  • A Binary Alignment Map (BAM) file from Parabricks fq2bam or Burrows-Wheeler Aligner.
  • A BAM Index (BAI) file.


Output Type(s): Text (Sample, Manifest, Path, Path)
Output Format: VCF File
Output Parameters: 1D

The output of the DeepVariant Microservice is the following:

  • A VCF file containing variant calls for your sample.
  • A VCF manifest (which contains the needed parts to sign a multipart-upload request if running in the cloud).
  • A path to the STDOUT of the run (either locally or in cloud storage)
  • A path to the STDERR of the run (either locally or in cloud storage)

Software Integration

Supported Hardware Platform(s): NVIDIA GPU(s) with at least 24 GB of RAM, including Hopper, Lovelace, Ampere, Turing, and Volta generations.

Supported Operating System(s): Linux

Model Version:

  • V4.2.1-1


Engine: Triton and PyTriton
Test Hardware: Other