Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: remove stat files and add count files for scout upload VCFs #899

Merged
merged 12 commits into from
Apr 13, 2022
Merged

fix: remove stat files and add count files for scout upload VCFs #899

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
6f58f68
update changelog
khurrammaqbool Mar 28, 2022
2b36ab9
update changelog
khurrammaqbool Mar 28, 2022
6866c48
remove bcftools_stats
khurrammaqbool Mar 28, 2022
e5e064e
add bcftools_stats
khurrammaqbool Mar 28, 2022
7809183
update changelog
khurrammaqbool Apr 4, 2022
0246abf
add bcftools +counts to end point VCFs
khurrammaqbool Apr 4, 2022
164e3ae
update black linter
khurrammaqbool Apr 4, 2022
4e78682
Merge branch 'develop' into fix/stat_files
khurrammaqbool Apr 11, 2022
f85eabe
remove bcftools counts for VCFs not to be uploaded to scout
khurrammaqbool Apr 11, 2022
fcaf654
remove bcftools counts for VCFs not to be uploaded to scout
khurrammaqbool Apr 11, 2022
6d10c55
Merge branch 'develop' into fix/stat_files
khurrammaqbool Apr 12, 2022
6bb9976
update changelog
khurrammaqbool Apr 13, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 16 additions & 9 deletions BALSAMIC/snakemake_rules/annotation/varcaller_filter_tumor_normal.rule
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,8 @@ rule bcftools_filter_vardict_tumor_normal:
vcf = vep_dir + "{var_type}.somatic.{case_name}.vardict.all.vcf.gz",
output:
vcf_filtered = vep_dir + "{var_type}.somatic.{case_name}.vardict.all.filtered.vcf.gz",
vcf_pass = vep_dir + "{var_type}.somatic.{case_name}.vardict.all.filtered.pass.vcf.gz",
vcf_pass_vardict = vep_dir + "{var_type}.somatic.{case_name}.vardict.all.filtered.pass.vcf.gz",
bcftools_counts = vep_dir + "{var_type}.somatic.{case_name}.vardict.all.filtered.pass.stats"
benchmark:
Path(benchmark_dir, 'bcftools_filter_vardict_tumor_normal_' + "{var_type}.somatic.{case_name}.tsv").as_posix()
singularity:
Expand Down Expand Up @@ -42,9 +43,11 @@ bcftools view {input.vcf} \

tabix -p vcf -f {output.vcf_filtered};

bcftools view -f PASS -o {output.vcf_pass} -O z {output.vcf_filtered};
bcftools view -f PASS -o {output.vcf_pass_vardict} -O z {output.vcf_filtered};

tabix -p vcf -f {output.vcf_pass};
tabix -p vcf -f {output.vcf_pass_vardict};

bcftools +counts {output.vcf_pass_vardict} > {output.bcftools_counts};
"""


Expand All @@ -53,7 +56,7 @@ rule bcftools_filter_tnhaplotyper_tumor_normal:
vcf = vep_dir + "{var_type}.somatic.{case_name}.tnhaplotyper.all.vcf.gz",
output:
vcf_filtered = vep_dir + "{var_type}.somatic.{case_name}.tnhaplotyper.all.filtered.vcf.gz",
vcf_pass = vep_dir + "{var_type}.somatic.{case_name}.tnhaplotyper.all.filtered.pass.vcf.gz",
vcf_pass_tnhaplotyper = vep_dir + "{var_type}.somatic.{case_name}.tnhaplotyper.all.filtered.pass.vcf.gz",
benchmark:
Path(benchmark_dir, 'bcftools_filter_tnhaplotyper_tumor_normal' + "{var_type}.somatic.{case_name}.tsv").as_posix()
singularity:
Expand All @@ -74,9 +77,10 @@ bcftools view {input.vcf} \

tabix -p vcf -f {output.vcf_filtered};

bcftools view -f PASS -o {output.vcf_pass} -O z {output.vcf_filtered};
bcftools view -f PASS -o {output.vcf_pass_tnhaplotyper} -O z {output.vcf_filtered};

tabix -p vcf -f {output.vcf_pass_tnhaplotyper};

tabix -p vcf -f {output.vcf_pass};
"""


