Skip to content

Commit

Permalink
fix(Snakefile): Linting...
Browse files Browse the repository at this point in the history
  • Loading branch information
@monikaBrandt
monikaBrandt committed Jan 20, 2025
1 parent a2ddc3c commit b7b3954
Showing 1 changed file with 49 additions and 145 deletions.
194 changes: 49 additions & 145 deletions workflow/Snakefile
View file
Original file line number Diff line number Diff line change
Expand Up @@ -45,9 +45,7 @@ use rule bcftools_id_snps as bcftools_id_snps_dna with:
input:
bam="alignment/samtools_merge_bam/{sample}_{type}.bam",
bai="alignment/samtools_merge_bam/{sample}_{type}.bam.bai",
bed=config.get("bcftools_id_snps", {}).get(
"snps_bed", "missing bcftools_id_snps snps_bed file"
),
bed=config.get("bcftools_id_snps", {}).get("snps_bed", "missing bcftools_id_snps snps_bed file"),
ref=config.get("reference", {}).get("fasta", "missing reference fasta"),
wildcard_constraints:
type="[TN]",
Expand Down Expand Up @@ -91,21 +89,11 @@ use rule fastp_pe from prealignment as prealignment_fastp_pe_arriba with:
config.get("fastp_pe_arriba", {}).get("benchmark_repeats", 1),
)
resources:
mem_mb=config.get("fastp_pe_arriba", {}).get(
"mem_mb", config["default_resources"]["mem_mb"]
),
mem_per_cpu=config.get("fastp_pe_arriba", {}).get(
"mem_per_cpu", config["default_resources"]["mem_per_cpu"]
),
partition=config.get("fastp_pe_arriba", {}).get(
"partition", config["default_resources"]["partition"]
),
threads=config.get("fastp_pe_arriba", {}).get(
"threads", config["default_resources"]["threads"]
),
time=config.get("fastp_pe_arriba", {}).get(
"time", config["default_resources"]["time"]
),
mem_mb=config.get("fastp_pe_arriba", {}).get("mem_mb", config["default_resources"]["mem_mb"]),
mem_per_cpu=config.get("fastp_pe_arriba", {}).get("mem_per_cpu", config["default_resources"]["mem_per_cpu"]),
partition=config.get("fastp_pe_arriba", {}).get("partition", config["default_resources"]["partition"]),
threads=config.get("fastp_pe_arriba", {}).get("threads", config["default_resources"]["threads"]),
time=config.get("fastp_pe_arriba", {}).get("time", config["default_resources"]["time"]),
threads: config.get("fastp_pe_arriba", {}).get("threads", config["default_resources"]["threads"])


Expand All @@ -122,31 +110,19 @@ use rule merged from prealignment as prealignment_merged_arriba with:
config.get("merged_arriba", {}).get("benchmark_repeats", 1),
)
resources:
mem_mb=config.get("merged_arriba", {}).get(
"mem_mb", config["default_resources"]["mem_mb"]
),
mem_per_cpu=config.get("merged_arriba", {}).get(
"mem_per_cpu", config["default_resources"]["mem_per_cpu"]
),
partition=config.get("merged_arriba", {}).get(
"partition", config["default_resources"]["partition"]
),
threads=config.get("merged_arriba", {}).get(
"threads", config["default_resources"]["threads"]
),
time=config.get("merged_arriba", {}).get(
"time", config["default_resources"]["time"]
),
mem_mb=config.get("merged_arriba", {}).get("mem_mb", config["default_resources"]["mem_mb"]),
mem_per_cpu=config.get("merged_arriba", {}).get("mem_per_cpu", config["default_resources"]["mem_per_cpu"]),
partition=config.get("merged_arriba", {}).get("partition", config["default_resources"]["partition"]),
threads=config.get("merged_arriba", {}).get("threads", config["default_resources"]["threads"]),
time=config.get("merged_arriba", {}).get("time", config["default_resources"]["time"]),
threads: config.get("merged_arriba", {}).get("threads", config["default_resources"]["threads"])
container:
config.get("merged_arriba", {}).get("container", config["default_container"])


module alignment:
snakefile:
get_module_snakefile(
config, "hydra-genetics/alignment", path="workflow/Snakefile", tag="v0.5.0"
)
get_module_snakefile(config, "hydra-genetics/alignment", path="workflow/Snakefile", tag="v0.5.0")
config:
config

