NVIDIA Clara Parabricks v4.0.0

Run a GPU-accelerated DeepVariant algorithm.

This tool is a deep-learning-based germline variant caller that can apply different models trained for specific sample types (such as whole genome vs. whole exome sequencing) to gain a higher accuracy result.

Parabricks has accelerated the Google Deepvariant to extensively use GPUs and finish 30x WGS analysis in 25 minutes instead of hours. The Parabricks flavor of Deepvariant is more like other command line tools that users are familiar with: It takes a BAM and reference as inputs and produces variants as outputs.

Currently, Deepvariant is supported for T4, V100, and A100 GPUs out of the box. Please visit the Models for additional GPUs section for more details.


In version 3.8 the --run-partition option was added, which can lead to a significant speed increase. However, using the --run-partition, --proposed-variants, and --gvcf options at the same time will lead to a substantial slowdown. A warning will be issued and the --run-partition option will be ignored.


# This command assumes all the inputs are in and all the outputs go to . $ docker run --rm --gpus all --volume <INPUT_DIR>:/workdir --volume <OUTPUT_DIR>:/outputdir -w /workdir \ \ pbrun deepvariant \ --ref /workdir/${REFERENCE_FILE} \ --in-bam /workdir/${INPUT_BAM} \ --out-variants /outputdir/${OUTPUT_VCF}

The commands below are the Google counterpart of the Parabricks command above. The output from these commands will be identical to the output from the above command. See the Output Comparison page for comparing the results.


sudo docker run \ --volume <INPUT_DIR>:/input \ --volume <OUTPUT_DIR>:/output \ google/deepvariant:1.4.0 \ /opt/deepvariant/bin/run_deepvariant \ --model_type WGS \ --ref /input/${REFERENCE_FILE} \ --reads /input/${INPUT_BAM} \ --output_vcf /output/${OUTPUT_VCF} \ --num_shards $(nproc) \ --make_examples_extra_args "ws_use_window_selector_model=true"

Parabricks Deep Variant supports the following models:

  1. Deep Variant WGS

  2. Deep Variant WES

  3. Deep Trio

    1. Parent

    2. Child

Deep Variant models for T4, V100 and A100 GPUs ship with the software. Additional models for A10, A30, A40, and A6000 GPUs can be downloaded from this NGC resource.

Downloading the additional model files will create a sub-directory in your current directory, containing a single .tar file. Extract the content of that tar file:


$ ls -lF drwx------ 2 user user 4096 Aug 31 14:46 deepvariant_model_files_v4.0.0-1.extramodels/ $ cd deepvariant_model_files_v4.0.0-1.extramodels/ $ tar xvf deepvariant_extra_model_files_v4.0.0-1.tar.gz

and copy the file for your model GPU into the <INPUT_DIR>. Use

  • deepvariant.eng for WGS,

  • deepvariant_wes.eng for WES or

  • pacbio/deepvariant.eng for the PacBio model.

Tell pbrun to use the alternate model file by adding the --pb-model-file option:


# This command assumes all the inputs are in and all the outputs go to . $ docker run --rm --gpus all --volume <INPUT_DIR>:/workdir --volume <OUTPUT_DIR>:/outputdir -w /workdir \ \ pbrun deepvariant \ --ref /workdir/${REFERENCE_FILE} \ --in-bam /workdir/${INPUT_BAM} \ --pb-model-file /workdir/<NAME_OF_MODEL_FILE> \ # <--- Add this. --out-variants /outputdir/${OUTPUT_VCF}

Run DeepVariant to convert BAM/CRAM to VCF.

Input/Output file options

--ref REF

Path to the reference file. (default: None)

Option is required.

--in-bam IN_BAM

Path to the input BAM/CRAM file for variant calling. (default: None)

Option is required.

--interval-file INTERVAL_FILE

Path to a BED file (.bed) for selective access. This option can be used multiple times. (default: None)

--out-variants OUT_VARIANTS

Path of the vcf/g.vcf/g.vcf.gz file after variant calling. (default: None)

Option is required.

