snakefmt

Author: FelixMoelder

workflow/rules/annotation.smk

@@ -8,18 +8,18 @@ rule annotate_candidate_variants:
     output:
         calls="results/candidate-calls/{caller}/{group}/{group}.{scatteritem}.annotated.bcf",
         stats="results/candidate-calls/{caller}/{group}/{group}.{scatteritem}.stats.html",
-    params:
-        plugins=config["annotations"]["vep"]["candidate_calls"]["plugins"],
-        extra="{} --vcf_info_field ANN ".format(
-            config["annotations"]["vep"]["candidate_calls"]["params"]
-        ),
     log:
         "logs/vep/{caller}/{group}/{group}.{scatteritem}.annotate_candidates.log",
     benchmark:
         "benchmarks/vep/{caller}/{group}/{group}.{scatteritem}.annotate_candidates.tsv"
-    threads: 4
     group:
         "candidate-annotation"
+    threads: 4
+    params:
+        plugins=config["annotations"]["vep"]["candidate_calls"]["plugins"],
+        extra="{} --vcf_info_field ANN ".format(
+            config["annotations"]["vep"]["candidate_calls"]["params"]
+        ),
     wrapper:
         "v8.0.0/bio/vep/annotate"
 
@@ -44,6 +44,11 @@ rule annotate_variants:
     output:
         calls="results/calls/vep_annotated/{group}/{group}.{calling_type}.{scatteritem}.bcf",
         stats="results/calls/vep_annotated/{group}/{group}.{calling_type}.{scatteritem}.stats.html",
+    log:
+        "logs/vep/{group}.{calling_type}.{scatteritem}.annotate.log",
+    group:
+        "annotation"
+    threads: 4
     params:
         # Pass a list of plugins to use, see https://www.ensembl.org/info/docs/tools/vep/script/vep_plugins.html
         # Plugin args can be added as well, e.g. via an entry "MyPlugin,1,FOO", see docs.
@@ -57,11 +62,6 @@ rule annotate_variants:
         extra="{} --vcf_info_field ANN --hgvsg".format(
             config["annotations"]["vep"]["final_calls"]["params"]
         ),
-    log:
-        "logs/vep/{group}.{calling_type}.{scatteritem}.annotate.log",
-    threads: 4
-    group:
-        "annotation"
     wrapper:
         "v8.0.0/bio/vep/annotate"
 
@@ -76,13 +76,13 @@ rule annotate_vcfs:
         "results/calls/db_annotated/{prefix}.bcf",
     log:
         "logs/annotate-vcfs/{prefix}.log",
-    params:
-        pipes=get_annotation_pipes,
+    group:
+        "annotation"
     conda:
         "../envs/snpsift.yaml"
     threads: 4
-    group:
-        "annotation"
+    params:
+        pipes=get_annotation_pipes,
     shell:
         "(bcftools view --threads {threads} {input.bcf} {params.pipes} | "
         "bcftools view --threads {threads} -Ob > {output}) 2> {log}"
@@ -91,18 +91,18 @@ rule annotate_vcfs:
 rule annotate_dgidb:
     input:
         get_annotate_dgidb_input,
-    params:
-        datasources=get_dgidb_datasources(),
     output:
         "results/calls/dgidb_annotated/{prefix}.bcf",
     log:
         "logs/annotate-dgidb/{prefix}.log",
+    group:
+        "annotation"
     conda:
         "../envs/rbt.yaml"
     resources:
         dgidb_requests=1,
-    group:
-        "annotation"
+    params:
+        datasources=get_dgidb_datasources(),
     shell:
         "rbt vcf-annotate-dgidb {input} {params.datasources} > {output} 2> {log}"
 
