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.

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

Modules/slms 3/1.0 #167

Merged
merged 3 commits into from
Jan 18, 2021
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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: 2 additions & 0 deletions modules/manta/2.0/config/default.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,8 @@ lcr-modules:
# Available wildcards: {seq_type} {genome_build} {sample_id}
sample_bam: null # UPDATE
sample_bai: null # UPDATE

scripts:
augment_manta_vcf: "{SCRIPTSDIR}/augment_manta_vcf/1.0/augment_manta_vcf.py"

options:
Expand Down
8 changes: 4 additions & 4 deletions modules/manta/2.0/manta.smk
Original file line number Diff line number Diff line change
Expand Up @@ -150,15 +150,15 @@ rule _manta_run:
# and fixes the sample IDs in the VCF header to match sample IDs used in Snakemake
rule _manta_augment_vcf:
input:
variants_dir = rules._manta_run.output.variants_dir,
aug_vcf = CFG["inputs"]["augment_manta_vcf"]
variants_dir = rules._manta_run.output.variants_dir
output:
vcf = CFG["dirs"]["augment_vcf"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/{vcf_name}.augmented.vcf"
log:
stdout = CFG["logs"]["augment_vcf"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/manta_augment_vcf.{vcf_name}.stdout.log",
stderr = CFG["logs"]["augment_vcf"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/manta_augment_vcf.{vcf_name}.stderr.log"
params:
opts = CFG["options"]["augment_vcf"]
opts = CFG["options"]["augment_vcf"],
aug_vcf = CFG["scripts"]["augment_manta_vcf"]
conda:
CFG["conda_envs"]["augment_manta_vcf"]
threads:
Expand All @@ -167,7 +167,7 @@ rule _manta_augment_vcf:
mem_mb = CFG["mem_mb"]["augment_vcf"]
shell:
op.as_one_line("""
{input.aug_vcf} {params.opts} --tumour_id {wildcards.tumour_id} --normal_id {wildcards.normal_id}
{params.aug_vcf} {params.opts} --tumour_id {wildcards.tumour_id} --normal_id {wildcards.normal_id}
--vcf_type {wildcards.vcf_name} {input.variants_dir}/{wildcards.vcf_name}.vcf.gz {output.vcf}
> {log.stdout} 2> {log.stderr}
""")
Expand Down
2 changes: 2 additions & 0 deletions modules/manta/2.1/config/default.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,8 @@ lcr-modules:
# Available wildcards: {seq_type} {genome_build} {sample_id}
sample_bam: "__UPDATE__"
sample_bai: "__UPDATE__"

scripts:
augment_manta_vcf: "{SCRIPTSDIR}/augment_manta_vcf/1.0/augment_manta_vcf.py"

options:
Expand Down
8 changes: 4 additions & 4 deletions modules/manta/2.1/manta.smk
Original file line number Diff line number Diff line change
Expand Up @@ -150,15 +150,15 @@ rule _manta_run:
# and fixes the sample IDs in the VCF header to match sample IDs used in Snakemake
rule _manta_augment_vcf:
input:
variants_dir = rules._manta_run.output.variants_dir,
aug_vcf = CFG["inputs"]["augment_manta_vcf"]
variants_dir = rules._manta_run.output.variants_dir
output:
vcf = CFG["dirs"]["augment_vcf"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/{vcf_name}.augmented.vcf"
log:
stdout = CFG["logs"]["augment_vcf"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/manta_augment_vcf.{vcf_name}.stdout.log",
stderr = CFG["logs"]["augment_vcf"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/manta_augment_vcf.{vcf_name}.stderr.log"
params:
opts = CFG["options"]["augment_vcf"]
opts = CFG["options"]["augment_vcf"],
aug_vcf = CFG["scripts"]["augment_manta_vcf"]
conda:
CFG["conda_envs"]["augment_manta_vcf"]
threads:
Expand All @@ -167,7 +167,7 @@ rule _manta_augment_vcf:
mem_mb = CFG["mem_mb"]["augment_vcf"]
shell:
op.as_one_line("""
{input.aug_vcf} {params.opts} --tumour_id {wildcards.tumour_id} --normal_id {wildcards.normal_id}
{params.aug_vcf} {params.opts} --tumour_id {wildcards.tumour_id} --normal_id {wildcards.normal_id}
--vcf_type {wildcards.vcf_name} {input.variants_dir}/{wildcards.vcf_name}.vcf.gz {output.vcf}
> {log.stdout} 2> {log.stderr}
""")
Expand Down
2 changes: 2 additions & 0 deletions modules/manta/2.2/config/default.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,8 @@ lcr-modules:
# Available wildcards: {seq_type} {genome_build} {sample_id}
sample_bam: "__UPDATE__"
sample_bai: "__UPDATE__"

