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: cnvpytor cluster resources #1083

Merged
merged 6 commits into from
Feb 3, 2023
Merged

fix: cnvpytor cluster resources #1083

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
c343eb2
changelog
khurrammaqbool Jan 18, 2023
e08b2ff
add bgzip
khurrammaqbool Jan 18, 2023
f2938e4
fix cnvpytor cluster resources
khurrammaqbool Feb 1, 2023
e0eefaf
changelog
khurrammaqbool Feb 1, 2023
a405154
Merge branch 'develop' into fix/cnvpytor_cluster_resources
khurrammaqbool Feb 3, 2023
2f7cdf6
changelog
khurrammaqbool Feb 3, 2023
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
2 changes: 1 addition & 1 deletion BALSAMIC/assets/scripts/edit_vcf_info.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ def edit_vcf_info(input_vcf, output_vcf, variant_caller):

new_vcf = Writer(output_vcf, vcf)

with gzip.open(output_vcf, "wb"):
with open(output_vcf, "wb"):
for variant in vcf:
variant.INFO["FOUND_IN"] = variant_caller + "|" + output_vcf
new_vcf.write_record(variant)
Expand Down
2 changes: 1 addition & 1 deletion BALSAMIC/config/cluster.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -248,7 +248,7 @@
"time": "12:00:00",
"n": 24
},
"cnvpytor_sv_tumor_normal": {
"cnvpytor_tumor_only": {
"time": "05:00:00",
"n": 24
},
Expand Down
8 changes: 4 additions & 4 deletions BALSAMIC/constants/reference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,23 +134,23 @@
"output_path": "genome",
},
"delly_mappability": {
"url": "https://raw.githubusercontent.com/Clinical-Genomics/reference-files/86aab2d10c5ffc009bc8c68ad077ab7283d8fe06/cancer/references/GRCh38.delly.blacklist.gz",
"url": "https://raw.githubusercontent.com/Clinical-Genomics/reference-files/ea051b864d18945980f0ded6b16a5d192bd736a5/cancer/references/GRCh38.delly.blacklist.gz",
"file_type": "text",
"gzip": False,
"genome_version": "hg38",
"output_file": "delly_mappability.gz",
"output_path": "genome",
},
"delly_mappability_gindex": {
"url": "https://raw.githubusercontent.com/Clinical-Genomics/reference-files/86aab2d10c5ffc009bc8c68ad077ab7283d8fe06/cancer/references/GRCh38.delly.blacklist.gz.gzi",
"url": "https://raw.githubusercontent.com/Clinical-Genomics/reference-files/ea051b864d18945980f0ded6b16a5d192bd736a5/cancer/references/GRCh38.delly.blacklist.gz.gzi",
"file_type": "text",
"gzip": False,
"genome_version": "hg38",
"output_file": "delly_mappability.gz.gzi",
"output_path": "genome",
},
"delly_mappability_findex": {
"url": "https://raw.githubusercontent.com/Clinical-Genomics/reference-files/86aab2d10c5ffc009bc8c68ad077ab7283d8fe06/cancer/references/GRCh38.delly.blacklist.gz.fai",
"url": "https://raw.githubusercontent.com/Clinical-Genomics/reference-files/ea051b864d18945980f0ded6b16a5d192bd736a5/cancer/references/GRCh38.delly.blacklist.gz.fai",
"file_type": "text",
"gzip": False,
"genome_version": "hg38",
Expand All @@ -166,7 +166,7 @@
"output_path": "genome",
},
"ascat_chryloci": {
"url": "https://raw.githubusercontent.com/Clinical-Genomics/reference-files/35465e2644f76f2d59427a9b379d34ecea71f259/cancer/references/hg38_Y.loci",
"url": "https://raw.githubusercontent.com/Clinical-Genomics/reference-files/ea051b864d18945980f0ded6b16a5d192bd736a5/cancer/references/hg38_Y.loci",
"file_type": "text",
"gzip": False,
"genome_version": "hg38",
Expand Down
56 changes: 32 additions & 24 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 @@ -31,20 +31,22 @@ rule bcftools_filter_vardict_research_tumor_normal:
bcftools view {input.vcf_snv_research} | \
bcftools filter --threads {threads} --include 'INFO/GNOMADAF_popmax <= {params.pop_freq[0]} || INFO/GNOMADAF_popmax == \".\"' --soft-filter '{params.pop_freq[1]}' --mode '+' | \
bcftools filter --threads {threads} --include 'INFO/SWEGENAF <= {params.swegen_freq[0]} || INFO/SWEGENAF == \".\"' --soft-filter '{params.swegen_freq[1]}' --mode '+' |\
bcftools view -f PASS -o {output.vcf_pass_vardict}.temp -O z;