@@ -123,9 +123,9 @@ rule gather_annotated_calls:
         "results/final-calls/{group}/{group}.{calling_type}.annotated.bcf",
     log:
         "logs/gather-annotated-calls/{group}/{group}.{calling_type}.log",
-    params:
-        extra="-a",
     group:
         "annotation"
+    params:
+        extra="-a",
     wrapper:
         "v2.3.2/bio/bcftools/concat"

workflow/rules/benchmarking.smk

@@ -57,13 +57,13 @@ rule chm_to_fastq:
 rule chm_eval_kit:
     output:
         directory("resources/benchmarking/chm-eval-kit"),
+    log:
+        "logs/benchmarking/chm-eval-kit.log",
+    cache: True
     params:
         # Tag and version must match, see https://github.com/lh3/CHM-eval/releases.
         tag="v0.5",
         version="20180222",
-    log:
-        "logs/benchmarking/chm-eval-kit.log",
-    cache: True
     wrapper:
         "v2.3.2/bio/benchmark/chm-eval-kit"
 
@@ -87,12 +87,12 @@ rule rename_chromosomes:
         map=f"resources/{genome_name}.chrmap.txt",
     output:
         "benchmarking/{query}.chr-mapped.vcf",
-    params:
-        targets=",".join(list(map("chr{}".format, range(23))) + ["chrX", "chrY"]),
     log:
         "logs/benchmarking/{query}.rename-chromosomes.log",
     conda:
         "../envs/bcftools.yaml"
+    params:
+        targets=",".join(list(map("chr{}".format, range(23))) + ["chrX", "chrY"]),
     shell:
         "(bcftools annotate --rename-chrs {input.map} {input} | "
         "bcftools view --targets {params.targets} > {output}) 2> {log} "
@@ -105,10 +105,10 @@ rule chm_eval:
     output:
         summary="benchmarking/{query}.summary",  # summary statistics
         bed="benchmarking/{query}.err.bed.gz",  # bed file with errors
+    log:
+        "logs/benchmarking/{query}.chm-eval.log",
     params:
         extra="",
         build="38",
-    log:
-        "logs/benchmarking/{query}.chm-eval.log",
     wrapper:
         "v2.3.2/bio/benchmark/chm-eval"

workflow/rules/calling.smk

@@ -13,11 +13,11 @@ rule render_scenario:
         ),
     log:
         "logs/render-scenario/{group}.log",
+    conda:
+        None
     params:
         samples=lambda wc: samples[samples["group"] == wc.group],
         annotation=lambda wc: group_annotation.loc[wc.group],
-    conda:
-        None
     template_engine:
         "yte"
 
@@ -48,16 +48,16 @@ rule varlociraptor_preprocess:
         alignment_props=get_alignment_props,
     output:
         "results/observations/{caller}/{group}/{sample}.{scatteritem}.bcf",
-    params:
-        extra=lambda wc: get_varlociraptor_params(
-            wc, config["params"]["varlociraptor"]["preprocess"]
-        ),
     log:
         "logs/varlociraptor/preprocess/{group}/{sample}.{caller}.{scatteritem}.log",
     benchmark:
         "benchmarks/varlociraptor/preprocess/{group}/{sample}.{caller}.{scatteritem}.tsv"
     conda:
         "../envs/varlociraptor.yaml"
+    params:
+        extra=lambda wc: get_varlociraptor_params(
+            wc, config["params"]["varlociraptor"]["preprocess"]
+        ),
     shell:
         "varlociraptor preprocess variants --candidates {input.candidates} {params.extra} "
         "--alignment-properties {input.alignment_props} {input.ref} --bam {input.bam} --output {output} "
@@ -74,6 +74,10 @@ rule varlociraptor_call:
         ),
     log:
         "logs/varlociraptor/call/{caller}/{group}.{scatteritem}.log",
+    benchmark:
+        "benchmarks/varlociraptor/call/{group}/{group}.{caller}.{scatteritem}.tsv"
+    conda:
+        "../envs/varlociraptor.yaml"
     params:
         obs=get_varlociraptor_obs_args,
         # Add -o as workaround to separate info field entries from subcommand
@@ -86,10 +90,6 @@ rule varlociraptor_call:
             if not config["calling"].get("infer_genotypes")
             else "| varlociraptor genotype >"
         ),
-    conda:
-        "../envs/varlociraptor.yaml"
-    benchmark:
-        "benchmarks/varlociraptor/call/{group}/{group}.{caller}.{scatteritem}.tsv"
     shell:
         "(varlociraptor call variants {params.extra} generic --obs {params.obs}"
         " --scenario {input.scenario} {params.postprocess} {output}) 2> {log}"
@@ -100,15 +100,15 @@ rule sort_calls:
         "results/calls/varlociraptor/{caller}/{group}/{group}.{scatteritem}.unsorted.bcf",
     output:
         temp("results/calls/varlociraptor/{caller}/{group}/{group}.{scatteritem}.bcf"),
+    log:
+        "logs/bcf-sort/{group}/{group}.{caller}.{scatteritem}.log",
+    resources:
+        mem_mb=8000,
     params:
         # Set to True, in case you want uncompressed BCF output
         uncompressed_bcf=False,
         # Extra arguments
         extras="",
-    log:
-        "logs/bcf-sort/{group}/{group}.{caller}.{scatteritem}.log",
-    resources:
-        mem_mb=8000,
     wrapper:
         "v2.6.0/bio/bcftools/sort"
 