--pb-model-file PB_MODEL_FILE

Path to a non-default parabricks model file for deepvariant. (default: None)

--proposed-variants PROPOSED_VARIANTS

Path of the VCF file, which has proposed variants for the make examples stage. (default: None)

Tool Options:


Change the window selector model from Allele Count Linear to Variant Reads. This option will increase the accuracy and runtime. (default: None)


Generate variant calls in .gvcf Format. (default: None)


Do not locally realign reads before calling variants. Reads longer than 500 bp are never realigned. (default: None)


Reads are sorted by haplotypes (using HP tag) (default: None)


Keep reads that are duplicate. (default: None)

--vsc-min-count-snps VSC_MIN_COUNT_SNPS

SNP alleles occurring at least this many times in the AlleleCount will be advanced as candidates. (default: 2)

--vsc-min-count-indels VSC_MIN_COUNT_INDELS

Indel alleles occurring at least this many times in the AlleleCount will be advanced as candidates. (default: 2)

--vsc-min-fraction-snps VSC_MIN_FRACTION_SNPS

SNP alleles occurring at least this fraction of all counts in the AlleleCount will be advanced as candidates. (default: 0.12)

--vsc-min-fraction-indels VSC_MIN_FRACTION_INDELS

Indel alleles occurring at least this fraction of all counts in the AlleleCount will be advanced as candidates. (default: None)

--min-mapping-quality MIN_MAPPING_QUALITY

By default, reads with any mapping quality are kept. Setting this field to a positive integer i will only keep reads that have a MAPQ >= i. Note this only applies to aligned reads. (default: 5)

--min-base-quality MIN_BASE_QUALITY

Minimum base quality. This option enforces a minimum base quality score for alternate alleles. Alternate alleles will only be considered if all bases in the allele have a quality greater than min_base_quality. (default: 10)

--mode MODE

Value can be one of [shortread, pacbio, ont]. By default, it is shortread. If mode is set to pacbio, the following defaults are used: --norealign-reads, --alt-aligned-pileup diff_channels, --vsc-min-fraction-indels 0.12. If mode is set to ont, the following defaults are used: -norealign-reads, --variant-caller VCF_CANDIDATE_IMPORTER. (default: shortread)

--alt-aligned-pileup ALT_ALIGNED_PILEUP

Value can be one of [none, diff_channels]. Include alignments of reads against each candidate alternate allele in the pileup image. (default: None)

--variant-caller VARIANT_CALLER

Value can be one of [VERY_SENSITIVE_CALLER, VCF_CANDIDATE_IMPORTER]. The caller to use to make examples. If you use VCF_CANDIDATE_IMPORTER, it implies force calling. Default is VERY_SENSITIVE_CALLER (default: None)


Add another channel to represent HP tags per read. (default: None)


Auxiliary fields of the BAM/CRAM records are parsed. If either --sort-by-haplotypes or --add-hp-channel is set then this option must also be set. (default: None)


If passed, the WES model file will be used. Only used in shortread mode. (default: None)


Divide the whole genome into multiple partition and run multiple processes at the same time, each on 1 partition. (default: None)


If True, include MED (default: None)


If True, allele counter left align INDELs for each read. (default: None)


If True, add insert_size channel into pileup image. By default it's true in WGS and WES mode (default: None)


If True, don't add insert_size channel into pileup image. (default: None)


Allow deepvariant to run on reads of size 512bp. Default is 320 bp (default: None)


Use an extra thread for the pre-align step. More useful when --max-reads-size-512 is set. (default: None)

--max-reads-per-partition MAX_READS_PER_PARTITION

The maximum number of reads per partition that we consider before following processing such as sampling and realigner. (default: 1500)

--partition-size PARTITION_SIZE

The maximum number of basepairs we will allow in a region before splitting it into multiple smaller subregions. (default: 1000)


If True, allele counter keeps track of ref supporting reads.By default allele counter keeps a simple count of number of reads supporting ref. (default: None)


Calculate phases and add HP tag to all reads on a fly. (default: None)


Interval within which to call the variants from the BAM/CRAM file. Overlapping intervals will be combined. Interval files should be passed using the --interval-file option. This option can be used multiple times (e.g. "-L chr1 -L chr2:10000 -L chr3:20000+ -L chr4:10000-20000") (default: None)

Common options:

--logfile LOGFILE

Path to the log file. If not specified, messages will only be written to the standard error output. (default: None)

--tmp-dir TMP_DIR

Full path to the directory where temporary files will be stored.

--with-petagene-dir WITH_PETAGENE_DIR

Full path to the PetaGene installation directory. By default, this should have been installed at /opt/petagene. Use of this option also requires that the PetaLink library has been preloaded by setting the LD_PRELOAD environment variable. Optionally set the PETASUITE_REFPATH and PGCLOUD_CREDPATH environment variables that are used for data and credentials (default: None)


Do not delete the directory storing temporary files after completion.


Do not override seccomp options for docker (default: None).


View compatible software versions.

GPU options:

--num-gpus NUM_GPUS

Number of GPUs to use for a run. GPUs 0..(NUM_GPUS-1) will be used.

© Copyright 2022, Nvidia. Last updated on Jun 28, 2023.