scripts:
augment_manta_vcf: "{SCRIPTSDIR}/augment_manta_vcf/1.0/augment_manta_vcf.py"

options:
Expand Down
8 changes: 4 additions & 4 deletions modules/manta/2.2/manta.smk
Original file line number Diff line number Diff line change
Expand Up @@ -150,15 +150,15 @@ rule _manta_run:
# and fixes the sample IDs in the VCF header to match sample IDs used in Snakemake
rule _manta_augment_vcf:
input:
variants_dir = str(rules._manta_run.output.variants_dir),
aug_vcf = CFG["inputs"]["augment_manta_vcf"]
variants_dir = str(rules._manta_run.output.variants_dir)
output:
vcf = CFG["dirs"]["augment_vcf"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/{vcf_name}.augmented.vcf"
log:
stdout = CFG["logs"]["augment_vcf"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/manta_augment_vcf.{vcf_name}.stdout.log",
stderr = CFG["logs"]["augment_vcf"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/manta_augment_vcf.{vcf_name}.stderr.log"
params:
opts = CFG["options"]["augment_vcf"]
opts = CFG["options"]["augment_vcf"],
aug_vcf = CFG["scripts"]["augment_manta_vcf"]
conda:
CFG["conda_envs"]["augment_manta_vcf"]
threads:
Expand All @@ -167,7 +167,7 @@ rule _manta_augment_vcf:
mem_mb = CFG["mem_mb"]["augment_vcf"]
shell:
op.as_one_line("""
{input.aug_vcf} {params.opts} --tumour_id {wildcards.tumour_id} --normal_id {wildcards.normal_id}
{params.aug_vcf} {params.opts} --tumour_id {wildcards.tumour_id} --normal_id {wildcards.normal_id}
--vcf_type {wildcards.vcf_name} {input.variants_dir}/{wildcards.vcf_name}.vcf.gz {output.vcf}
> {log.stdout} 2> {log.stderr}
""")
Expand Down
2 changes: 2 additions & 0 deletions modules/manta/2.3/config/default.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,8 @@ lcr-modules:
# Available wildcards: {seq_type} {genome_build} {sample_id}
sample_bam: "__UPDATE__"
sample_bai: "__UPDATE__"

scripts:
augment_manta_vcf: "{SCRIPTSDIR}/augment_manta_vcf/1.1/augment_manta_vcf.py"