workflow/rules/candidate_calling.smk

@@ -10,6 +10,7 @@ rule freebayes:
         "results/candidate-calls/freebayes/{group}/{group}.bcf",
     log:
         "logs/freebayes/{group}.log",
+    threads: 96  # with more cores, we expect freebayes to become too IO bound and memory hungry
     params:
         # genotyping is performed by varlociraptor, hence we deactivate it in freebayes by
         # always setting --pooled-continuous
@@ -18,7 +19,6 @@ rule freebayes:
             config["params"]["freebayes"].get("min_alternate_fraction", "0.05"),
             config["params"]["freebayes"].get("extra", ""),
         ),
-    threads: 96  # with more cores, we expect freebayes to become too IO bound and memory hungry
     wrapper:
         "v2.7.0/bio/freebayes"
 
@@ -34,9 +34,9 @@ rule delly:
         "results/candidate-calls/delly/{group}/{group}.bcf",
     log:
         "logs/delly/{group}.log",
+    threads: lambda _, input: len(input.alns)  # delly parallelizes over the number of samples
     params:
         extra=config["params"].get("delly", ""),
-    threads: lambda _, input: len(input.alns)  # delly parallelizes over the number of samples
     wrapper:
         "v2.3.2/bio/delly"
 
@@ -62,10 +62,10 @@ rule filter_offtarget_variants:
         regions="resources/target_regions/target_regions.bed",
     output:
         "results/candidate-calls/{caller}/filtered/{group}/{group}.bcf",
-    params:
-        extra="",
     log:
         "logs/filter_offtarget_variants/{group}/{group}.{caller}.log",
+    params:
+        extra="",
     wrapper:
         "v2.3.2/bio/bcftools/filter"
 

workflow/rules/datavzrd.smk

@@ -6,14 +6,14 @@ rule split_call_tables:
     output:
         coding="results/tables/{group}/{group}.{event}.coding.fdr-controlled.tsv",
         noncoding="results/tables/{group}/{group}.{event}.noncoding.fdr-controlled.tsv",
-    params:
-        sorting=lambda wc: config["calling"]["fdr-control"]["events"][wc.event].get(
-            "sort", list()
-        ),
     log:
         "logs/split_tables/{group}.{event}.log",
     conda:
         "../envs/split_call_tables.yaml"
+    params:
+        sorting=lambda wc: config["calling"]["fdr-control"]["events"][wc.event].get(
+            "sort", list()
+        ),
     script:
         "../scripts/split-call-tables.py"
 
@@ -53,11 +53,11 @@ rule prepare_oncoprint:
         ),
     log:
         "logs/prepare_oncoprint/{batch}.{event}.log",
+    conda:
+        "../envs/oncoprint.yaml"
     params:
         groups=get_report_batch("variants"),
         labels=get_heterogeneous_labels(),
-    conda:
-        "../envs/oncoprint.yaml"
     script:
         "../scripts/oncoprint.py"
 
