Merge pull request #658 from IdoBar/patch-2

Add PU tag to Read Groups for all mapping methods

Author: jfy133

CHANGELOG.md

@@ -10,6 +10,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 ### `Fixed`
 
 - [#654](https://github.com/nf-core/eager/issues/654) - Fixed some values in JSON schema (used in launch GUI) not passing validation checks during run
+- [#655](https://github.com/nf-core/eager/issues/655) - Updated read groups for all mappers to allow proper GATK validation
 
 ### `Dependencies`
 

README.md

@@ -160,6 +160,7 @@ Those who have provided conceptual guidance, suggestions, bug reports etc.
 
 * Arielle Munters
 * [Hester van Schalkwyk](https://github.com/hesterjvs)
+* [Ido Bar](https://github.com/IdoBar)
 * [Irina Velsko](https://github.com/ivelsko)
 * [Katerine Eaton](https://github.com/ktmeaton)
 * [Luc Venturini](https://github.com/lucventurini)

main.nf

@@ -1494,14 +1494,14 @@ process bwa {
     """
     bwa aln -t ${task.cpus} $fasta ${r1} -n ${params.bwaalnn} -l ${params.bwaalnl} -k ${params.bwaalnk} -f ${libraryid}.r1.sai
     bwa aln -t ${task.cpus} $fasta ${r2} -n ${params.bwaalnn} -l ${params.bwaalnl} -k ${params.bwaalnk} -f ${libraryid}.r2.sai
-    bwa sampe -r "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina" $fasta ${libraryid}.r1.sai ${libraryid}.r2.sai ${r1} ${r2} | samtools sort -@ ${task.cpus} -O bam - > ${libraryid}_"${seqtype}".mapped.bam
+    bwa sampe -r "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina\\tPU:ILLUMINA-${libraryid}-${seqtype}" $fasta ${libraryid}.r1.sai ${libraryid}.r2.sai ${r1} ${r2} | samtools sort -@ ${task.cpus} -O bam - > ${libraryid}_"${seqtype}".mapped.bam
     samtools index "${libraryid}"_"${seqtype}".mapped.bam ${size}
     """
     } else {
     //PE collapsed, or SE data 
     """
     bwa aln -t ${task.cpus} ${fasta} ${r1} -n ${params.bwaalnn} -l ${params.bwaalnl} -k ${params.bwaalnk} -f ${libraryid}.sai
-    bwa samse -r "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina" $fasta ${libraryid}.sai $r1 | samtools sort -@ ${task.cpus} -O bam - > "${libraryid}"_"${seqtype}".mapped.bam
+    bwa samse -r "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina\\tPU:ILLUMINA-${libraryid}-${seqtype}" $fasta ${libraryid}.sai $r1 | samtools sort -@ ${task.cpus} -O bam - > "${libraryid}"_"${seqtype}".mapped.bam
     samtools index "${libraryid}"_"${seqtype}".mapped.bam ${size}
     """
     }
@@ -1531,12 +1531,12 @@ process bwamem {
 
