feat: filter snvs

config/config.yaml

@@ -16,6 +16,7 @@ modules:
   prealignment: "v1.1.0"
   qc: "v0.3.0"
   reports: "7c8b8c5"
+  snv_indels: "v0.6.0"
   misc: "v0.1.0"
   sentieon: "b002d39"
 
@@ -117,8 +118,10 @@ fastqc:
   container: "docker://hydragenetics/fastqc:0.11.9"
 
 filter_vcf:
+  sample_name_regex: "^([A-Za-z0-9-]+_[RT])$"
   germline: "config/config_germline_filter.yaml"
   cnv_hardfilter: "config/config_cnv_hardfilter.yaml"
+  somatic: "config/config_snv_softfilter.yaml"
 
 fusioncatcher:
   container: "docker://hydragenetics/fusioncatcher:1.33"
@@ -337,3 +340,9 @@ vep:
   container: "docker://hydragenetics/vep:105"
   vep_cache: ""
   extra: "--assembly GRCh38 --check_existing --pick --sift b --polyphen b --ccds --uniprot --hgvs --symbol --numbers --domains --regulatory --canonical --protein --biotype --uniprot --tsl --appris --gene_phenotype --af --af_1kg --af_gnomad --max_af --pubmed --variant_class"
+
+vt_decompose:
+  container: "docker://hydragenetics/vt:2015.11.10"
+
+vt_normalize:
+  container: "docker://hydragenetics/vt:2015.11.10"

config/config_snv_softfilter.yaml

@@ -0,0 +1,51 @@
+filters:
+  af:
+    description: "Softfilter variants where T have AF lower than 5 percent"
+    expression: "FORMAT:AF:0 < 0.05"
+    soft_filter: "True"
+    soft_filter_flag: "AF_lt_0.05"
+  ad:
+    description: "Softfilter variants where T have AD lower than 3?"
+    expression: "FORMAT:AD:1 < 3"
+    soft_filter: "True"
+    soft_filter_flag: "AD_lt_3"
+  dp:
+    description: "Softfilter variants where dp is lower than 10x"
+    expression: "FORMAT:DP < 10"
+    soft_filter: "True"
+    soft_filter_flag: "DP_lt_10"
+  germline:
+    description: "Soft filter germline if >2% in any population from 1000 genomes, ESP or gnomADe"
+    expression: "(VEP:MAX_AF > 0.02)"
+    soft_filter_flag: "PopAF_0.02"
+    soft_filter: "True"
+  intron:
+    description: "Soft filter intronic variants except if also splice"
+    expression: "(exist[intron_variant, VEP:Consequence] and !exist[splice, VEP:Consequence])"
+    soft_filter_flag: "Intron"
+    soft_filter: "True"
+  protein_coding:
+    description: "Soft filter variants not deemed protein_coding"
+    expression: "(VEP:BIOTYPE != protein_coding)"
+    soft_filter_flag: "Biotype"
+    soft_filter: "True"
+  consequences:
+    description: "Soft filter based on consequences"
+    expression:
+      "(exist[intergenic_variant, VEP:Consequence] or exist[NMD_transcript_variant, VEP:Consequence] or
+      exist[non_coding_transcript_variant, VEP:Consequence] or
+      exist[upstream_gene_variant, VEP:Consequence] or
+      exist[downstream_gene_variant, VEP:Consequence] or
+      exist[TFBS_ablation, VEP:Consequence] or
+      exist[TFBS_amplification, VEP:Consequence] or
+      exist[TF_binding_site_variant, VEP:Consequence] or
+      exist[regulatory_region_ablation, VEP:Consequence] or
+      exist[regulatory_region_amplification, VEP:Consequence] or
+      exist[regulatory_region_variant, VEP:Consequence])"
+    soft_filter_flag: "Consequence"
+    soft_filter: "True"
+  n_ratio:
+    description: "Soft filter variants where normal freq is atleast 5 times bigger than tumour freq"
+    expression: "INFO:NA_FALSE:N_ratio > 5"
+    soft_filter_flag: "N_ratio_lgt_5"
+    soft_filter: "True"

