ricketts

#!/bin/bash

## Download the HG002 30X VCFs shared by google
gsutil cp gs://brain-genomics-public/research/sequencing/grch38/vcf/novaseq/wgs_pcr_free/30x/HG002.novaseq.pcr-free.30x.deepvariant-v1.0.grch38.vcf.gz .

## Split multi allelics using bcftools norm
## (Assumes bcftools is installed and in your PATH)
bcftools norm -m- -Oz --output HG002.novaseq.pcr-free.30x.deepvariant-v1.0.grch38.split.vcf.gz HG002.novaseq.pcr-free.30x.deepvariant-v1.0.grch38.vcf.gz

## Tabix index our VCF file