@@ -162,11 +162,11 @@ rule bedtools_merge:
         right="results/regions/{group}.covered_regions.bed",
     output:
         "results/coverage/{group}/{sample}.regions.filtered.bed",
+    log:
+        "logs/bedtools/{group}/{sample}.log",
     params:
         ## Add optional parameters
         extra="-wa",
-    log:
-        "logs/bedtools/{group}/{sample}.log",
     wrapper:
         "v2.6.0/bio/bedtools/intersect"
 
@@ -179,12 +179,12 @@ rule coverage_table:
         ),
     output:
         "results/coverage/{group}.csv",
-    params:
-        min_cov=config["gene_coverage"].get("min_avg_coverage", 0),
-    conda:
-        "../envs/pandas.yaml"
     log:
         "logs/coverage/{group}_coverage_table.log",
+    conda:
+        "../envs/pandas.yaml"
+    params:
+        min_cov=config["gene_coverage"].get("min_avg_coverage", 0),
     script:
         "../scripts/coverage_table.py"
 

workflow/rules/filtering.smk

@@ -6,11 +6,11 @@ rule filter_candidates_by_annotation:
         "results/candidate-calls/{caller}/filtered/{group}/{group}.{scatteritem}.bcf",
     log:
         "logs/filter-calls/annotation/{caller}/{group}/{group}.{scatteritem}.log",
+    conda:
+        "../envs/vembrane.yaml"
     params:
         filter=get_candidate_filter_expression,
         aux=get_candidate_filter_aux,
-    conda:
-        "../envs/vembrane.yaml"
     shell:
         "(bcftools norm -Ou --do-not-normalize --multiallelics -any {input} | "
         'vembrane filter {params.aux} "{params.filter}" | bcftools sort -Ob > {output}) &> {log}'
@@ -25,11 +25,11 @@ rule filter_by_annotation:
         "results/calls/filtered/filtered_ann/{group}/{event}/{group}.{calling_type}.{scatteritem}.bcf",
     log:
         "logs/filter-calls/annotation/{group}/{event}/{group}.{calling_type}.{scatteritem}.log",
+    conda:
+        "../envs/vembrane.yaml"
     params:
         filter=get_annotation_filter_expression,
         aux=get_annotation_filter_aux,
-    conda:
-        "../envs/vembrane.yaml"
     shell:
         'vembrane filter {params.aux} "{params.filter}" {input.bcf} --output-fmt bcf --output {output} &> {log}'
 
@@ -39,14 +39,14 @@ rule filter_odds:
         "results/calls/filtered/filtered_ann/{group}/{event}/{group}.{calling_type}.{scatteritem}.bcf",
     output:
         "results/calls/filtered/filtered_odds/{group}/{event}/{group}.{calling_type}.{scatteritem}.bcf",
-    params:
-        events=lambda wc: config["calling"]["fdr-control"]["events"][wc.event][
-            "varlociraptor"
-        ],
     log:
         "logs/filter-calls/posterior_odds/{group}/{event}/{group}.{calling_type}.{scatteritem}.log",
     conda:
         "../envs/varlociraptor.yaml"
+    params:
+        events=lambda wc: config["calling"]["fdr-control"]["events"][wc.event][
+            "varlociraptor"
+        ],
     shell:
         "varlociraptor filter-calls posterior-odds --events {params.events} --odds barely < {input} > {output} 2> {log}"
 
@@ -72,10 +72,10 @@ rule control_fdr:
         "results/calls/fdr-controlled/{group}/{event}/{group}.{vartype}.{calling_type}.bcf",
     log:
         "logs/control-fdr/{group}/{event}/{group}.{vartype}.{calling_type}.log",
-    params:
-        query=get_fdr_control_params,
     conda:
         "../envs/varlociraptor.yaml"
+    params:
+        query=get_fdr_control_params,
     shell:
         "varlociraptor filter-calls control-fdr {input} {params.query[mode]} --var {wildcards.vartype} "
         "--events {params.query[events]} --fdr {params.query[threshold]} {params.query[retain_artifacts]} > {output} 2> {log}"