config/output_files.json

@@ -16,28 +16,28 @@
 
   "Results/{sample}/Cram/{sample}_{type}.crumble.cram": {"name": "_results_cram", "file": "compression/crumble/{sample}_{type}.crumble.cram", "types": ["T", "N"]},
   "Results/{sample}/Cram/{sample}_{type}.crumble.cram.crai": {"name": "_results_crai", "file": "compression/crumble/{sample}_{type}.crumble.cram.crai", "types": ["T", "N"]},
-  "Results/{sample}/SNV_indels/{sample}_T.vep.vcf.gz": {"name": "_results_vcf_t", "file": "parabricks/pbrun_mutectcaller_t/{sample}_T.vep.vcf.gz", "types": ["T"]},
-  "Results/{sample}/SNV_indels/{sample}_T.vep.vcf.gz.tbi": {"name": "_results_tbi_t", "file": "parabricks/pbrun_mutectcaller_t/{sample}_T.vep.vcf.gz.tbi", "types": ["T"]},
-  "Results/{sample}/SNV_indels/{sample}_T.vep.all.vcf.gz": {"name": "_results_vcf_all_t", "file": "parabricks/pbrun_mutectcaller_t/{sample}_T.vep.include.all.vcf.gz", "types": ["T"]},
-  "Results/{sample}/SNV_indels/{sample}_T.vep.all.vcf.gz.tbi": {"name": "_results_tbi_all_t", "file": "parabricks/pbrun_mutectcaller_t/{sample}_T.vep.include.all.vcf.gz.tbi", "types": ["T"]},
-  "Results/{sample}/SNV_indels/{sample}_T.vep.aml.vcf.gz": {"name": "_results_vcf_aml_t", "file": "parabricks/pbrun_mutectcaller_t/{sample}_T.vep.include.aml.vcf.gz", "types": ["T"]},
-  "Results/{sample}/SNV_indels/{sample}_T.vep.aml.vcf.gz.tbi": {"name": "_results_tbi_aml_t", "file": "parabricks/pbrun_mutectcaller_t/{sample}_T.vep.include.aml.vcf.gz.tbi", "types": ["T"]},
-  "Results/{sample}/SNV_indels/{sample}_T.vep.tm.vcf.gz": {"name": "_results_vcf_tm_t", "file": "parabricks/pbrun_mutectcaller_t/{sample}_T.vep.include.tm.vcf.gz", "types": ["T"]},
-  "Results/{sample}/SNV_indels/{sample}_T.vep.tm.vcf.gz.tbi": {"name": "_results_tbi_tm_t", "file": "parabricks/pbrun_mutectcaller_t/{sample}_T.vep.include.tm.vcf.gz.tbi", "types": ["T"]},