     if (!params.single_end && params.skip_collapse){
     """
-    bwa mem -t ${task.cpus} $fasta $r1 $r2 -R "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina" | samtools sort -@ ${task.cpus} -O bam - > "${libraryid}"_"${seqtype}".mapped.bam
+    bwa mem -t ${task.cpus} $fasta $r1 $r2 -R "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina\\tPU:ILLUMINA-${libraryid}-${seqtype}" | samtools sort -@ ${task.cpus} -O bam - > "${libraryid}"_"${seqtype}".mapped.bam
     samtools index ${size} -@ ${task.cpus} "${libraryid}".mapped.bam
     """
     } else {
     """
-    bwa mem -t ${task.cpus} $fasta $r1 -R "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina" | samtools sort -@ ${task.cpus} -O bam - > "${libraryid}"_"${seqtype}".mapped.bam
+    bwa mem -t ${task.cpus} $fasta $r1 -R "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina\\tPU:ILLUMINA-${libraryid}-${seqtype}" | samtools sort -@ ${task.cpus} -O bam - > "${libraryid}"_"${seqtype}".mapped.bam
     samtools index -@ ${task.cpus} "${libraryid}"_"${seqtype}".mapped.bam ${size} 
     """
     }
@@ -1600,15 +1600,15 @@ process circularmapper{
     """
     bwa aln -t ${task.cpus} $elongated_root $r1 -n ${params.bwaalnn} -l ${params.bwaalnl} -k ${params.bwaalnk} -f ${libraryid}.r1.sai
     bwa aln -t ${task.cpus} $elongated_root $r2 -n ${params.bwaalnn} -l ${params.bwaalnl} -k ${params.bwaalnk} -f ${libraryid}.r2.sai
-    bwa sampe -r "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina" $elongated_root ${libraryid}.r1.sai ${libraryid}.r2.sai $r1 $r2 > tmp.out
+    bwa sampe -r "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina\\tPU:ILLUMINA-${libraryid}-${seqtype}" $elongated_root ${libraryid}.r1.sai ${libraryid}.r2.sai $r1 $r2 > tmp.out
     realignsamfile -e ${params.circularextension} -i tmp.out -r $fasta $filter 
     samtools sort -@ ${task.cpus} -O bam tmp_realigned.bam > ${libraryid}_"${seqtype}".mapped.bam
     samtools index "${libraryid}"_"${seqtype}".mapped.bam ${size} 
     """
     } else {
     """ 
     bwa aln -t ${task.cpus} $elongated_root $r1 -n ${params.bwaalnn} -l ${params.bwaalnl} -k ${params.bwaalnk} -f ${libraryid}.sai
-    bwa samse -r "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina" $elongated_root ${libraryid}.sai $r1 > tmp.out
+    bwa samse -r "@RG\\tID:ILLUMINA-${libraryid}\\tSM:${libraryid}\\tPL:illumina\\tPU:ILLUMINA-${libraryid}-${seqtype}" $elongated_root ${libraryid}.sai $r1 > tmp.out
     realignsamfile -e ${params.circularextension} -i tmp.out -r $fasta $filter 
     samtools sort -@ ${task.cpus} -O bam tmp_realigned.bam > "${libraryid}"_"${seqtype}".mapped.bam
     samtools index "${libraryid}"_"${seqtype}".mapped.bam ${size}
@@ -1677,13 +1677,13 @@ process bowtie2 {
     //PE data without merging, PE data without any AR applied
     if ( seqtype == 'PE' && ( params.skip_collapse || params.skip_adapterremoval ) ){
     """
-    bowtie2 -x ${fasta} -1 ${r1} -2 ${r2} -p ${task.cpus} ${sensitivity} ${bt2n} ${bt2l} ${trim5} ${trim3} 2> "${libraryid}"_bt2.log | samtools sort -@ ${task.cpus} -O bam > "${libraryid}"_"${seqtype}".mapped.bam
+    bowtie2 -x ${fasta} -1 ${r1} -2 ${r2} -p ${task.cpus} ${sensitivity} ${bt2n} ${bt2l} ${trim5} ${trim3} --rg-id ILLUMINA-${libraryid} --rg SM:${libraryid} --rg PL:illumina --rg PU:ILLUMINA-${libraryid}-${seqtype} 2> "${libraryid}"_bt2.log | samtools sort -@ ${task.cpus} -O bam > "${libraryid}"_"${seqtype}".mapped.bam
     samtools index "${libraryid}"_"${seqtype}".mapped.bam ${size}
     """
     } else {
     //PE collapsed, or SE data 
     """
-    bowtie2 -x ${fasta} -U ${r1} -p ${task.cpus} ${sensitivity} ${bt2n} ${bt2l} ${trim5} ${trim3} 2> "${libraryid}"_bt2.log | samtools sort -@ ${task.cpus} -O bam > "${libraryid}"_"${seqtype}".mapped.bam
+    bowtie2 -x ${fasta} -U ${r1} -p ${task.cpus} ${sensitivity} ${bt2n} ${bt2l} ${trim5} ${trim3} --rg-id ILLUMINA-${libraryid} --rg SM:${libraryid} --rg PL:illumina --rg PU:ILLUMINA-${libraryid}-${seqtype} 2> "${libraryid}"_bt2.log | samtools sort -@ ${task.cpus} -O bam > "${libraryid}"_"${seqtype}".mapped.bam
     samtools index "${libraryid}"_"${seqtype}".mapped.bam ${size}
     """
     }