Expand All @@ -85,7 +89,8 @@ rule bcftools_filter_TNscope_umi_tumor_normal:
vcf = vep_dir + "{var_type}.somatic.{case_name}.TNscope_umi.all.vcf.gz",
output:
vcf_filtered = vep_dir + "{var_type}.somatic.{case_name}.TNscope_umi.all.filtered.vcf.gz",
vcf_pass = vep_dir + "{var_type}.somatic.{case_name}.TNscope_umi.all.filtered.pass.vcf.gz",
vcf_pass_TNscope_umi = vep_dir + "{var_type}.somatic.{case_name}.TNscope_umi.all.filtered.pass.vcf.gz",
bcftools_counts = vep_dir + "{var_type}.somatic.{case_name}.TNscope_umi.all.filtered.pass.stats"
benchmark:
Path(benchmark_dir, 'bcftools_filter_TNscope_umi_tumor_normal' + "{var_type}.somatic.{case_name}.tsv").as_posix()
singularity:
Expand All @@ -106,7 +111,9 @@ bcftools view {input.vcf} \

tabix -p vcf -f {output.vcf_filtered};

bcftools view -f PASS -o {output.vcf_pass} -O z {output.vcf_filtered};
bcftools view -f PASS -o {output.vcf_pass_TNscope_umi} -O z {output.vcf_filtered};

tabix -p vcf -f {output.vcf_pass_TNscope_umi};

tabix -p vcf -f {output.vcf_pass};
bcftools +counts {output.vcf_pass_TNscope_umi} > {output.bcftools_counts};
"""
25 changes: 16 additions & 9 deletions BALSAMIC/snakemake_rules/annotation/varcaller_filter_tumor_only.rule
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,8 @@ rule bcftools_filter_vardict_tumor_only:
vcf = vep_dir + "{var_type}.somatic.{case_name}.vardict.all.vcf.gz",
output:
vcf_filtered = vep_dir + "{var_type}.somatic.{case_name}.vardict.all.filtered.vcf.gz",
vcf_pass = vep_dir + "{var_type}.somatic.{case_name}.vardict.all.filtered.pass.vcf.gz",
vcf_pass_vardict = vep_dir + "{var_type}.somatic.{case_name}.vardict.all.filtered.pass.vcf.gz",
bcftools_counts = vep_dir + "{var_type}.somatic.{case_name}.vardict.all.filtered.pass.stats"
benchmark:
Path(benchmark_dir, 'bcftools_filter_vardict_tumor_only_' + "{var_type}.somatic.{case_name}.tsv").as_posix()
singularity:
Expand Down Expand Up @@ -40,9 +41,11 @@ bcftools view {input.vcf} \

tabix -p vcf -f {output.vcf_filtered};

bcftools view -f PASS -o {output.vcf_pass} -O z {output.vcf_filtered};
bcftools view -f PASS -o {output.vcf_pass_vardict} -O z {output.vcf_filtered};

tabix -p vcf -f {output.vcf_pass};
tabix -p vcf -f {output.vcf_pass_vardict};

bcftools +counts {output.vcf_pass_vardict} > {output.bcftools_counts};
"""


Expand All @@ -51,7 +54,7 @@ rule bcftools_filter_tnhaplotyper_tumor_only:
vcf = vep_dir + "{var_type}.somatic.{case_name}.tnhaplotyper.all.vcf.gz",
output:
vcf_filtered = vep_dir + "{var_type}.somatic.{case_name}.tnhaplotyper.all.filtered.vcf.gz",
vcf_pass = vep_dir + "{var_type}.somatic.{case_name}.tnhaplotyper.all.filtered.pass.vcf.gz",
vcf_pass_tnhaplotyper = vep_dir + "{var_type}.somatic.{case_name}.tnhaplotyper.all.filtered.pass.vcf.gz",
benchmark:
Path(benchmark_dir, 'bcftools_filter_tnhaplotyper_tumor_only' + "{var_type}.somatic.{case_name}.tsv").as_posix()
singularity:
Expand All @@ -72,9 +75,10 @@ bcftools view {input.vcf} \

tabix -p vcf -f {output.vcf_filtered};

bcftools view -f PASS -o {output.vcf_pass} -O z {output.vcf_filtered};
bcftools view -f PASS -o {output.vcf_pass_tnhaplotyper} -O z {output.vcf_filtered};

tabix -p vcf -f {output.vcf_pass_tnhaplotyper};

tabix -p vcf -f {output.vcf_pass};
"""


