Add Read Groups to bowtie2 mapping

.github/workflows/ci.yml

@@ -144,18 +144,21 @@ jobs:
       - name: PMDTOOLS Test PMDtools works alone
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile test_tsv,docker --run_pmdtools
+      - name: GENOTYPING_UG AND BOWTIE2 Test running bowtie2 mapping and genotyping to check valid output for GATK
+        run: |
+          nextflow run ${GITHUB_WORKSPACE} -profile test_tsv,docker --mapper 'bowtie2' --bt2_alignmode 'local' --bt2_sensitivity 'sensitive' --bt2n 1 --bt2l 16 --run_genotyping --genotyping_tool 'ug' --gatk_out_mode 'EMIT_ALL_SITES' --gatk_ug_genotype_model 'SNP'
       - name: GENOTYPING_UG AND MULTIVCFANALYZER Test running GATK UnifiedGenotyper and MultiVCFAnalyzer, additional VCFS
         run: |
-         nextflow run ${GITHUB_WORKSPACE} -profile test_tsv,docker --run_genotyping --genotyping_tool 'ug' --gatk_out_mode 'EMIT_ALL_SITES' --gatk_ug_genotype_model 'SNP' --run_multivcfanalyzer --additional_vcf_files 'https://raw.githubusercontent.com/nf-core/test-datasets/eager/testdata/Mammoth/vcf/JK2772_CATCAGTGAGTAGA_L008_R1_001.fastq.gz.tengrand.fq.combined.fq.mapped_rmdup.bam.unifiedgenotyper.vcf.gz' --write_allele_frequencies
+          nextflow run ${GITHUB_WORKSPACE} -profile test_tsv,docker --run_genotyping --genotyping_tool 'ug' --gatk_out_mode 'EMIT_ALL_SITES' --gatk_ug_genotype_model 'SNP' --run_multivcfanalyzer --additional_vcf_files 'https://raw.githubusercontent.com/nf-core/test-datasets/eager/testdata/Mammoth/vcf/JK2772_CATCAGTGAGTAGA_L008_R1_001.fastq.gz.tengrand.fq.combined.fq.mapped_rmdup.bam.unifiedgenotyper.vcf.gz' --write_allele_frequencies
       - name: COMPLEX LANE/LIBRARY MERGING Test running lane and library merging prior to GATK UnifiedGenotyper and running MultiVCFAnalyzer
         run: |
-         nextflow run ${GITHUB_WORKSPACE} -profile test_tsv_complex,docker --run_genotyping --genotyping_tool 'ug' --gatk_out_mode 'EMIT_ALL_SITES' --gatk_ug_genotype_model 'SNP' --run_multivcfanalyzer
+          nextflow run ${GITHUB_WORKSPACE} -profile test_tsv_complex,docker --run_genotyping --genotyping_tool 'ug' --gatk_out_mode 'EMIT_ALL_SITES' --gatk_ug_genotype_model 'SNP' --run_multivcfanalyzer
       - name: GENOTYPING_UG ON TRIMMED BAM Test
         run: |
-         nextflow run ${GITHUB_WORKSPACE} -profile test_tsv,docker --run_genotyping --run_trim_bam --genotyping_source 'trimmed' --genotyping_tool 'ug' --gatk_out_mode 'EMIT_ALL_SITES' --gatk_ug_genotype_model 'SNP'
+          nextflow run ${GITHUB_WORKSPACE} -profile test_tsv,docker --run_genotyping --run_trim_bam --genotyping_source 'trimmed' --genotyping_tool 'ug' --gatk_out_mode 'EMIT_ALL_SITES' --gatk_ug_genotype_model 'SNP'
       - name: BAM_INPUT Run the basic pipeline with the bam input profile, skip AdapterRemoval as no convertBam
         run: |
-         nextflow run ${GITHUB_WORKSPACE} -profile test_tsv_bam,docker --skip_adapterremoval
+          nextflow run ${GITHUB_WORKSPACE} -profile test_tsv_bam,docker --skip_adapterremoval
       - name: BAM_INPUT Run the basic pipeline with the bam input profile, convert to FASTQ for adapterremoval test and downstream
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile test_tsv_bam,docker --run_convertinputbam

main.nf

@@ -1663,13 +1663,13 @@ 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:${libraryid} --rg PL:illumina 2> "${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:${libraryid} --rg PL:illumina 2> "${libraryid}"_bt2.log | samtools sort -@ ${task.cpus} -O bam > "${libraryid}"_"${seqtype}".mapped.bam
     samtools index "${libraryid}"_"${seqtype}".mapped.bam ${size}
     """
     }