options:
Expand Down
8 changes: 4 additions & 4 deletions modules/manta/2.3/manta.smk
Original file line number Diff line number Diff line change
Expand Up @@ -153,15 +153,15 @@ rule _manta_run:
# and fixes the sample IDs in the VCF header to match sample IDs used in Snakemake
rule _manta_augment_vcf:
input:
variants_dir = str(rules._manta_run.output.variants_dir),
aug_vcf = CFG["inputs"]["augment_manta_vcf"]
variants_dir = str(rules._manta_run.output.variants_dir)
output:
vcf = CFG["dirs"]["augment_vcf"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/{vcf_name}.augmented.vcf"
log:
stdout = CFG["logs"]["augment_vcf"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/manta_augment_vcf.{vcf_name}.stdout.log",
stderr = CFG["logs"]["augment_vcf"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/manta_augment_vcf.{vcf_name}.stderr.log"
params:
opts = CFG["options"]["augment_vcf"]
opts = CFG["options"]["augment_vcf"],
aug_vcf = CFG["scripts"]["augment_manta_vcf"]
conda:
CFG["conda_envs"]["augment_manta_vcf"]
threads:
Expand All @@ -170,7 +170,7 @@ rule _manta_augment_vcf:
mem_mb = CFG["mem_mb"]["augment_vcf"]
shell:
op.as_one_line("""
{input.aug_vcf} {params.opts} --tumour_id {wildcards.tumour_id} --normal_id {wildcards.normal_id}
{params.aug_vcf} {params.opts} --tumour_id {wildcards.tumour_id} --normal_id {wildcards.normal_id}
--vcf_type {wildcards.vcf_name} {input.variants_dir}/{wildcards.vcf_name}.vcf.gz {output.vcf}
> {log.stdout} 2> {log.stderr}
""")
Expand Down
16 changes: 10 additions & 6 deletions modules/slms_3/1.0/slms_3.smk
Original file line number Diff line number Diff line change
Expand Up @@ -288,8 +288,7 @@ rule _slms_3_mutect2_depth_filt:
table = str(rules._slms_3_mutect2_samples_table.output.table)
output:
vcf = CFG_SLMS3["dirs"]["mutect2_depth_filt"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}.depthfilt.mutect2.combined.vcf.gz",
tbi = CFG_SLMS3["dirs"]["mutect2_depth_filt"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}.depthfilt.mutect2.combined.vcf.gz.tbi",
samples = temp(CFG_SLMS3["dirs"]["mutect2_depth_filt"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}.samples.txt")
tbi = CFG_SLMS3["dirs"]["mutect2_depth_filt"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}.depthfilt.mutect2.combined.vcf.gz.tbi"
log:
stderr = CFG_SLMS3["logs"]["mutect2_depth_filt"] + "{seq_type}--{genome_build}/{tumour_id}--{normal_id}--{pair_status}/mutect2_depth_filt.stderr.log"
conda:
Expand All @@ -302,10 +301,10 @@ rule _slms_3_mutect2_depth_filt:
op.as_one_line("""
tsamp=$(zgrep "##tumor_sample=" {input.vcf} | sed 's|##tumor_sample=||g');
nsamp=$(zgrep "##normal_sample=" {input.vcf} | sed 's|##normal_sample=||g');
printf "$tsamp TUMOR\\n$nsamp NORMAL\\n" > {output.samples} &&
bcftools reheader -s {output.samples} {input.vcf} 2> {log.stderr} |
bcftools view {input.vcf} |
sed "s|$tsamp|TUMOR|g" | sed "s|$nsamp|NORMAL|g" |
bcftools view -s "NORMAL,TUMOR" -i 'FMT/DP[@{input.table}] >= 10 && FMT/AD[@{input.table}:1] >= 4 && FMT/AF[@{input.table}:0] >= 0.1'
-Oz -o {output.vcf} 2>> {log.stderr} &&
-Oz -o {output.vcf} 2> {log.stderr} &&
tabix -p vcf {output.vcf} 2>> {log.stderr}
""")

Expand Down Expand Up @@ -427,7 +426,12 @@ rule _slms_3_output_vcf:
# Generates the target sentinels for each run, which generate the symlinks
rule _slms_3_all:
input:
# rules._starfish_all.input,
rules._manta_all.input,
rules._strelka_all.input,
rules._lofreq_all.input,
rules._sage_all.input,
rules._mutect2_all.input,
rules._starfish_all.input,
expand(
[
str(rules._slms_3_output_vcf.output.isec_vcf),
Expand Down