+  "Results/{sample}/SNV_indels/{sample}_T.vep.vcf.gz": {"name": "_results_vcf_t", "file": "parabricks/pbrun_mutectcaller_t/{sample}_T.normalized.vep.filter.somatic.vcf.gz", "types": ["T"]},
+  "Results/{sample}/SNV_indels/{sample}_T.vep.vcf.gz.tbi": {"name": "_results_tbi_t", "file": "parabricks/pbrun_mutectcaller_t/{sample}_T.normalized.vep.filter.somatic.vcf.gz.tbi", "types": ["T"]},
+  "Results/{sample}/SNV_indels/{sample}_T.vep.all.vcf.gz": {"name": "_results_vcf_all_t", "file": "parabricks/pbrun_mutectcaller_t/{sample}_T.normalized.vep.filter.somatic.include.all.vcf.gz", "types": ["T"]},
+  "Results/{sample}/SNV_indels/{sample}_T.vep.all.vcf.gz.tbi": {"name": "_results_tbi_all_t", "file": "parabricks/pbrun_mutectcaller_t/{sample}_T.normalized.vep.filter.somatic.include.all.vcf.gz.tbi", "types": ["T"]},
+  "Results/{sample}/SNV_indels/{sample}_T.vep.aml.vcf.gz": {"name": "_results_vcf_aml_t", "file": "parabricks/pbrun_mutectcaller_t/{sample}_T.normalized.vep.filter.somatic.include.aml.vcf.gz", "types": ["T"]},
+  "Results/{sample}/SNV_indels/{sample}_T.vep.aml.vcf.gz.tbi": {"name": "_results_tbi_aml_t", "file": "parabricks/pbrun_mutectcaller_t/{sample}_T.normalized.vep.filter.somatic.include.aml.vcf.gz.tbi", "types": ["T"]},
+  "Results/{sample}/SNV_indels/{sample}_T.vep.tm.vcf.gz": {"name": "_results_vcf_tm_t", "file": "parabricks/pbrun_mutectcaller_t/{sample}_T.normalized.vep.filter.somatic.include.tm.vcf.gz", "types": ["T"]},
+  "Results/{sample}/SNV_indels/{sample}_T.vep.tm.vcf.gz.tbi": {"name": "_results_tbi_tm_t", "file": "parabricks/pbrun_mutectcaller_t/{sample}_T.normalized.vep.filter.somatic.include.tm.vcf.gz.tbi", "types": ["T"]},
   "Results/{sample}/SNV_indels/{sample}_T.xlsx": {"name": "_results_xlsx_t", "file": "export_to_xlsx/t/{sample}_T.snvs.xlsx", "types": ["T"]},
 
