fix: change back to gatk3

Author: dnousome

docker/logan_base/Dockerfile

@@ -17,12 +17,10 @@ WORKDIR /opt2
 # This section installs system packages required for your project
 # If you need extra system packages add them here.
 # python/3.8.0 and python/2.7.16 (strelka and manta)
-# JDK 17 for DISCVRSeq
 RUN apt-get update \
  && apt-get -y upgrade \
  && DEBIAN_FRONTEND=noninteractive apt-get install -y \
-      bc \
-      openjdk-17-jdk   
+      bc
 
 # Common bioinformatics tools 
 # bwa/0.7.17-4  bowtie/1.2.3  bowtie2/2.3.5.1 
@@ -54,9 +52,15 @@ RUN wget https://github.com/broadinstitute/gatk/releases/download/4.3.0.0/gatk-4
     && /opt2/gatk-4.3.0.0/gatk --list
 ENV PATH="/opt2/gatk-4.3.0.0:$PATH"
 
-# Use DISCVRSeq For CombineVariants Replacement
-RUN wget https://github.com/BimberLab/DISCVRSeq/releases/download/1.3.61/DISCVRSeq-1.3.61.jar 
-ENV DISCVRSeq_JAR="/opt2/DISCVRSeq-1.3.61.jar"
+# Install last release of GATK3 (GATK/3.8-1)
+# Only being used for the CombineVariants
+# command that is not available in GATK4
+# Available via env variable: $GATK_JAR
+# Requires Java8 or 1.8
+RUN wget https://storage.googleapis.com/gatk-software/package-archive/gatk/GenomeAnalysisTK-3.8-1-0-gf15c1c3ef.tar.bz2 \
+    && tar -xvjf /opt2/GenomeAnalysisTK-3.8-1-0-gf15c1c3ef.tar.bz2 \
+    && rm /opt2/GenomeAnalysisTK-3.8-1-0-gf15c1c3ef.tar.bz2
+ENV GATK_JAR="/opt2/GenomeAnalysisTK-3.8-1-0-gf15c1c3ef/GenomeAnalysisTK.jar"
 
 # Install dependencies needed to add a new repository over HTTPS
 RUN DEBIAN_FRONTEND=noninteractive apt-get install -y \

nextflow.config

@@ -23,7 +23,7 @@ params {
     script_freecpaired = "${projectDir}/workflow/scripts/freec_paired.pl"
     freec_significance = "${projectDir}/workflow/scripts/assess_significance.R"
     freec_plot = "${projectDir}/workflow/scripts/makeGraph.R"
-    lofreq_convert = "${projectDir}/workflow/scripts/lofreq_convert.sh"
+    lofreq_convert = "${projectDir}/workflow/scripts/add_gt_lofreq.sh"
     vep_cache = "/fdb/VEP/102/cache"
 
     //Biowulf
@@ -84,6 +84,10 @@ profiles {
             withLabel: process_somaticcaller {
                 container = 'docker://dnousome/ccbr_logan_base:v0.3.3' 
             }
+            //Name Based 
+            withName:bwamem2 {
+                container = 'docker://dnousome/ccbr_logan_base:v0.3.3'
+            }
             withName:fastq_screen {
                 container = 'docker://nciccbr/ccbr_fastq_screen_0.13.0:v2.0' 
             }

workflow/modules/trim_align.nf

@@ -63,7 +63,7 @@ process bwamem2 {
         ${GENOMEREF} \
         ${samplename}.R1.trimmed.fastq.gz ${samplename}.R2.trimmed.fastq.gz | \
     samblaster -M | \
-    samtools sort -@$task.cpus -m 4G - -o ${samplename}.bam
+    samtools sort -@ $task.cpus -m 4G - -o ${samplename}.bam
 
     samtools index -@ $task.cpus ${samplename}.bam ${samplename}.bai
 

workflow/modules/variant_calling.nf

@@ -360,7 +360,7 @@ process vardict_tn {
             -S \
             -f 0.05 >  ${tumor.simpleName}_vs_${normal.simpleName}_${bed.simpleName}.vardict.vcf
 