Expand All @@ -83,7 +87,8 @@ rule bcftools_filter_TNscope_umi_tumor_only:
vcf = vep_dir + "{var_type}.somatic.{case_name}.TNscope_umi.all.vcf.gz",
output:
vcf_filtered = vep_dir + "{var_type}.somatic.{case_name}.TNscope_umi.all.filtered.vcf.gz",
vcf_pass = vep_dir + "{var_type}.somatic.{case_name}.TNscope_umi.all.filtered.pass.vcf.gz",
vcf_pass_TNscope_umi = vep_dir + "{var_type}.somatic.{case_name}.TNscope_umi.all.filtered.pass.vcf.gz",
bcftools_counts = vep_dir + "{var_type}.somatic.{case_name}.TNscope_umi.all.filtered.pass.stats"
benchmark:
Path(benchmark_dir, 'bcftools_filter_TNscope_umi_tumor_only' + "{var_type}.somatic.{case_name}.tsv").as_posix()
singularity:
Expand All @@ -104,7 +109,9 @@ bcftools view {input.vcf} \

tabix -p vcf -f {output.vcf_filtered};

bcftools view -f PASS -o {output.vcf_pass} -O z {output.vcf_filtered};
bcftools view -f PASS -o {output.vcf_pass_TNscope_umi} -O z {output.vcf_filtered};

tabix -p vcf -f {output.vcf_pass_TNscope_umi};

tabix -p vcf -f {output.vcf_pass};
bcftools +counts {output.vcf_pass_TNscope_umi} > {output.bcftools_counts};
"""
9 changes: 6 additions & 3 deletions BALSAMIC/snakemake_rules/annotation/varcaller_sv_filter.rule
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,8 @@ rule bcftools_filter_svdb:
input:
vcf = vep_dir + "SV.somatic.{case_name}.svdb.all.vcf.gz",
output:
vcf_sv_pass_svdb = vep_dir + "SV.somatic.{case_name}.svdb.all.filtered.pass.vcf.gz",
vcf_pass_svdb = vep_dir + "SV.somatic.{case_name}.svdb.all.filtered.pass.vcf.gz",
bcftools_counts = vep_dir + "SV.somatic.{case_name}.svdb.all.filtered.pass.stats"
benchmark:
benchmark_dir + "bcftools_filter_svdb_SV.somatic.{case_name}.svdb.vep.tsv"
singularity:
Expand All @@ -20,7 +21,9 @@ rule bcftools_filter_svdb:
"Filtering svdb merged Manta and Delly results for PASS variants using bcftools for sample '{params.case_name}' "
shell:
"""
bcftools view --threads {threads} -f .,PASS -o {output.vcf_sv_pass_svdb} -O z {input.vcf};
bcftools view --threads {threads} -f .,PASS -o {output.vcf_pass_svdb} -O z {input.vcf};

tabix -p vcf -f {output.vcf_sv_pass_svdb};
tabix -p vcf -f {output.vcf_pass_svdb};

bcftools +counts {output.vcf_pass_svdb} > {output.bcftools_counts};
"""
16 changes: 10 additions & 6 deletions BALSAMIC/snakemake_rules/annotation/varcaller_wgs_filter_tumor_normal.rule
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,8 @@ rule bcftools_filter_tnscope_tumor_normal:
vcf = vep_dir + "{var_type}.somatic.{case_name}.tnscope.all.vcf.gz",
output:
vcf_filtered = vep_dir + "{var_type}.somatic.{case_name}.tnscope.all.filtered.vcf.gz",
vcf_pass = vep_dir + "{var_type}.somatic.{case_name}.tnscope.all.filtered.pass.vcf.gz",
vcf_pass_tnscope = vep_dir + "{var_type}.somatic.{case_name}.tnscope.all.filtered.pass.vcf.gz",
bcftools_counts = vep_dir + "{var_type}.somatic.{case_name}.tnscope.all.filtered.pass.stats"
benchmark:
Path(benchmark_dir, 'bcftools_filter_tnscope_tumor_normal_' + "{var_type}.somatic.{case_name}.tsv").as_posix()
singularity:
Expand Down Expand Up @@ -38,9 +39,11 @@ bcftools view {input.vcf} \

tabix -p vcf -f {output.vcf_filtered};

bcftools view -f PASS -o {output.vcf_pass} -O z {output.vcf_filtered};
bcftools view -f PASS -o {output.vcf_pass_tnscope} -O z {output.vcf_filtered};

tabix -p vcf -f {output.vcf_pass};
tabix -p vcf -f {output.vcf_pass_tnscope};

bcftools +counts {output.vcf_pass_tnscope} > {output.bcftools_counts};
"""