Expand All @@ -168,9 +144,7 @@ use rule star from alignment as alignment_star with:
extra=lambda wildcards: "%s %s"
% (
config.get("star", {}).get("extra", ""),
config.get("star", {}).get(
"read_group", generate_star_read_group(wildcards)
),
config.get("star", {}).get("read_group", generate_star_read_group(wildcards)),
),
idx="{input.idx}",

Expand Down Expand Up @@ -215,17 +189,13 @@ use rule samtools_merge_bam from alignment as alignment_samtools_merge_bam_mutec
benchmark:
repeat(
"snv_indels/gatk_mutect2_merge/{sample}_{type}.bam_unsorted.benchmark.tsv",
config.get("alignment_samtools_merge_bam_mutect2", {}).get(
"benchmark_repeats", 1
),
config.get("alignment_samtools_merge_bam_mutect2", {}).get("benchmark_repeats", 1),
)


module snv_indels:
snakefile:
get_module_snakefile(
config, "hydra-genetics/snv_indels", path="workflow/Snakefile", tag="v1.1.0"
)
get_module_snakefile(config, "hydra-genetics/snv_indels", path="workflow/Snakefile", tag="v1.1.0")
config:
config

Expand All @@ -241,8 +211,7 @@ use rule bcftools_sort from snv_indels as snv_indels_bcftools_sort with:
use rule vardict from snv_indels as snv_indels_vardict with:
input:
bam=lambda wildcards: get_deduplication_bam_chr_input(wildcards),
bai=lambda wildcards: "%s%s"
% (get_deduplication_bam_chr_input(wildcards), ".bai"),
bai=lambda wildcards: "%s%s" % (get_deduplication_bam_chr_input(wildcards), ".bai"),
reference=config["reference"]["fasta"],
regions="snv_indels/bed_split/design_bedfile_{chr}.bed",
params:
Expand All @@ -255,26 +224,22 @@ use rule vardict from snv_indels as snv_indels_vardict with:
use rule gatk_mutect2 from snv_indels as snv_indels_gatk_mutect2 with:
input:
map=lambda wildcards: get_deduplication_bam_chr_input(wildcards),
bai=lambda wildcards: "%s%s"
% (get_deduplication_bam_chr_input(wildcards), ".bai"),
bai=lambda wildcards: "%s%s" % (get_deduplication_bam_chr_input(wildcards), ".bai"),
fasta=config.get("reference", {}).get("fasta", ""),
bed="snv_indels/bed_split/design_bedfile_{chr}.bed",


use rule gatk_mutect2_gvcf from snv_indels as snv_indels_gatk_mutect2_gvcf with:
input:
map=lambda wildcards: get_deduplication_bam_chr_input(wildcards),
bai=lambda wildcards: "%s%s"
% (get_deduplication_bam_chr_input(wildcards), ".bai"),
bai=lambda wildcards: "%s%s" % (get_deduplication_bam_chr_input(wildcards), ".bai"),
fasta=config.get("reference", {}).get("fasta", ""),
bed="snv_indels/bed_split/design_bedfile_{chr}.bed",


module annotation:
snakefile:
get_module_snakefile(
config, "hydra-genetics/annotation", path="workflow/Snakefile", tag="v1.1.0"
)
get_module_snakefile(config, "hydra-genetics/annotation", path="workflow/Snakefile", tag="v1.1.0")
config:
config

Expand Down Expand Up @@ -325,9 +290,7 @@ use rule bcftools_annotate from annotation as annotation_bcftools_annotate_purec
params:
annotation_db=lambda wildcards, input: input.annotation_db,
output_type=config.get("bcftools_annotate_purecn", {}).get("output_type", "z"),
annotation_string=config.get("bcftools_annotate_purecn", {}).get(
"annotation_string", "-m DB"
),
annotation_string=config.get("bcftools_annotate_purecn", {}).get("annotation_string", "-m DB"),
extra=config.get("bcftools_annotate_purecn", {}).get("extra", ""),
log:
"snv_indels/gatk_mutect2/{sample}_{type}.normalized.sorted.vep_annotated.filter.snv_hard_filter_purecn.bcftools_annotated_purecn.vcf.log",
Expand All @@ -340,9 +303,7 @@ use rule bcftools_annotate from annotation as annotation_bcftools_annotate_purec

module filtering:
snakefile:
get_module_snakefile(
config, "hydra-genetics/filtering", path="workflow/Snakefile", tag="v0.3.0"
)
get_module_snakefile(config, "hydra-genetics/filtering", path="workflow/Snakefile", tag="v0.3.0")
config:
config