-    printf "${normal.Name}\t${normalname}\t${tumor.Name}\t${tumorname}\n" > sampname 
+    printf "${normal.Name}\t${normalname}\n${tumor.Name}\t${tumorname}\n" > sampname 
     
     bcftools reheader -s sampname ${tumor.simpleName}_vs_${normal.simpleName}_${bed.simpleName}.vardict.vcf \
         | bcftools view -Oz -o ${tumor.simpleName}_vs_${normal.simpleName}_${bed.simpleName}.vardict.vcf.gz
@@ -493,8 +493,15 @@ process lofreq_tn {
         ${tumorname}_vs_${normalname}_${bed.simpleName}_somatic_final_minus-dbsnp.indels.vcf.gz --threads $task.cpus -Oz -o \
         ${tumorname}_vs_${normalname}_${bed.simpleName}_temp_lofreq.vcf.gz
 
-    $LOFREQ_CONVERT ${tumorname}_vs_${normalname}_${bed.simpleName}_temp_lofreq.vcf.gz ${tumorname} \
-        | bcftools view -Oz -o ${tumorname}_vs_${normalname}_${bed.simpleName}_lofreq.vcf.gz
+    $LOFREQ_CONVERT -i ${tumorname}_vs_${normalname}_${bed.simpleName}_temp_lofreq.vcf.gz -g 1/0 \
+        -n ${tumorname} -o ${tumorname}_vs_${normalname}_${bed.simpleName}_temp1_lofreq.vcf.gz
+    
+    bcftools view -h ${tumorname}_vs_${normalname}_${bed.simpleName}_temp1_lofreq.vcf.gz >temphead
+    
+    sed 's/^##FORMAT=<ID=DP4,Number=4,Type=Integer,Description="Counts for ref-forward bases, ref-reverse, alt-forward and alt-reverse bases">/##FORMAT=<ID=DP4,Number=1,Type=String,Description="Strand read counts: ref\\/fwd, ref\\/rev, var\\/fwd, var\\/rev">/' temphead > temphead1
+    bcftools reheader ${tumorname}_vs_${normalname}_${bed.simpleName}_temp1_lofreq.vcf.gz -h temphead1 |\
+        bcftools view -Oz -o ${tumorname}_vs_${normalname}_${bed.simpleName}_lofreq.vcf.gz
+
     bcftools index -t ${tumorname}_vs_${normalname}_${bed.simpleName}_lofreq.vcf.gz
 
     """
@@ -738,12 +745,12 @@ process somaticcombine {
         vcfin1=[callers, vcfs].transpose().collect { a, b -> a + " " + b }
         vcfin2="-V:" + vcfin1.join(" -V:")
 
-    """
-    java -jar \$DISCVRSeq_JAR MergeVcfsAndGenotypes \
-        -R $GENOMEREF \
-        --genotypeMergeOption PRIORITIZE \
-        --priority_list mutect2,strelka,octopus,muse,lofreq,vardict,varscan \
-        --filteredRecordsMergeType KEEP_IF_ANY_UNFILTERED \
+    """    
+    java  -jar \$GATK_JAR -T CombineVariants \
+        -nt $task.cpus \
+        --filteredrecordsmergetype KEEP_IF_ANY_UNFILTERED \
+        --genotypemergeoption PRIORITIZE \
+        --rod_priority_list mutect2,strelka,muse,lofreq,vardict,varscan \
         -O ${tumorsample}_vs_${normal}_combined.vcf.gz \
         $vcfin2
     """

workflow/modules/variant_calling_tonly.nf

@@ -364,8 +364,8 @@ process somaticcombine_tonly {
         vcfin2="-V:" + vcfin1.join(" -V:")
 
     """
-    java -jar \$DISCVRSeq_JAR MergeVcfsAndGenotypes \
-        -R $GENOMEREF \
+    java -jar \$GATK_JAR -T CombineVariants \
+        -nt $task.cpus \
         --genotypeMergeOption PRIORITIZE \
         --priority_list mutect2_tonly,octopus_tonly,vardict_tonly,varscan_tonly \
         --filteredRecordsMergeType KEEP_IF_ANY_UNFILTERED \