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
What it does
Not yet documented on this card.
Tasks, data types and cancers
Architecture
Training data
Genome in a Bottle truth sets (NA12878 and others) across Illumina, PacBio and ONT sequencing.
Linked datasets
- benchmark Genome in a Bottle (GIAB) Open download
Evaluation
| Benchmark / dataset | Metric | Value | External validation | Source |
|---|---|---|---|---|
| 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
Regulatory status and intended use
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
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.