Expand All @@ -50,7 +53,7 @@ rule bcftools_filter_tnhaplotyper_tumor_normal:
wgs_calling_file = config["reference"]["wgs_calling_interval"]
output:
vcf_filtered = vep_dir + "{var_type}.somatic.{case_name}.tnhaplotyper.all.filtered.vcf.gz",
vcf_pass = vep_dir + "{var_type}.somatic.{case_name}.tnhaplotyper.all.filtered.pass.vcf.gz",
vcf_pass_tnhaplotyper = vep_dir + "{var_type}.somatic.{case_name}.tnhaplotyper.all.filtered.pass.vcf.gz",
benchmark:
Path(benchmark_dir, 'bcftools_filter_tnhaplotyper_tumor_normal_' + "{var_type}.somatic.{case_name}.tsv").as_posix()
singularity:
Expand All @@ -73,7 +76,8 @@ bcftools view -f PASS --threads {threads} --regions-file {input.wgs_calling_file

tabix -p vcf -f {output.vcf_filtered};

bcftools view -f PASS --threads {threads} -O z -o {output.vcf_pass} {output.vcf_filtered}
bcftools view -f PASS --threads {threads} -O z -o {output.vcf_pass_tnhaplotyper} {output.vcf_filtered}

tabix -p vcf -f {output.vcf_pass_tnhaplotyper}

tabix -p vcf -f {output.vcf_pass}
"""
16 changes: 10 additions & 6 deletions BALSAMIC/snakemake_rules/annotation/varcaller_wgs_filter_tumor_only.rule
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,7 @@ rule bcftools_filter_tnhaplotyper_tumor_only:
wgs_calling_file = config["reference"]["wgs_calling_interval"]
output:
vcf_filtered = vep_dir + "{var_type}.somatic.{case_name}.tnhaplotyper.all.filtered.vcf.gz",
vcf_pass = vep_dir + "{var_type}.somatic.{case_name}.tnhaplotyper.all.filtered.pass.vcf.gz",
vcf_pass_tnhaplotyper = vep_dir + "{var_type}.somatic.{case_name}.tnhaplotyper.all.filtered.pass.vcf.gz",
benchmark:
Path(benchmark_dir, 'bcftools_filter_tnhaplotyper_tumor_only_' + "{var_type}.somatic.{case_name}.tsv").as_posix()
singularity:
Expand Down Expand Up @@ -89,9 +89,10 @@ bcftools view -f PASS --threads {threads} --regions-file {input.wgs_calling_file

tabix -p vcf -f {output.vcf_filtered};

bcftools view -f PASS --threads {threads} -O z -o {output.vcf_pass} {output.vcf_filtered}
bcftools view -f PASS --threads {threads} -O z -o {output.vcf_pass_tnhaplotyper} {output.vcf_filtered}

tabix -p vcf -f {output.vcf_pass_tnhaplotyper}

tabix -p vcf -f {output.vcf_pass}
"""


Expand All @@ -101,7 +102,8 @@ rule bcftools_intersect_tumor_only:
tnhaplotyper = vep_dir + "{var_type}.somatic.{case_name}.tnhaplotyper.all.filtered.vcf.gz"
output:
vcf_filtered = vep_dir + "{var_type}.somatic.{case_name}.tnscope.all.filtered.vcf.gz",
vcf_pass = vep_dir + "{var_type}.somatic.{case_name}.tnscope.all.filtered.pass.vcf.gz",
vcf_pass_tnscope = vep_dir + "{var_type}.somatic.{case_name}.tnscope.all.filtered.pass.vcf.gz",
bcftools_counts = vep_dir + "{var_type}.somatic.{case_name}.tnscope.all.filtered.pass.stats"
benchmark:
Path(benchmark_dir, 'bcftools_intersect_tumor_only_' + "{var_type}.somatic.{case_name}.tsv").as_posix()
singularity:
Expand All @@ -122,9 +124,11 @@ cp {params.vcf_dir}/0002.vcf.gz {output.vcf_filtered};