tabix -p vcf -f {output.vcf_pass_vardict}.temp;
bcftools view -f PASS -o {output.vcf_pass_vardict}.temp1 -O z;

python {params.edit_vcf_script} \
--input_vcf {output.vcf_pass_vardict}.temp \
--output_vcf {output.vcf_pass_vardict} \
--input_vcf {output.vcf_pass_vardict}.temp1 \
--output_vcf {output.vcf_pass_vardict}.temp2 \
--variant_caller {params.variant_caller};

bgzip -@ {threads} -l 9 -c {output.vcf_pass_vardict}.temp2 > {output.vcf_pass_vardict}

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

bcftools +counts {output.vcf_pass_vardict} > {output.bcftools_counts_research};

rm {output.vcf_pass_vardict}.temp;
rm {output.vcf_pass_vardict}.temp1;

rm {output.vcf_pass_vardict}.temp2;
"""


Expand Down Expand Up @@ -107,20 +109,22 @@ rule bcftools_filter_TNscope_umi_research_tumor_normal:
bcftools view -f PASS,triallelic_site --threads {threads} {input.vcf_snv_research} | \
bcftools filter --threads {threads} --include 'INFO/GNOMADAF_popmax <= {params.pop_freq[0]} || INFO/GNOMADAF_popmax == \".\"' --soft-filter '{params.pop_freq[1]}' --mode '+' | \
bcftools filter --threads {threads} --include 'INFO/SWEGENAF <= {params.swegen_freq[0]} || INFO/SWEGENAF == \".\"' --soft-filter '{params.swegen_freq[1]}' --mode '+' |\
bcftools view --threads {threads} -f PASS,triallelic_site -o {output.vcf_pass_tnscope_umi}.temp -O z;

tabix -p vcf -f {output.vcf_pass_tnscope_umi}.temp;
bcftools view --threads {threads} -f PASS,triallelic_site -o {output.vcf_pass_tnscope_umi}.temp1 -O z;

python {params.edit_vcf_script} \
--input_vcf {output.vcf_pass_tnscope_umi}.temp \
--output_vcf {output.vcf_pass_tnscope_umi} \
--input_vcf {output.vcf_pass_tnscope_umi}.temp1 \
--output_vcf {output.vcf_pass_tnscope_umi}.temp2 \
--variant_caller {params.variant_caller};

bgzip -@ {threads} -l 9 -c {output.vcf_pass_tnscope_umi}.temp2 > {output.vcf_pass_tnscope_umi}

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

bcftools +counts {output.vcf_pass_tnscope_umi} > {output.bcftools_counts_research};

rm {output.vcf_pass_tnscope_umi}.temp;
rm {output.vcf_pass_tnscope_umi}.temp1;

rm {output.vcf_pass_tnscope_umi}.temp2;
"""


Expand Down Expand Up @@ -153,20 +157,22 @@ bcftools view {input.vcf_snv_clinical} | \
bcftools filter --threads {threads} --include 'INFO/GNOMADAF_popmax <= {params.pop_freq[0]} || INFO/GNOMADAF_popmax == \".\"' --soft-filter '{params.pop_freq[1]}' --mode '+' | \
bcftools filter --threads {threads} --include 'INFO/SWEGENAF <= {params.swegen_freq[0]} || INFO/SWEGENAF == \".\"' --soft-filter '{params.swegen_freq[1]}' --mode '+' |\
bcftools filter --threads {threads} --include 'INFO/Frq <= {params.loqusdb_clinical_freq[0]} || INFO/Frq == \".\"' --soft-filter '{params.loqusdb_clinical_freq[1]}' --mode '+' |\
bcftools view --threads {threads} -f PASS -o {output.vcf_pass_vardict}.temp -O z;

