Commit 36e4a0ef authored by Kevin Kunzmann's avatar Kevin Kunzmann

bugfix

parent ba722fac
...@@ -16,6 +16,7 @@ Nat Genet. doi:10.1038/ng.3367. ...@@ -16,6 +16,7 @@ Nat Genet. doi:10.1038/ng.3367.
2. `wget` (pre-installed or via distribution package manager) 2. `wget` (pre-installed or via distribution package manager)
3. `singularity` container software (tested on 3.3.0, https://sylabs.io/guides/3.3/user-guide) 3. `singularity` container software (tested on 3.3.0, https://sylabs.io/guides/3.3/user-guide)
4. `git` (https://git-scm.com/book/en/v2/Getting-Started-Installing-Git) 4. `git` (https://git-scm.com/book/en/v2/Getting-Started-Installing-Git)
5. for data download fimm GCP bucket access to `fimm-horizon-outgoing-data/CENTER_TBI_data_freeze_190829/Imputed_data`
### Optional ### Optional
...@@ -39,6 +40,15 @@ Download the container image ...@@ -39,6 +40,15 @@ Download the container image
bash scripts/download_container.sh bash scripts/download_container.sh
Obtain the imputed genomes (GCP bucket: fimm-horizon-outgoing-data/CENTER_TBI_data_freeze_190829/Imputed_data).
`gsutils` is pre-installed in the container image, to authenticate with your
GCP account run and follow the interactive instructions
singularity shell container.sif
gcloud auth login
snakemake download_imputed_genotypes
exit
Execute the workflow inside the container on a single core (takes a while!) Execute the workflow inside the container on a single core (takes a while!)
singularity exec container.sif snakemake impute singularity exec container.sif snakemake impute
......
...@@ -70,7 +70,7 @@ rule vcf_to_dosages: ...@@ -70,7 +70,7 @@ rule vcf_to_dosages:
export prefix={wildcards.output_dir}/dosages export prefix={wildcards.output_dir}/dosages
mkdir -p $prefix mkdir -p $prefix
echo "extracting and computing MAFs ..." echo "extracting and computing MAFs ..."
bcftools +fill-tags {inputs.vcf_gz_file} > $prefix/chr{wildcards.i}.vcf bcftools +fill-tags {input.vcf_gz_file} > $prefix/chr{wildcards.i}.vcf
echo 'querying dosages ...' echo 'querying dosages ...'
bcftools query -e 'MAF[0]>{config[min_MAF]} | INFO>{config[min_INFO]} | TYPE!="snp" | N_ALT!=1' -f '%CHROM %ID %POS %REF %ALT %INFO/MAF [%DS ]\n' $prefix/chr{wildcards.i}.vcf > $prefix/chr{wildcards.i}.dosage.txt bcftools query -e 'MAF[0]>{config[min_MAF]} | INFO>{config[min_INFO]} | TYPE!="snp" | N_ALT!=1' -f '%CHROM %ID %POS %REF %ALT %INFO/MAF [%DS ]\n' $prefix/chr{wildcards.i}.vcf > $prefix/chr{wildcards.i}.dosage.txt
echo 'compressing ...' echo 'compressing ...'
...@@ -94,7 +94,7 @@ rule generate_samples_file: ...@@ -94,7 +94,7 @@ rule generate_samples_file:
""" """
export prefix={wildcards.output_dir}/dosages export prefix={wildcards.output_dir}/dosages
mkdir -p $prefix mkdir -p $prefix
bcftools query -l {inputs.vcf_gz_file} >> $prefix/samples_.txt bcftools query -l {input.vcf_gz_file} >> $prefix/samples_.txt
# family ID = individual ID # family ID = individual ID
awk {params.format} < $prefix/samples_.txt > $prefix/samples.txt awk {params.format} < $prefix/samples_.txt > $prefix/samples.txt
rm $prefix/samples_.txt rm $prefix/samples_.txt
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment