Cancer3.AIAI in OncologyAI Models › DeepVariant
Tool Open weights Research use only genomics

DeepVariant

Deep-learning variant caller that turns aligned sequencing reads into pileup images and classifies genotypes with a CNN; widely used for germline calling, with the companion DeepSomatic extending the approach to tumour–normal somatic variants.

At a glance

DeveloperGoogle
Released2017-12-04
LicenceBSD-3-Clause
AvailabilityOpen weights
KindTool
Regulatory statusResearch use only

What it does

Not yet documented on this card.

Tasks, data types and cancers

Clinical settingDiagnosisBasic research
CancerPan-cancer
InputBAM/CRAM + reference
OutputVCF/gVCF

Architecture

FamilyCNN over read-pileup images

Training data

Genome in a Bottle truth sets (NA12878 and others) across Illumina, PacBio and ONT sequencing.

Linked datasets

Evaluation

Benchmark / datasetMetricValueExternal validationSource
PrecisionFDA Truth Challenge (2016) SNP/indel F1 highest SNP accuracy award yes Source

How to run

docker run -v $PWD:/data google/deepvariant:latest /opt/deepvariant/bin/run_deepvariant \
  --model_type=WGS --ref=/data/ref.fa --reads=/data/sample.bam \
  --output_vcf=/data/sample.vcf.gz --num_shards=8
LibraryDocker image google/deepvariant

Regulatory status and intended use

Regulatory statusResearch use only
Intended useResearch pipelines; clinical labs validate it inside their own accredited workflows.

Source →

Regulatory status is quoted from the source linked above and can change. Research-use-only models must not be used for clinical decisions.

Limitations and bias

  • Germline-first; somatic calling needs DeepSomatic or a dedicated caller.
  • Model type must match the sequencing technology.

Sources

  1. Poplin R et al. A universal SNP and small-indel variant caller using deep neural networks. Nat Biotechnol 2018
  2. GitHub — google/deepvariant

This page is educational — it is not medical advice and does not replace consultation with an oncologist. Diagnostic and treatment decisions are made solely by specialist physicians.