tabix -p vcf -f {output.vcf_pass_vardict}.temp;
bcftools view --threads {threads} -f PASS -o {output.vcf_pass_vardict}.temp1 -O z;

python {params.edit_vcf_script} \
--input_vcf {output.vcf_pass_vardict}.temp \
--output_vcf {output.vcf_pass_vardict} \
--input_vcf {output.vcf_pass_vardict}.temp1 \
--output_vcf {output.vcf_pass_vardict}.temp2 \
--variant_caller {params.variant_caller};

bgzip -@ {threads} -l 9 -c {output.vcf_pass_vardict}.temp2 > {output.vcf_pass_vardict}

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

bcftools +counts {output.vcf_pass_vardict} > {output.bcftools_counts_clinical};

rm {output.vcf_pass_vardict}.temp;
rm {output.vcf_pass_vardict}.temp1;

rm {output.vcf_pass_vardict}.temp2;
"""


Expand Down Expand Up @@ -199,18 +205,20 @@ bcftools view -f PASS,triallelic_site --threads {threads} {input.vcf_snv_clinic
bcftools filter --threads {threads} --include 'INFO/GNOMADAF_popmax <= {params.pop_freq[0]} || INFO/GNOMADAF_popmax == \".\"' --soft-filter '{params.pop_freq[1]}' --mode '+' | \
bcftools filter --threads {threads} --include 'INFO/SWEGENAF <= {params.swegen_freq[0]} || INFO/SWEGENAF == \".\"' --soft-filter '{params.swegen_freq[1]}' --mode '+' |\
bcftools filter --threads {threads} --include 'INFO/Frq <= {params.loqusdb_clinical_freq[0]} || INFO/Frq == \".\"' --soft-filter '{params.loqusdb_clinical_freq[1]}' --mode '+' |\
bcftools view --threads {threads} -f PASS,triallelic_site -o {output.vcf_pass_tnscope_umi}.temp -O z;

tabix -p vcf -f {output.vcf_pass_tnscope_umi}.temp;
bcftools view --threads {threads} -f PASS,triallelic_site -o {output.vcf_pass_tnscope_umi}.temp1 -O z;

python {params.edit_vcf_script} \
--input_vcf {output.vcf_pass_tnscope_umi}.temp \
--output_vcf {output.vcf_pass_tnscope_umi} \
--input_vcf {output.vcf_pass_tnscope_umi}.temp1 \
--output_vcf {output.vcf_pass_tnscope_umi}.temp2 \
--variant_caller {params.variant_caller};

bgzip -@ {threads} -l 9 -c {output.vcf_pass_tnscope_umi}.temp2 > {output.vcf_pass_tnscope_umi}

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

bcftools +counts {output.vcf_pass_tnscope_umi} > {output.bcftools_counts_clinical};

rm {output.vcf_pass_tnscope_umi}.temp;
rm {output.vcf_pass_tnscope_umi}.temp1;

rm {output.vcf_pass_tnscope_umi}.temp2;
"""
56 changes: 32 additions & 24 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 @@ -31,20 +31,22 @@ rule bcftools_filter_vardict_research_tumor_only:
bcftools view {input.vcf_snv_research} | \
bcftools filter --threads {threads} --include 'INFO/GNOMADAF_popmax <= {params.pop_freq[0]} || INFO/GNOMADAF_popmax == \".\"' --soft-filter '{params.pop_freq[1]}' --mode '+' | \
bcftools filter --threads {threads} --include 'INFO/SWEGENAF <= {params.swegen_freq[0]} || INFO/SWEGENAF == \".\"' --soft-filter '{params.swegen_freq[1]}' --mode '+' |\
bcftools view --threads {threads} -f PASS -o {output.vcf_pass_vardict}.temp -O z;

tabix -p vcf -f {output.vcf_pass_vardict}.temp;
bcftools view --threads {threads} -f PASS -o {output.vcf_pass_vardict}.temp1 -O z;

python {params.edit_vcf_script} \
--input_vcf {output.vcf_pass_vardict}.temp \
--output_vcf {output.vcf_pass_vardict} \
--input_vcf {output.vcf_pass_vardict}.temp1 \
--output_vcf {output.vcf_pass_vardict}.temp2 \
--variant_caller {params.variant_caller};

bgzip -@ {threads} -l 9 -c {output.vcf_pass_vardict}.temp2 > {output.vcf_pass_vardict}