-  "Results/{sample}/SNV_indels/{sample}_TN.vep.vcf.gz": {"name": "_results_vcf_tn", "file": "parabricks/pbrun_mutectcaller_tn/{sample}.vep.vcf.gz", "types": ["TN"]},
-  "Results/{sample}/SNV_indels/{sample}_TN.vep.vcf.gz.tbi": {"name": "_results_tbi_tn", "file": "parabricks/pbrun_mutectcaller_tn/{sample}.vep.vcf.gz.tbi", "types": ["TN"]},
-  "Results/{sample}/SNV_indels/{sample}_TN.vep.all.vcf.gz": {"name": "_results_vcf_all", "file": "parabricks/pbrun_mutectcaller_tn/{sample}.vep.include.all.vcf.gz", "types": ["TN"]},
-  "Results/{sample}/SNV_indels/{sample}_TN.vep.all.vcf.gz.tbi": {"name": "_results_tbi_all", "file": "parabricks/pbrun_mutectcaller_tn/{sample}.vep.include.all.vcf.gz.tbi", "types": ["TN"]},
-  "Results/{sample}/SNV_indels/{sample}_TN.vep.aml.vcf.gz": {"name": "_results_vcf_aml", "file": "parabricks/pbrun_mutectcaller_tn/{sample}.vep.include.aml.vcf.gz", "types": ["TN"]},
-  "Results/{sample}/SNV_indels/{sample}_TN.vep.aml.vcf.gz.tbi": {"name": "_results_tbi_aml", "file": "parabricks/pbrun_mutectcaller_tn/{sample}.vep.include.aml.vcf.gz.tbi", "types": ["TN"]},
-  "Results/{sample}/SNV_indels/{sample}_TN.vep.tm.vcf.gz": {"name": "_results_vcf_tm", "file": "parabricks/pbrun_mutectcaller_tn/{sample}.vep.include.tm.vcf.gz", "types": ["TN"]},
-  "Results/{sample}/SNV_indels/{sample}_TN.vep.tm.vcf.gz.tbi": {"name": "_results_tbi_tm", "file": "parabricks/pbrun_mutectcaller_tn/{sample}.vep.include.tm.vcf.gz.tbi", "types": ["TN"]},
+  "Results/{sample}/SNV_indels/{sample}_TN.vep.vcf.gz": {"name": "_results_vcf_tn", "file": "parabricks/pbrun_mutectcaller_tn/{sample}.normalized.vep.ratio.filter.somatic.vcf.gz", "types": ["TN"]},
+  "Results/{sample}/SNV_indels/{sample}_TN.vep.vcf.gz.tbi": {"name": "_results_tbi_tn", "file": "parabricks/pbrun_mutectcaller_tn/{sample}.normalized.vep.ratio.filter.somatic.vcf.gz.tbi", "types": ["TN"]},
+  "Results/{sample}/SNV_indels/{sample}_TN.vep.all.vcf.gz": {"name": "_results_vcf_all", "file": "parabricks/pbrun_mutectcaller_tn/{sample}.normalized.vep.ratio.filter.somatic.include.all.vcf.gz", "types": ["TN"]},
+  "Results/{sample}/SNV_indels/{sample}_TN.vep.all.vcf.gz.tbi": {"name": "_results_tbi_all", "file": "parabricks/pbrun_mutectcaller_tn/{sample}.normalized.vep.ratio.filter.somatic.include.all.vcf.gz.tbi", "types": ["TN"]},
+  "Results/{sample}/SNV_indels/{sample}_TN.vep.aml.vcf.gz": {"name": "_results_vcf_aml", "file": "parabricks/pbrun_mutectcaller_tn/{sample}.normalized.vep.ratio.filter.somatic.include.aml.vcf.gz", "types": ["TN"]},
+  "Results/{sample}/SNV_indels/{sample}_TN.vep.aml.vcf.gz.tbi": {"name": "_results_tbi_aml", "file": "parabricks/pbrun_mutectcaller_tn/{sample}.normalized.vep.ratio.filter.somatic.include.aml.vcf.gz.tbi", "types": ["TN"]},
+  "Results/{sample}/SNV_indels/{sample}_TN.vep.tm.vcf.gz": {"name": "_results_vcf_tm", "file": "parabricks/pbrun_mutectcaller_tn/{sample}.normalized.vep.ratio.filter.somatic.include.tm.vcf.gz", "types": ["TN"]},
+  "Results/{sample}/SNV_indels/{sample}_TN.vep.tm.vcf.gz.tbi": {"name": "_results_tbi_tm", "file": "parabricks/pbrun_mutectcaller_tn/{sample}.normalized.vep.ratio.filter.somatic.include.tm.vcf.gz.tbi", "types": ["TN"]},
   "Results/{sample}/SNV_indels/{sample}_TN.xlsx": {"name": "_results_xlsx_tn", "file": "export_to_xlsx/tn/{sample}.snvs.xlsx", "types": ["TN"]},
 