Expand All @@ -357,9 +318,7 @@ use rule filter_vcf from filtering as filtering_filter_vcf with:

module qc:
snakefile:
get_module_snakefile(
config, "hydra-genetics/qc", path="workflow/Snakefile", tag="v0.5.0"
)
get_module_snakefile(config, "hydra-genetics/qc", path="workflow/Snakefile", tag="v0.5.0")
config:
config

Expand Down Expand Up @@ -447,9 +406,7 @@ use rule picard_collect_alignment_summary_metrics from qc as qc_picard_collect_a
params:
extra="%s %s"
% (
config.get("picard_collect_alignment_summary_metrics", {}).get(
"extra", ""
),
config.get("picard_collect_alignment_summary_metrics", {}).get("extra", ""),
"VALIDATION_STRINGENCY=LENIENT",
),
wildcard_constraints:
Expand Down Expand Up @@ -477,9 +434,7 @@ use rule gatk_get_pileup_summaries from qc as qc_gatk_get_pileup_summaries with:

module biomarker:
snakefile:
get_module_snakefile(
config, "hydra-genetics/biomarker", path="workflow/Snakefile", tag="v0.5.0"
)
get_module_snakefile(config, "hydra-genetics/biomarker", path="workflow/Snakefile", tag="v0.5.0")
config:
config

Expand All @@ -494,9 +449,7 @@ use rule cnvkit2scarhrd from biomarker as biomarker_cnvkit2scarhrd with:

use rule msisensor_pro_filter_sites from biomarker as biomarker_msisensor_pro_filter_sites_unfiltered with:
output:
PoN=temp(
"biomarker/msisensor_pro_filter_sites/{sample}_{type}.Msisensor_pro_reference.unfiltered.list_baseline"
),
PoN=temp("biomarker/msisensor_pro_filter_sites/{sample}_{type}.Msisensor_pro_reference.unfiltered.list_baseline"),
params:
msi_sites_bed="",

Expand Down Expand Up @@ -538,12 +491,8 @@ use rule tmb from biomarker as biomarker_tmb with:

use rule optitype from biomarker as biomarker_optitype with:
output:
coverage_plot=temp(
"biomarker/optitype/{sample}_{type}/{sample}_{type}_hla_type_coverage_plot.pdf"
),
hla_type=temp(
"biomarker/optitype/{sample}_{type}/{sample}_{type}_hla_type_result.tsv"
),
coverage_plot=temp("biomarker/optitype/{sample}_{type}/{sample}_{type}_hla_type_coverage_plot.pdf"),
hla_type=temp("biomarker/optitype/{sample}_{type}/{sample}_{type}_hla_type_result.tsv"),
out_dir=directory("biomarker/optitype/{sample}_{type}/"),


