Deepvariant and input CRAM files

Question

[biology.may20]

Good day,

Could anyone please advise how to start DeepVarian if I have CRAM instead of BAM files ?

[DBScan]

What happened when you tried to use a CRAM? Did DeepVariant throw an error?

[biology.may20]

Hello, I'm using syntax from official DeepVariant github page, so there should not be the error, that's why I thought it because of my cram file:

$ PWD=/project_folder
$ INPUT_DIR="${PWD}/cram_folder"
$ mkdir -p ${INPUT_DIR}
$ OUTPUT_DIR="${PWD}/result_folder"
$ mkdir -p "${OUTPUT_DIR}"
$ sudo docker run \
> -v "${INPUT_DIR}":"/input" \
> -v "${OUTPUT_DIR}":"/output" \
> google/deepvariant:"${BIN_VERSION}" \
> /opt/deepvariant/bin/run_deepvariant \
> --model_type=WGS \
> ref=/home/folder_with_ref/some_ref.fa \
> reads=/input/file.cram \
> --output_vcf=/output/output.vcf.gz \
> --output_gvcf=/output/output.g.vcf.gz \
> --num_shards=5
docker: invalid reference format.
See 'docker run --help'.

[GenoMax]

Error in your case is saying:

docker: invalid reference format

See if any of the suggestions here help:

https://www.positioniseverything.net/docker-invalid-reference-format/

[GenoMax]

https://github.com/google/deepvariant says right in first line that

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.

Your CRAM file will need to be sorted and indexed. It will likely need to exist on disk (can't be streamed according to this page).

[biology.may20]

hello, my cram file sorted and indexed, but still not working ((