-  "Results/{sample}/SNV_indels/{sample}_mutectcaller_T.all.tsv": {"name": "_results_tsv_all_t", "file": "tsv_files/{sample}_mutectcaller_t.all.tsv", "types": ["T"]},
-  "Results/{sample}/SNV_indels/{sample}_mutectcaller_T.aml.tsv": {"name": "_results_tsv_aml_t", "file": "tsv_files/{sample}_mutectcaller_t.aml.tsv", "types": ["T"]},
+  "Results/{sample}/SNV_indels/{sample}_mutectcaller_T.all.tsv": {"name": "_results_tsv_all_t", "file": "tsv_files/{sample}_T_mutectcaller_t.all.tsv", "types": ["T"]},
+  "Results/{sample}/SNV_indels/{sample}_mutectcaller_T.aml.tsv": {"name": "_results_tsv_aml_t", "file": "tsv_files/{sample}_T_mutectcaller_t.aml.tsv", "types": ["T"]},
 
   "Results/{sample}/SNV_indels/{sample}_mutectcaller_TN.all.tsv": {"name": "_results_tsv_all", "file": "tsv_files/{sample}_mutectcaller_tn.all.tsv", "types": ["TN"]},
   "Results/{sample}/SNV_indels/{sample}_mutectcaller_TN.aml.tsv": {"name": "_results_tsv_aml", "file": "tsv_files/{sample}_mutectcaller_tn.aml.tsv", "types": ["TN"]},

docs/softwares.md

@@ -19,3 +19,24 @@ Introduction to export_to_xlsx
 #### Resources settings (`resources.yaml`)
 
 #RESOURCESSCHEMA__export_to_xlsx#
+
+## [annotate_normal_ratio](url_to_tool)
+Introduction to annotate_normal_ratio
+
+### :snake: Rule
+
+#SNAKEMAKE_RULE_SOURCE__annotate__annotate_normal_ratio#
+
+#### :left_right_arrow: input / output files
+
+#SNAKEMAKE_RULE_TABLE__annotate__annotate_normal_ratio#
+
+### :wrench: Configuration
+
+#### Software settings (`config.yaml`)
+
+#CONFIGSCHEMA__annotate_normal_ratio#
+
+#### Resources settings (`resources.yaml`)
+
+#RESOURCESSCHEMA__annotate_normal_ratio#

workflow/Snakefile

@@ -5,6 +5,7 @@ __license__ = "GPL-3"
 
 
 include: "rules/common.smk"
+include: "rules/annotate.smk"
 include: "rules/cnvkit.smk"
 include: "rules/cnvkit_table.smk"
 include: "rules/dux4_rearrangements.smk"
@@ -96,40 +97,21 @@ use rule * from annotation as annotation_*
 
 use rule vep from annotation as annotation_vep with:
     input:
-        vcf="parabricks/pbrun_mutectcaller_tn/{sample}.vcf.gz",
-        tabix="parabricks/pbrun_mutectcaller_tn/{sample}.vcf.gz.tbi",
+        vcf="parabricks/pbrun_mutectcaller_{analysis}/{sample_type}.normalized.vcf.gz",
+        tabix="parabricks/pbrun_mutectcaller_{analysis}/{sample_type}.normalized.vcf.gz.tbi",
         cache=config["vep"]["vep_cache"],
         fasta=config["reference"]["fasta"],
     output:
-        vcf=temp("parabricks/pbrun_mutectcaller_tn/{sample}.vep.vcf"),
+        vcf=temp("parabricks/pbrun_mutectcaller_{analysis}/{sample_type}.normalized.vep.vcf"),
     log:
-        "parabricks/pbrun_mutectcaller_tn/{sample}.vep.vcf.log",
+        "parabricks/pbrun_mutectcaller_{analysis}/{sample_type}.normalized.vep.vcf.log",
     benchmark:
         repeat(
-            "parabricks/pbrun_mutectcaller_tn/{sample}.vep.vcf.benchmark.tsv",
+            "parabricks/pbrun_mutectcaller_{analysis}/{sample_type}.normalized.vep.vcf.benchmark.tsv",
             config.get("vep", {}).get("benchmark_repeats", 1),
         )
     message:
-        "{rule}: Annotate {wildcards.sample}.vcf"
-
-
-use rule vep from annotation as annotation_vep_t with:
-    input:
-        vcf="parabricks/pbrun_mutectcaller_t/{sample}_T.vcf.gz",
-        tabix="parabricks/pbrun_mutectcaller_t/{sample}_T.vcf.gz.tbi",
-        cache=config["vep"]["vep_cache"],
-        fasta=config["reference"]["fasta"],
-    output:
-        vcf=temp("parabricks/pbrun_mutectcaller_t/{sample}_T.vep.vcf"),
-    log:
-        "parabricks/pbrun_mutectcaller_t/{sample}_T.vep.vcf.log",
-    benchmark:
-        repeat(
-            "parabricks/pbrun_mutectcaller_t/{sample}_T.vep.vcf.benchmark.tsv",
-            config.get("vep", {}).get("benchmark_repeats", 1),
-        )
-    message:
-        "{rule}: Annotate {wildcards.sample}_T.vcf"
+        "{rule}: Annotate {input.vcf} with vep"
 
