v0.4 - clear folders for Manta run, fix optional annotation parameters.

Author: ricardovialle

config/config.yaml

@@ -1,37 +1,31 @@
 # All paths set on this file are relative to the workdir (if not absolute). 
 workdir: "/hpc/users/viallr01/ad-omics/ricardo/MyRepo/snakeSV/"
 
-OUT_FOLDER: "results_GIAB"
+OUT_FOLDER: "results_GIAB_refHGSVC2"
 SAMPLE_KEY: "config/sampleKey.txt"
 
 TOOLS: 
   - "manta"
   - "smoove" 
   - "delly"
 
-# Custom annotations (optional)
-ANNOTATION_BED: 
-  - "data/annotation/custom/astrocytes_H3K27ac.bed"
-  - "data/annotation/custom/microglia_H3K27ac.bed"
-  - "data/annotation/custom/neurons_H3K27ac.bed"
-  - "data/annotation/custom/oligodendrocytes_H3K27ac.bed"
-
 # Custom SVs for genotyping (optional)
 SV_PANEL:
-  - "data/sv_panel/hg002/variants.vcf"
+  - "data/sv_panel/HGSVC2/merged.h37.vcf"
 
 # Reference genome files
 REFERENCE_FASTA: "data/ref/human_g1k_v37.fasta"
 REF_BUILD: "37"
 
 # Gencode GTF for SV annotation
-GENCODE_GTF: "data/annotation/gtf/gencode.v38lift37.annotation.nochr.gtf.gz"
+#GENCODE_GTF: "data/annotation/gtf/gencode.v38lift37.annotation.nochr.gtf.gz"
+
+# Custom annotations (optional)
+#ANNOTATION_BED: 
+#  - "data/annotation/custom/astrocytes_H3K27ac.bed"
+#  - "data/annotation/custom/microglia_H3K27ac.bed"
+#  - "data/annotation/custom/neurons_H3K27ac.bed"
+#  - "data/annotation/custom/oligodendrocytes_H3K27ac.bed"
 
 # Custom tmp folder (if not /tmp)
 TMP_DIR: "~/ad-omics/ricardo/tmp/"
-
-# Supporting files for tools like smoove and delly. 
-# This path is relative to the Snakefile folder. 
-# No need to change in most of the cases.
-LIB_DIR: "../resources/"
-

example/tiny/config.yaml

@@ -1,4 +1,4 @@
-# All paths set on this file are relative to the workdir (if not absolute). 
+# All paths set on this file are relative to the workdir (if not absolute).
 SAMPLE_KEY: "sampleKey.txt"
 
 TOOLS: 
@@ -8,16 +8,7 @@ TOOLS:
 # Reference genome files
 REFERENCE_FASTA: "ref.fasta"
 REF_BUILD: "37"
-#DICT: "ref.dict"
-#NMASK: "ref.nmask.fasta.bed"
 
 # Gencode GTF for SV annotation
 GENCODE_GTF: "gencode.gtf.gz"
 
-# Custom tmp folder (if not /tmp)
-TMP_DIR: "/tmp/"
-
-# Supporting files for tools like smoove and delly. 
-# This path is relative to the Snakefile folder. 
-# No need to change in most of the cases.
-LIB_DIR: "../resources/"

snakeSV

@@ -2,7 +2,7 @@
 
 # Function: Print a help message.
 display_help() {
-	echo "snakeSV Pipeline (powered by Snakemake)"
+	echo "snakeSV pipeline (powered by Snakemake)"
 	echo ""
 	echo "Usage: $0 --configfile FILE [Snakemake options]"
 	echo ""
@@ -15,11 +15,13 @@ display_help() {
 	echo "   -k, --keep-going       go on with independent jobs if a job fails"
 	echo "   -n, --dryrun           do not execute anything"
 	echo "   -p, --printshellcmds   print out the shell commands that will be executed"
-	echo "   -t, --timestamp  		  add a timestamp to all logging output"
+	echo "   -t, --timestamp        add a timestamp to all logging output"
   echo ""
 	echo " Full list of parameters:"
   echo "   --help                 show Snakemake help (or snakemake -h)"
 	echo ""
+	echo "More info at https://github.com/RajLabMSSM/snakeSV"
+	echo ""
   exit 0
 }
 

workflow/Snakefile

@@ -112,7 +112,6 @@ include: "rules/preprocess.smk"
 include: "rules/qc.smk"
 include: "rules/other.smk"
 include: "rules/genotype.smk"
-include: "rules/annotation.smk"
 
 ###################################################################################################
 ## SV discovery tools
@@ -126,7 +125,11 @@ for tool in config["TOOLS"]:
 ###################################################################################################
 final_output = [OUT_FOLDER + "/merged_cohort/gt_merged.vcf.gz.tbi"]
 
-if( "GENCODE_GTF" or "ANNOTATION_BED" not in config ):
+################################################################################################### 
+## Annotations
+###################################################################################################
+if( ("GENCODE_GTF" in config) or ("ANNOTATION_BED" in config) ):
+	include: "rules/annotation.smk"
 	final_output.append(OUT_FOLDER + "/merged_cohort/gt_merged.annot.vcf.gz.tbi")
 
 ################################################################################################### 

workflow/rules/tools/manta.smk

@@ -3,6 +3,7 @@ rule manta:
 		bam = OUT_FOLDER + "/input/{sample}.bam",
 		bai = OUT_FOLDER + "/input/{sample}.bam.bai"
 	output:
+		outdir = directory(OUT_FOLDER + "/sv_discovery/manta/{sample}/outdir/"),
 		vcf = OUT_FOLDER + "/sv_discovery/manta/{sample}/{sample}.manta.vcf.gz",
 		tbi = OUT_FOLDER + "/sv_discovery/manta/{sample}/{sample}.manta.vcf.gz.tbi"
 	conda:
@@ -14,9 +15,8 @@ rule manta:
 		"configManta.py \
 			--bam {input.bam} \
 			--referenceFasta {REFERENCE_FASTA} \
-			--runDir {OUT_FOLDER}/sv_discovery/manta/{wildcards.sample}/; "
-		"{OUT_FOLDER}/sv_discovery/manta/{wildcards.sample}/runWorkflow.py; "
-		"zgrep -v 'SVTYPE=BND' {OUT_FOLDER}/sv_discovery/manta/{wildcards.sample}/results/variants/diploidSV.vcf.gz | \
+			--runDir {output.outdir}; "
+		"{output.outdir}/runWorkflow.py; "
+		"zgrep -v 'SVTYPE=BND' {output.outdir}/results/variants/diploidSV.vcf.gz | \
 			bcftools sort -Oz -o {output.vcf}; "
 		"tabix -p vcf {output.vcf}; "
-