deeptrio - NVIDIA Docs

Run GPU-accelerated DeepTrio for calling de novo variants.

Parabricks has accelerated Google Deeptrio to extensively use GPUs. The Parabricks flavor of Deepvariant is more like other command line tools that users are familiar with: It takes two or three BAM files and reference as inputs and produces both vcf and g.vcf as outputs.

Currently, Deepvariant is supported for T4, V100, and A100 GPUs only.

Quick Start

Copy
Copied!

            
            $ pbrun deeptrio \
    --ref Ref/Homo_sapiens_assembly38.fasta \
    --in-bam-child child.bam \
    --in-bam-parent1 parent1.bam \
    --in-bam-parent2 parent2.bam \
    --sample-name-child sample_child \
    --sample-name-parent1 sample_parent1 \
    --sample-name-parent2 sample_parent2 \
    --out-variants-child child.vcf \
    --out-variants-parent1 parent1.vcf \
    --out-variants-parent2 parent2.vcf \
    --out-variants-gvcf-child child.g.vcf.gz \
    --out-variants-gvcf-parent1 parent1.g.vcf.gz \
    --out-variants-gvcf-parent2 parent2.g.vcf.gz

Compatible Google DeepVariant Commands

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.

Copy
Copied!

            
            mkdir -p output
mkdir -p output/intermediate_results_dir

BIN_VERSION=1.1.0

time sudo docker run \
-v "${PWD}/input":"/input"   \
-v "${PWD}/output":"/output"  \
-v "${PWD}/reference":"/reference" \
google/deepvariant:deeptrio-"${BIN_VERSION}" \
/opt/deepvariant/bin/deeptrio/run_deeptrio \
--model_type WGS \
--ref /reference/Homo_sapiens_assembly38.fasta \
--reads_child /input/child.bam \
--reads_parent1 /input/parent1.bam \
--reads_parent2 /input/parent2.bam \
--output_vcf_child /output/child.vcf \
--output_vcf_parent1 /output/parent1.vcf \
--output_vcf_parent2 /output/parent2.vcf \
--sample_name_child sample_child \
--sample_name_parent1 sample_parent1 \
--sample_name_parent2 sample_parent2 \
--num_shards $(nproc)  \
--intermediate_results_dir /output/intermediate_results_dir \
--output_gvcf_child /output/child.g.vcf.gz \
--output_gvcf_parent1 /output/parent1.g.vcf.gz \
--output_gvcf_parent2 /output/parent2.g.vcf.gz \
--make_examples_extra_args "ws_use_window_selector_model=True"

deeptrio Reference

Run DeepTrio on 3 samples for de novo variant detection

Input/Output file options

--ref REF

Path to the reference file. (default: None)

Option is required.

--in-bam-child IN_BAM_CHILD

Path to the input child bam/cram file for variant calling. (default: None)

Option is required.

--in-bam-parent1 IN_BAM_PARENT1

Path to the input parent1 bam/cram file for variant calling. (default: None)

--in-bam-parent2 IN_BAM_PARENT2

Path to the input parent2 bam/cram file for variant calling. (default: None)

--interval-file INTERVAL_FILE

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

--out-variants-child OUT_VARIANTS_CHILD

Path of child vcf file after variant calling. (default: None)

Option is required.

--out-variants-parent1 OUT_VARIANTS_PARENT1

Path of parent1 vcf file after variant calling (default: None)

--out-variants-parent2 OUT_VARIANTS_PARENT2

Path of parent2 vcf file after variant calling (default: None)

--out-variants-gvcf-child OUT_VARIANTS_GVCF_CHILD

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

Option is required.

--out-variants-gvcf-parent1 OUT_VARIANTS_GVCF_PARENT1

Path of parent1 g.vcf/g.vcf.gz file after variant calling (default: None)

--out-variants-gvcf-parent2 OUT_VARIANTS_GVCF_PARENT2

Path of parent2 g.vcf/g.vcf.gz file after variant calling (default: None)

--pb-model-file-child PB_MODEL_FILE_CHILD

Path of non-default child parabricks model file for deeptrio. (default: None)

--pb-model-file-parent PB_MODEL_FILE_PARENT

Path of non-default parent parabricks model file for deeptrio. (default: None)

Options specific to this tool

--disable-use-window-selector-model

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

--keep-duplicates

Keep reads that are duplicate. (default: None)

--vsc-min-count-snps VSC_MIN_COUNT_SNPS

SNP alleles occurring at least this many times in our 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 our 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 our 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 our AlleleCount will be advanced as candidates. (default: 0.06)

--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 field indicates that we are enforcing 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)

--sample-name-child SAMPLE_NAME_CHILD

Name of sample for child reads. (default: None)

Option is required.

--sample-name-parent1 SAMPLE_NAME_PARENT1

Name of sample for parent1 reads. (default: None)

--sample-name-parent2 SAMPLE_NAME_PARENT2

Name of sample for parent2 reads. (default: None)

--mode MODE

Value can only be [shortread] for now. (default: shortread)

-L INTERVAL, --interval INTERVAL

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)
--keep-tmp: Do not delete the directory storing temporary files after completion.
--license-file LICENSE_FILE: Path to license file license.bin if not in the installation directory.
--no-seccomp-override: Do not override seccomp options for docker (default: None).
--version: 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.
--gpu-devices GPU_DEVICES: GPU devices to use for a run. By default, all GPU devices will be used. To use specific GPU devices, enter a comma-separated list of GPU device numbers. Possible device numbers can be found by examining the output of the nvidia-smi command. For example, using --gpu-devices 0,1 would only use the first two GPUs.