 
 use rule simple_sv_annotation from annotation as annotation_simple_sv_annotation_tn with:
@@ -147,7 +129,7 @@ use rule simple_sv_annotation from annotation as annotation_simple_sv_annotation
             config.get("snpeff", {}).get("benchmark_repeats", 1),
         )
     message:
-        "{rule}: Annotate cnv_sv/manta_run_workflow_tn/{wildcards.sample}/results/variants/somaticSV.snpeff.vcf.gz"
+        "{rule}: Annotate {input.vcf}"
 
 
 use rule simple_sv_annotation from annotation as annotation_simple_sv_annotation_t with:
@@ -324,18 +306,18 @@ use rule filter_vcf from filtering as filtering_filter_vcf
 
 use rule bcftools_filter_include_region from filtering as filtering_bcftools_filter_include_region_snv_t with:
     input:
-        vcf="parabricks/pbrun_mutectcaller_t/{sample}_T.vep.vcf.gz",
-        tabix="parabricks/pbrun_mutectcaller_t/{sample}_T.vep.vcf.gz.tbi",
+        vcf="parabricks/pbrun_mutectcaller_t/{sample}_T.normalized.vep.filter.somatic.vcf.gz",
+        tabix="parabricks/pbrun_mutectcaller_t/{sample}_T.normalized.vep.filter.somatic.vcf.gz.tbi",
     output:
-        vcf=temp("parabricks/pbrun_mutectcaller_t/{sample}_T.vep.include.{bed}.vcf"),
+        vcf=temp("parabricks/pbrun_mutectcaller_t/{sample}_T.normalized.vep.filter.somatic.include.{bed}.vcf"),
     params:
         filter=lambda wildcards: "-R %s" % config["bcftools_SNV"][wildcards.bed],
         extra=config.get("bcftools_SNV", {}).get("extra", ""),
     log:
-        "parabricks/pbrun_mutectcaller_t/{sample}_T.vep.include.{bed}.vcf.log",
+        "parabricks/pbrun_mutectcaller_t/{sample}_T.normalized.vep.filter.somatic.include.{bed}.vcf.log",
     benchmark:
         repeat(
-            "parabricks/pbrun_mutectcaller_t/{sample}_T.vep.include.{bed}.vcf.benchmark.tsv",
+            "parabricks/pbrun_mutectcaller_t/{sample}_T.normalized.vep.filter.somatic.include.{bed}.vcf.benchmark.tsv",
             config.get("bcftools_SNV", {}).get("benchmark_repeats", 1),
         )
     message:
@@ -344,18 +326,18 @@ use rule bcftools_filter_include_region from filtering as filtering_bcftools_fil
 
 use rule bcftools_filter_include_region from filtering as filtering_bcftools_filter_include_region_snv_tn with:
     input:
-        vcf="parabricks/pbrun_mutectcaller_tn/{sample}.vep.vcf.gz",
-        tabix="parabricks/pbrun_mutectcaller_tn/{sample}.vep.vcf.gz.tbi",
+        vcf="parabricks/pbrun_mutectcaller_tn/{sample}.normalized.vep.ratio.filter.somatic.vcf.gz",
+        tabix="parabricks/pbrun_mutectcaller_tn/{sample}.normalized.vep.ratio.filter.somatic.vcf.gz.tbi",
     output:
-        vcf=temp("parabricks/pbrun_mutectcaller_tn/{sample}.vep.include.{bed}.vcf"),
+        vcf=temp("parabricks/pbrun_mutectcaller_tn/{sample}.normalized.vep.ratio.filter.somatic.include.{bed}.vcf"),
     params:
         filter=lambda wildcards: "-R %s" % config["bcftools_SNV"][wildcards.bed],
         extra=config.get("bcftools_SNV", {}).get("extra", ""),
     log:
-        "parabricks/pbrun_mutectcaller_tn/{sample}.vep.include.{bed}.vcf.log",
+        "parabricks/pbrun_mutectcaller_tn/{sample}.normalized.vep.ratio.filter.somatic.include.{bed}.vcf.log",
     benchmark:
         repeat(
-            "parabricks/pbrun_mutectcaller_tn/{sample}.vep.include.{bed}.vcf.benchmark.tsv",
+            "parabricks/pbrun_mutectcaller_tn/{sample}.normalized.vep.ratio.filter.somatic.include.{bed}.vcf.benchmark.tsv",
             config.get("bcftools_SNV", {}).get("benchmark_repeats", 1),
         )
     message:
@@ -556,9 +538,9 @@ if aligner == "bwa_sentieon":
 