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

bcftools +counts {output.vcf_pass_vardict} > {output.bcftools_counts_research};

rm {output.vcf_pass_vardict}.temp;
rm {output.vcf_pass_vardict}.temp1;

rm {output.vcf_pass_vardict}.temp2;
"""


Expand Down Expand Up @@ -107,20 +109,22 @@ rule bcftools_filter_TNscope_umi_research_tumor_only:
bcftools view {input.vcf_snv_research} | \
bcftools filter --include 'INFO/GNOMADAF_popmax <= {params.pop_freq[0]} || INFO/GNOMADAF_popmax == \".\"' --soft-filter '{params.pop_freq[1]}' --mode '+' | \
bcftools filter --threads {threads} --include 'INFO/SWEGENAF <= {params.swegen_freq[0]} || INFO/SWEGENAF == \".\"' --soft-filter '{params.swegen_freq[1]}' --mode '+' |\
bcftools view --threads {threads} -f PASS,triallelic_site -o {output.vcf_pass_tnscope_umi}.temp -O z;

tabix -p vcf -f {output.vcf_pass_tnscope_umi}.temp;
bcftools view --threads {threads} -f PASS,triallelic_site -o {output.vcf_pass_tnscope_umi}.temp1 -O z;

python {params.edit_vcf_script} \
--input_vcf {output.vcf_pass_tnscope_umi}.temp \
--output_vcf {output.vcf_pass_tnscope_umi} \
--input_vcf {output.vcf_pass_tnscope_umi}.temp1 \
--output_vcf {output.vcf_pass_tnscope_umi}.temp2 \
--variant_caller {params.variant_caller};

bgzip -@ {threads} -l 9 -c {output.vcf_pass_tnscope_umi}.temp2 > {output.vcf_pass_tnscope_umi}

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

bcftools +counts {output.vcf_pass_tnscope_umi} > {output.bcftools_counts_research};

rm {output.vcf_pass_tnscope_umi}.temp;
rm {output.vcf_pass_tnscope_umi}.temp1;

rm {output.vcf_pass_tnscope_umi}.temp2;
"""


Expand Down Expand Up @@ -153,20 +157,22 @@ bcftools view {input.vcf_snv_clinical} | \
bcftools filter --include 'INFO/GNOMADAF_popmax <= {params.pop_freq[0]} || INFO/GNOMADAF_popmax == \".\"' --soft-filter '{params.pop_freq[1]}' --mode '+' | \
bcftools filter --threads {threads} --include 'INFO/SWEGENAF <= {params.swegen_freq[0]} || INFO/SWEGENAF == \".\"' --soft-filter '{params.swegen_freq[1]}' --mode '+' |\
bcftools filter --threads {threads} --include 'INFO/Frq <= {params.loqusdb_clinical_freq[0]} || INFO/Frq == \".\"' --soft-filter '{params.loqusdb_clinical_freq[1]}' --mode '+' |\
bcftools view --threads {threads} -f PASS -o {output.vcf_pass_vardict}.temp -O z;

tabix -p vcf -f {output.vcf_pass_vardict}.temp;
bcftools view --threads {threads} -f PASS -o {output.vcf_pass_vardict}.temp1 -O z;

python {params.edit_vcf_script} \
--input_vcf {output.vcf_pass_vardict}.temp \
--output_vcf {output.vcf_pass_vardict} \
--input_vcf {output.vcf_pass_vardict}.temp1 \
--output_vcf {output.vcf_pass_vardict}.temp2 \
--variant_caller {params.variant_caller};

bgzip -@ {threads} -l 9 -c {output.vcf_pass_vardict}.temp2 > {output.vcf_pass_vardict}