Expand All @@ -553,12 +502,8 @@ use rule tmb from biomarker as biomarker_tmb_umi with:
output:
tmb=temp("biomarker/tmb/{sample}_{type}.umi.TMB.txt"),
params:
af_germline_lower_limit=config.get("tmb_umi", {}).get(
"af_germline_lower_limit", 0.47
),
af_germline_upper_limit=config.get("tmb_umi", {}).get(
"af_germline_upper_limit", 0.53
),
af_germline_lower_limit=config.get("tmb_umi", {}).get("af_germline_lower_limit", 0.47),
af_germline_upper_limit=config.get("tmb_umi", {}).get("af_germline_upper_limit", 0.53),
af_lower_limit=config.get("tmb_umi", {}).get("af_lower_limit", 0.05),
af_upper_limit=config.get("tmb_umi", {}).get("af_upper_limit", 0.95),
artifacts=config.get("tmb_umi", {}).get("artifacts", ""),
Expand All @@ -567,9 +512,7 @@ use rule tmb from biomarker as biomarker_tmb_umi with:
db1000g_limit=config.get("tmb_umi", {}).get("db1000g_limit", 0.0001),
dp_limit=config.get("tmb_umi", {}).get("dp_limit", 200),
filter_genes=config.get("tmb_umi", {}).get("filter_genes", ""),
filter_nr_observations=config.get("tmb_umi", {}).get(
"filter_nr_observations", 1
),
filter_nr_observations=config.get("tmb_umi", {}).get("filter_nr_observations", 1),
gnomad_limit=config.get("tmb_umi", {}).get("gnomad_limit", 0.0001),
nr_avg_germline_snvs=config.get("tmb_umi", {}).get("nr_avg_germline_snvs", 2.0),
nssnv_tmb_correction=config.get("tmb_umi", {}).get("nssnv_tmb_correction", 0.84),
Expand All @@ -578,9 +521,7 @@ use rule tmb from biomarker as biomarker_tmb_umi with:

module fusions:
snakefile:
get_module_snakefile(
config, "hydra-genetics/fusions", path="workflow/Snakefile", tag="v0.2.2"
)
get_module_snakefile(config, "hydra-genetics/fusions", path="workflow/Snakefile", tag="v0.2.2")
config:
config

Expand All @@ -594,43 +535,27 @@ use rule fuseq_wes from fusions as fusions_fuseq_wes with:

use rule filter_report_fuseq_wes from fusions as fusions_filter_report_fuseq_wes_umi with:
output:
fusions=temp(
"fusions/filter_fuseq_wes/{sample}_{type}.fuseq_wes.report.umi.csv"
),
fusions=temp("fusions/filter_fuseq_wes/{sample}_{type}.fuseq_wes.report.umi.csv"),
params:
min_support=config.get("filter_fuseq_wes_umi", {}).get("min_support", ""),
gene_white_list=config.get("filter_fuseq_wes_umi", {}).get(
"gene_white_list", ""
),
gene_fusion_black_list=config.get("filter_fuseq_wes_umi", {}).get(
"gene_fusion_black_list", ""
),
transcript_black_list=config.get("filter_fuseq_wes_umi", {}).get(
"transcript_black_list", ""
),
filter_on_fusiondb=config.get("filter_fuseq_wes_umi", {}).get(
"filter_on_fusiondb", ""
),
gene_white_list=config.get("filter_fuseq_wes_umi", {}).get("gene_white_list", ""),
gene_fusion_black_list=config.get("filter_fuseq_wes_umi", {}).get("gene_fusion_black_list", ""),
transcript_black_list=config.get("filter_fuseq_wes_umi", {}).get("transcript_black_list", ""),
filter_on_fusiondb=config.get("filter_fuseq_wes_umi", {}).get("filter_on_fusiondb", ""),
gtf=config.get("filter_fuseq_wes_umi", {}).get("gtf", ""),


use rule star_fusion from fusions as fusions_star_fusion with:
output:
bam=temp("fusions/star_fusion/{sample}_{type}/Aligned.out.bam"),
fusions=temp(
"fusions/star_fusion/{sample}_{type}/star-fusion.fusion_predictions.tsv"
),
fusions_abridged=temp(
"fusions/star_fusion/{sample}_{type}/star-fusion.fusion_predictions.abridged.coding_effect.tsv"
),
fusions=temp("fusions/star_fusion/{sample}_{type}/star-fusion.fusion_predictions.tsv"),
fusions_abridged=temp("fusions/star_fusion/{sample}_{type}/star-fusion.fusion_predictions.abridged.coding_effect.tsv"),
sj=temp("fusions/star_fusion/{sample}_{type}/SJ.out.tab"),


module cnv_sv:
snakefile:
get_module_snakefile(
config, "hydra-genetics/cnv_sv", path="workflow/Snakefile", tag="v0.7.1"
)
get_module_snakefile(config, "hydra-genetics/cnv_sv", path="workflow/Snakefile", tag="v0.7.1")
config:
config