 use rule peddy from qc as qc_peddy with:
     input:
-        vcf="parabricks/pbrun_mutectcaller_t/{sample}_T.vcf.gz",
+        vcf="parabricks/pbrun_mutectcaller_t/{sample}_T.normalized.vcf.gz",
         ped="qc/peddy/{sample}.peddy.fam",
-        tbi="parabricks/pbrun_mutectcaller_t/{sample}_T.vcf.gz.tbi",
+        tbi="parabricks/pbrun_mutectcaller_t/{sample}_T.normalized.vcf.gz.tbi",
     output:
         ped=temp("qc/peddy/{sample}/peddy.peddy.ped"),
         ped_check=temp("qc/peddy/{sample}/peddy.ped_check.csv"),
@@ -712,6 +694,47 @@ use rule cnv_html_report from reports as reports_cnv_html_report with:
         tc_method="pathology",
 
 
+module snv_indels:
+    snakefile:
+        github(
+            "hydra-genetics/snv_indels",
+            path="workflow/Snakefile",
+            tag=config["modules"]["snv_indels"],
+        )
+    config:
+        config
+
+
+use rule vt_decompose from snv_indels as snv_indels_vt_decompose with:
+    input:
+        vcf="parabricks/pbrun_mutectcaller_{analysis}/{sample_type}.vcf.gz",
+        tbi="parabricks/pbrun_mutectcaller_{analysis}/{sample_type}.vcf.gz.tbi",
+    output:
+        vcf=temp("parabricks/pbrun_mutectcaller_{analysis}/{sample_type}.decomposed.vcf.gz"),
+    log:
+        "parabricks/pbrun_mutectcaller_{analysis}/{sample_type}.decomposed.vcf.gz.log",
+    benchmark:
+        repeat(
+            "parabricks/pbrun_mutectcaller_{analysis}/{sample_type}.decomposed.vcf.gz.benchmark.tsv",
+            config.get("vt_decompose", {}).get("benchmark_repeats", 1),
+        )
+
+
+use rule vt_normalize from snv_indels as snv_indels_vt_normalize with:
+    input:
+        vcf="parabricks/pbrun_mutectcaller_{analysis}/{sample_type}.decomposed.vcf.gz",
+        ref=config["reference"]["fasta"],
+    output:
+        vcf="parabricks/pbrun_mutectcaller_{analysis}/{sample_type}.normalized.vcf.gz",
+    log:
+        "parabricks/pbrun_mutectcaller_{analysis}/{sample_type}.normalized.vcf.gz.log",
+    benchmark:
+        repeat(
+            "parabricks/pbrun_mutectcaller_{analysis}/{sample_type}.normalized.vcf.gz.benchmark.tsv",
+            config.get("vt_normalize", {}).get("benchmark_repeats", 1),
+        )
+
+
 module misc:
     snakefile:
         github("hydra-genetics/misc", path="workflow/Snakefile", tag=config["modules"]["misc"])