tabix -p vcf -f {output.vcf_filtered};

bcftools view -f PASS -o {output.vcf_pass} -O z {output.vcf_filtered};
bcftools view -f PASS -o {output.vcf_pass_tnscope} -O z {output.vcf_filtered};

tabix -p vcf -f {output.vcf_pass_tnscope};

tabix -p vcf -f {output.vcf_pass};
bcftools +counts {output.vcf_pass_tnscope} > {output.bcftools_counts};

rm -r {params.vcf_dir}
"""
12 changes: 0 additions & 12 deletions BALSAMIC/snakemake_rules/annotation/vep.rule
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,8 +10,6 @@ rule vep_somatic_snv:
cosmic = config["reference"]["cosmic"]
output:
vcf_all = temp(vep_dir + "SNV.somatic.{case_name}.{var_caller}.all.vcf.gz"),
vcf_summary = vep_dir + "SNV.somatic.{case_name}.{var_caller}.all.vcf.gz_summary.html",
bcftools_stats = vep_dir + "SNV.somatic.{case_name}.{var_caller}.all.stats"
benchmark:
Path(benchmark_dir, "vep_somatic_SNV.somatic.{case_name}.{var_caller}.tsv").as_posix()
singularity:
Expand Down Expand Up @@ -50,8 +48,6 @@ vep \

tabix -p vcf -f {output.vcf_all};

bcftools stats {output.vcf_all} > {output.bcftools_stats};

rm $tmpvcf;
"""

Expand All @@ -61,8 +57,6 @@ rule vep_somatic_sv:
header = vcf_dir + "SV.somatic.{case_name}.svdb.sample_name_map",
output:
vcf_all = temp(vep_dir + "SV.somatic.{case_name}.svdb.all.vcf.gz"),
vcf_summary = vep_dir + "SV.somatic.{case_name}.svdb.all.vcf.gz_summary.html",
bcftools_stats = vep_dir + "SV.somatic.{case_name}.svdb.all.stats"
benchmark:
Path(benchmark_dir, "vep_somatic_SV.somatic.{case_name}.svdb.tsv").as_posix()
singularity:
Expand Down Expand Up @@ -92,9 +86,6 @@ vep \
{params.vep_defaults} \

tabix -p vcf -f {output.vcf_all};

bcftools stats {output.vcf_all} > {output.bcftools_stats};

"""

rule tmb_calculation:
Expand Down Expand Up @@ -160,8 +151,6 @@ rule vep_germline:
cosmic = config["reference"]["cosmic"]
output:
vcf_all = vep_dir + "{var_type}.germline.{sample}.{var_caller}.vcf.gz",
vcf_summary = vep_dir + "{var_type}.germline.{sample}.{var_caller}.vcf.gz_summary.html",
bcftools_stats = vep_dir + "{var_type}.germline.{sample}.{var_caller}.all.stats"
benchmark:
Path(benchmark_dir, "vep_germline_{var_type}.germline.{sample}.{var_caller}.tsv").as_posix()
singularity:
Expand Down Expand Up @@ -192,5 +181,4 @@ vep \

tabix -p vcf -f {output.vcf_all};

bcftools stats {output.vcf_all} > {output.bcftools_stats};
"""
2 changes: 2 additions & 0 deletions CHANGELOG.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@ Added:
* Snakemake rule for creating `.cgh` files from `CNVkit` outputs #858
* SVdb to TGA workflow #871
* SVdb merge SV and CNV #871
* bcftools counts to varcall filter rules #898
* Additional WGS metrics to be stored in ``<case>_metrics_deliverables.yaml`` #907

Changed:
Expand All @@ -39,6 +40,7 @@ Removed
* vcfanno from SV annotation
* Removed `MSK_impact` and `MSK_impact_noStrelka` json files from config
* Cleanup of `strelka`, `pindel` , `mutect2` variables from BALSAMIC
* bcftools_stats from vep #898

[8.2.10]
--------
Expand Down