Expand All @@ -652,18 +577,12 @@ use rule cnvkit_batch from cnv_sv as cnv_sv_cnvkit_batch_hrd with:
bai="alignment/samtools_merge_bam/{sample}_{type}.bam.bai",
reference=config.get("cnvkit_batch_hrd", {}).get("normal_reference_hrd", ""),
output:
antitarget_coverage=temp(
"cnv_sv/cnvkit_batch_hrd/{sample}/{sample}_{type}.antitargetcoverage.cnn"
),
antitarget_coverage=temp("cnv_sv/cnvkit_batch_hrd/{sample}/{sample}_{type}.antitargetcoverage.cnn"),
bins=temp("cnv_sv/cnvkit_batch_hrd/{sample}/{sample}_{type}.bintest.cns"),
regions=temp("cnv_sv/cnvkit_batch_hrd/{sample}/{sample}_{type}.cnr"),
segments=temp("cnv_sv/cnvkit_batch_hrd/{sample}/{sample}_{type}.cns"),
segments_called=temp(
"cnv_sv/cnvkit_batch_hrd/{sample}/{sample}_{type}.call.cns"
),
target_coverage=temp(
"cnv_sv/cnvkit_batch_hrd/{sample}/{sample}_{type}.targetcoverage.cnn"
),
segments_called=temp("cnv_sv/cnvkit_batch_hrd/{sample}/{sample}_{type}.call.cns"),
target_coverage=temp("cnv_sv/cnvkit_batch_hrd/{sample}/{sample}_{type}.targetcoverage.cnn"),
log:
"cnv_sv/cnvkit_batch_hrd/{sample}/{sample}_{type}.log",
benchmark:
Expand Down Expand Up @@ -795,9 +714,7 @@ use rule purecn_purity_file from cnv_sv as cnv_sv_purecn_purity_file with:

module reports:
snakefile:
get_module_snakefile(
config, "hydra-genetics/reports", path="workflow/Snakefile", tag="v0.6.0"
)
get_module_snakefile(config, "hydra-genetics/reports", path="workflow/Snakefile", tag="v0.6.0")
config:
config

Expand All @@ -822,10 +739,7 @@ use rule cnv_html_report from reports as reports_cnv_html_report with:
workflow.source_path("templates/cnv_html_report/style.css"),
],
tc_file=get_tc_file,
extra_table_files=[
t["path"]
for t in config.get("cnv_html_report", {}).get("extra_tables", [])
],
extra_table_files=[t["path"] for t in config.get("cnv_html_report", {}).get("extra_tables", [])],
params:
extra_tables=config.get("cnv_html_report", {}).get("extra_tables", []),
include_table=config.get("cnv_html_report", {}).get("show_table", True),
Expand Down Expand Up @@ -858,21 +772,11 @@ rule merge_cnv_json:
)
threads: config.get("merge_cnv_json", {}).get("threads", config["default_resources"]["threads"])
resources:
mem_mb=config.get("merge_cnv_json", {}).get(
"mem_mb", config["default_resources"]["mem_mb"]
),
mem_per_cpu=config.get("merge_cnv_json", {}).get(
"mem_per_cpu", config["default_resources"]["mem_per_cpu"]
),
partition=config.get("merge_cnv_json", {}).get(
"partition", config["default_resources"]["partition"]
),
threads=config.get("merge_cnv_json", {}).get(
"threads", config["default_resources"]["threads"]
),
time=config.get("merge_cnv_json", {}).get(
"time", config["default_resources"]["time"]
),
mem_mb=config.get("merge_cnv_json", {}).get("mem_mb", config["default_resources"]["mem_mb"]),
mem_per_cpu=config.get("merge_cnv_json", {}).get("mem_per_cpu", config["default_resources"]["mem_per_cpu"]),
partition=config.get("merge_cnv_json", {}).get("partition", config["default_resources"]["partition"]),
threads=config.get("merge_cnv_json", {}).get("threads", config["default_resources"]["threads"]),
time=config.get("merge_cnv_json", {}).get("time", config["default_resources"]["time"]),
container:
config.get("merge_cnv_json", {}).get("container", config["default_container"])
message:
Expand Down

0 comments on commit b7b3954

Please sign in to comment.