Merge pull request #21 from CCBR/dev/feature-SVCNV

Dev/feature svcnv

.github/workflows/tests.yaml

@@ -20,12 +20,14 @@ jobs:
       run: |
         docker run -v $PWD:/opt2 nextflow/nextflow:22.10.8 \
         python /opt2/logan --fastq "/opt2/.tests/*R{1,2}.fastq.gz" \
+        --genome hg38 \
         --vc --sv --cnv \
         --output /opt2/output_tn_fqs \
         --sample_sheet "/opt2/.tests/pairs.tsv" --stub
     - name: Tumor-only FastQ Stub Run
       run: |
         docker run -v $PWD:/opt2 nextflow/nextflow:22.10.8 \
         python /opt2/logan --fastq "/opt2/.tests/*R{1,2}.fastq.gz" \
-        --vc \
+        --genome hg38 \
+        --vc --sv --cnv \
         --output /opt2/output_tonly_fqs --stub

docker/logan_base/Dockerfile

@@ -20,7 +20,8 @@ WORKDIR /opt2
 RUN apt-get update \
  && apt-get -y upgrade \
  && DEBIAN_FRONTEND=noninteractive apt-get install -y \
-      bc
+      bc \
+      openjdk-17-jdk   
 
 # Common bioinformatics tools 
 # bwa/0.7.17-4  bowtie/1.2.3  bowtie2/2.3.5.1 
@@ -44,23 +45,9 @@ RUN wget https://github.com/biod/sambamba/releases/download/v0.8.1/sambamba-0.8.
     && mv /opt2/sambamba-0.8.1-linux-amd64-static /opt2/sambamba \
     && chmod a+rx /opt2/sambamba
 
-# Install GATK4 (GATK/4.3.0.0)
-# Requires Java8 or 1.8
-RUN wget https://github.com/broadinstitute/gatk/releases/download/4.3.0.0/gatk-4.3.0.0.zip \
-    && unzip /opt2/gatk-4.3.0.0.zip \
-    && rm /opt2/gatk-4.3.0.0.zip \
-    && /opt2/gatk-4.3.0.0/gatk --list
-ENV PATH="/opt2/gatk-4.3.0.0:$PATH"
-
-# 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"
+# Use DISCVRSeq For CombineVariants Replacement
+RUN wget https://github.com/BimberLab/DISCVRSeq/releases/download/1.3.61/DISCVRSeq-1.3.62.jar 
+ENV DISCVRSeq_JAR="/opt2/DISCVRSeq-1.3.62.jar"
 
 # Install dependencies needed to add a new repository over HTTPS
 RUN DEBIAN_FRONTEND=noninteractive apt-get install -y \

logan

@@ -159,19 +159,18 @@ def main():
                 in1="--file_input "+args.file_input
     if (args.stub and args.profile is None): 
         profile="-profile localstub"
+        splitreg="4"
     elif args.profile=="local":
         profile="-profile local"
+        splitreg=str(args.splitregions)
     elif (args.profile=="biowulf" or args.profile is None):
         profile="-profile biowulf"
+        splitreg=str(args.splitregions)
     if args.resume:
         resume="-resume"
     else:
         resume=""
     ###COMBINE ALL COMMANDS (PIPE ALIGN)
-    if args.stub:
-        splitreg="4"
-    else:
-        splitreg=str(args.splitregions)
     commandbase=["nextflow run",dirname + '/main.nf',"-c "+ dirname +"/nextflow.config",
         in1,profile,resume,sample_path,"--genome",args.genome,
         "--output '" +args.output+"'"+" --split_regions " + splitreg]

workflow/modules/variant_calling.nf

@@ -744,13 +744,13 @@ process somaticcombine {
     script:
         vcfin1=[callers, vcfs].transpose().collect { a, b -> a + " " + b }
         vcfin2="-V:" + vcfin1.join(" -V:")
-
-    """    
-    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 \
+    
+    """
+    java -jar \$DISCVRSeq_JAR MergeVcfsAndGenotypes \
+        -R $GENOMEREF \
+        --genotypeMergeOption PRIORITIZE \
+        --priority_list mutect2,strelka,octopus,muse,lofreq,vardict,varscan \
+        --filteredRecordsMergeType KEEP_IF_ANY_UNFILTERED \
         -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 \$GATK_JAR -T CombineVariants \
-        -nt $task.cpus \
+    java -jar \$DISCVRSeq_JAR MergeVcfsAndGenotypes \
+        -R $GENOMEREF \
         --genotypeMergeOption PRIORITIZE \
         --priority_list mutect2_tonly,octopus_tonly,vardict_tonly,varscan_tonly \
         --filteredRecordsMergeType KEEP_IF_ANY_UNFILTERED \