deepvariant
DeepVariant is an analysis pipeline that uses a deep neural network to call genetic variants from next-generation DNA sequencing data.
What is deepvariant?
DeepVariant is an analysis pipeline that uses a deep neural network to call genetic variants from next-generation DNA sequencing data.
Overview of deepvariant
What it is
DeepVariant is a deep learning-based variant caller that takes aligned reads (in BAM or CRAM format), produces pileup image tensors from them, classifies each tensor using a convolutional neural network, and finally reports the results in a standard VCF or gVCF file. It supports germline variant-calling in diploid organisms.
Key features
- High accuracy – won the 2020 PrecisionFDA Truth Challenge V2 for multiple technology categories and the 2016 PrecisionFDA Truth Challenge for best SNP Performance.
- Flexibility – works out-of-the-box with PCR-positive samples, low quality sequencing runs, and different sequencing technologies (Illumina, PacBio HiFi, Oxford Nanopore, Complete Genomics, Roche SBX, etc.).
- Ease of use – no filtering is needed beyond setting a minimum quality threshold.
- Cost effectiveness – on Google Cloud, a non-preemptible n1-standard-16 machine costs ~$11.8 for a 30x whole genome and ~$0.89 for an exome; preemptible pricing reduces costs further.
- Speed – runtime metrics are available for all supported datatypes on a 96-core CPU-only machine.
- Usage options – can be run via Docker or binaries, on-premise or in the cloud, with support for GPUs and TPUs.
Use cases
- Germline variant calling in diploid organisms for whole genome, whole exome, and targeted sequencing.
- Supports data from Illumina, Element, PacBio HiFi, Oxford Nanopore R10.4.1, Complete Genomics, Roche SBX, and pangenome-mapping-based approaches.
- Pangenome-aware variant calling for WGS and WES.
- Somatic variant calling via the DeepSomatic repository.
- Trio/duo variant calling via DeepTrio.
Getting started
BIN_VERSION="1.10.0"
docker run \
-v "YOUR_INPUT_DIR":"/input" \
-v "YOUR_OUTPUT_DIR:/output" \
google/deepvariant:"${BIN_VERSION}" \
/opt/deepvariant/bin/run_deepvariant \
--model_type=WGS \ **Replace this string with exactly one of the following [WGS,WES,PACBIO,ONT_R104,HYBRID_PACBIO_ILLUMINA]**
--ref=/input/YOUR_REF \
--reads=/input/YOUR_BAM \
--output_vcf=/output/YOUR_OUTPUT_VCF \
--output_gvcf=/output/YOUR_OUTPUT_GVCF \
--num_shards=$(nproc) \ **This will use all your cores to run make_examples. Feel free to change.**
--vcf_stats_report=true \ **Optional. Creates VCF statistics report in html file. Default is false.
--disable_small_model=true \ **Optional. Disables the small model from make_examples stage. Default is false.
--logging_dir=/output/logs \ **Optional. This saves the log output for each stage separately.
--haploid_contigs="chrX,chrY" \ **Optional. Heterozygous variants in these contigs will be re-genotyped as the most likely of reference or homozygous alternates. For a sample with karyotype XY, it should be set to "chrX,chrY" for GRCh38 and "X,Y" for GRCh37. For a sample with karyotype XX, this should not be used.
--par_regions_bed="/input/GRCh3X_par.bed" \ **Optional. If --haploid_contigs is set, then this can be used to provide PAR regions to be excluded from genotype adjustment. Download links to this files are available in this page.
--dry_run=false **Default is false. If set to true, commands will be printed out but not executed.
License and pricing
License: BSD-3-Clause. Pricing: open source (free).
Based on the project's public README and repository metadata.