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

bcftools +counts {output.vcf_pass_vardict} > {output.bcftools_counts_clinical};

rm {output.vcf_pass_vardict}.temp;
rm {output.vcf_pass_vardict}.temp1;

rm {output.vcf_pass_vardict}.temp2;
"""


Expand Down Expand Up @@ -199,18 +205,20 @@ bcftools view {input.vcf_snv_clinical} | \
bcftools filter --include 'INFO/GNOMADAF_popmax <= {params.pop_freq[0]} || INFO/GNOMADAF_popmax == \".\"' --soft-filter '{params.pop_freq[1]}' --mode '+' | \
bcftools filter --threads {threads} --include 'INFO/SWEGENAF <= {params.swegen_freq[0]} || INFO/SWEGENAF == \".\"' --soft-filter '{params.swegen_freq[1]}' --mode '+' |\
bcftools filter --threads {threads} --include 'INFO/Frq <= {params.loqusdb_clinical_freq[0]} || INFO/Frq == \".\"' --soft-filter '{params.loqusdb_clinical_freq[1]}' --mode '+' |\
bcftools view --threads {threads} -f PASS,triallelic_site -o {output.vcf_pass_tnscope_umi}.temp -O z;

tabix -p vcf -f {output.vcf_pass_tnscope_umi}.temp;
bcftools view --threads {threads} -f PASS,triallelic_site -o {output.vcf_pass_tnscope_umi}.temp1 -O z;

python {params.edit_vcf_script} \
--input_vcf {output.vcf_pass_tnscope_umi}.temp \
--output_vcf {output.vcf_pass_tnscope_umi} \
--input_vcf {output.vcf_pass_tnscope_umi}.temp1 \
--output_vcf {output.vcf_pass_tnscope_umi}.temp2 \
--variant_caller {params.variant_caller};

bgzip -@ {threads} -l 9 -c {output.vcf_pass_tnscope_umi}.temp2 > {output.vcf_pass_tnscope_umi}

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

bcftools +counts {output.vcf_pass_tnscope_umi} > {output.bcftools_counts_clinical};

rm {output.vcf_pass_tnscope_umi}.temp;
rm {output.vcf_pass_tnscope_umi}.temp1;

rm {output.vcf_pass_tnscope_umi}.temp2;
"""
3 changes: 1 addition & 2 deletions BALSAMIC/snakemake_rules/variant_calling/somatic_sv_tumor_only.rule
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -185,11 +185,10 @@ echo -e \"{params.tumor}\\tTUMOR\" > {output.namemap};
rm -rf {params.tmpdir};
"""

rule cnvpytor_cnv_tumor_only:
rule cnvpytor_tumor_only:
input:
bamT = bam_dir + tumor_bam,
vcfT = vcf_dir + "SNV.somatic." + config["analysis"]["case_id"] + ".tnscope.vcf.gz",
map = config["reference"]["delly_mappability"],
output:
cnv_cnvpytor = vcf_dir + "CNV.somatic." + config["analysis"]["case_id"] + ".cnvpytor.vcf.gz",
circular_cnvpytor = vcf_dir + "CNV.somatic." + config["analysis"]["case_id"] + ".cnvpytor.circular.png",
Expand Down
12 changes: 11 additions & 1 deletion CHANGELOG.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,13 @@
[X.X.X]

Fixed:
^^^^^^
* Reference files for hg38 https://github.com/Clinical-Genomics/BALSAMMIC/pull/1081

Added:
^^^^^^
* Cluster resources for CNVPytor tumor only https://github.com/Clinical-Genomics/BALSAMIC/pull/1083
khurrammaqbool marked this conversation as resolved.
Show resolved Hide resolved

[11.1.0]
--------

Expand Down Expand Up @@ -25,7 +35,7 @@ Changed:

Fixed:
^^^^^^
* MacDepth in quality filter for SV https://github.com/Clinical-Genomics/BALSAMIC/pull/1051
* MaxDepth in quality filter for SV https://github.com/Clinical-Genomics/BALSAMIC/pull/1051

[11.0.1]
--------
Expand Down