implemented readgroup addition in fastq_align_chromap, since chromap has no option to do it

subworkflows/nf-core/fastq_align_chromap/main.nf

@@ -2,8 +2,9 @@
  * Map reads, sort, index BAM file and run samtools stats, flagstat and idxstats
  */
 
-include { CHROMAP_CHROMAP         } from '../../../modules/nf-core/chromap/chromap/main'
-include { BAM_SORT_STATS_SAMTOOLS } from '../bam_sort_stats_samtools/main'
+include { CHROMAP_CHROMAP               } from '../../../modules/nf-core/chromap/chromap/main'
+include { PICARD_ADDORREPLACEREADGROUPS } from '../../../modules/nf-core/picard/addorreplacereadgroups/main'
+include { BAM_SORT_STATS_SAMTOOLS       } from '../bam_sort_stats_samtools/main'
 
 workflow FASTQ_ALIGN_CHROMAP {
     take:
@@ -14,9 +15,13 @@ workflow FASTQ_ALIGN_CHROMAP {
     ch_whitelist // channel (optional):  [ whitelist ]
     ch_chr_order // channel (optional):  [ chr_order ]
     ch_pairs_chr_order // channel (optional):  [ pairs_chr_order ]
+    update_readgroups // boolean (optional): true or false controls whether readgroups should be updated post alignment
 
     main:
 
+    ch_bam = channel.empty()
+    def add_readgroups = update_readgroups ?: false
+
     //
     // Remap ch_fasta_fai to ch_fasta
     //
@@ -27,10 +32,21 @@ workflow FASTQ_ALIGN_CHROMAP {
     //
     CHROMAP_CHROMAP(ch_reads, ch_fasta, ch_index, ch_barcodes, ch_whitelist, ch_chr_order, ch_pairs_chr_order)
 
+    //
+    // Update read groups
+    //
+    PICARD_ADDORREPLACEREADGROUPS(CHROMAP_CHROMAP.out.bam, ch_fasta_fai)
+
+    if (add_readgroups == true) {
+        ch_bam = PICARD_ADDORREPLACEREADGROUPS.out.bam
+    } else {
+        ch_bam = CHROMAP_CHROMAP.out.bam
+    }
+
     //
     // Sort, index BAM file and run samtools stats, flagstat and idxstats
     //
-    BAM_SORT_STATS_SAMTOOLS(CHROMAP_CHROMAP.out.bam, ch_fasta_fai)
+    BAM_SORT_STATS_SAMTOOLS(ch_bam, ch_fasta_fai)
 
     emit:
     bam      = BAM_SORT_STATS_SAMTOOLS.out.bam // channel: [ val(meta), [ bam ] ]

subworkflows/nf-core/fastq_align_chromap/meta.yml

@@ -1,6 +1,6 @@
 # yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/subworkflows/yaml-schema.json
 name: "fastq_align_chromap"
-description: Align high throughput chromatin profiles using Chromap then sort with samtools
+description: Align high throughput chromatin profiles using Chromap, updating readgroups if neccessary and then sort with samtools
 keywords:
   - align
   - fasta
@@ -12,6 +12,7 @@ keywords:
   - hic
 components:
   - chromap/chromap
+  - picard/addorreplacereadgroups
   - samtools/sort
   - samtools/index
   - samtools/stats
@@ -67,6 +68,11 @@ input:
       description: |
         Structure: [path(pairs_chr_order)]
         Natural chromosome order for pairs flipping
+  - update_readgroups:
+      type: boolean
+      description: |
+        Boolean controling whether the readgroups should be added or updated
+        after chromap alignment
 output:
   - meta:
       type: map

subworkflows/nf-core/fastq_align_chromap/tests/main.nf.test

@@ -10,6 +10,7 @@ nextflow_workflow {
     tag "chromap"
     tag "chromap/chromap"
     tag "chromap/index"
+    tag "picard/addorreplacereadgroups"
     tag "fastq_align_chromap"
     tag "subworkflows/fastq_align_chromap"
     tag "subworkflows/bam_sort_stats_samtools"
@@ -46,16 +47,18 @@ nextflow_workflow {
                 input[4] = []
                 input[5] = []
                 input[6] = []
+                input[7] = false
                 """
             }
         }
         then {
             assertAll(
                 { assert workflow.success },
-                { assert snapshot(workflow.out).match() }
+                { assert snapshot(sanitizeOutput(workflow.out)).match() }
             )
         }
     }
+
     test("test_fastq_align_chromap_paired_end") {
         when {
             workflow {
@@ -77,13 +80,77 @@ nextflow_workflow {
                 input[4] = []
                 input[5] = []
                 input[6] = []
+                input[7] = false
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(sanitizeOutput(workflow.out)).match() }
+            )
+        }
+    }
+
+    test("test_fastq_align_chromap_single_end_add_readgroups") {
+        when {
+            workflow {
+                """
+                input[0] = [
+                    [id:'test', single_end:true],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists:true)
+                ]
+                input[1] = CHROMAP_INDEX.out.index
+                input[2] = Channel.of([
+                    [id:'test'],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists:true),
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta.fai', checkIfExists:true)
+                ])
+                input[3] = []
+                input[4] = []
+                input[5] = []
+                input[6] = []
+                input[7] = true
+                """
+            }
+        }
+        then {
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(sanitizeOutput(workflow.out)).match() }
+            )
+        }
+    }
+
+    test("test_fastq_align_chromap_paired_end_add_readgroups") {
+        when {
+            workflow {
+                """
+                input[0] = [
+                    [id:'test', single_end:false],
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists:true),
+                        file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists:true)
+                    ]
+                ]
+                input[1] = CHROMAP_INDEX.out.index
+                input[2] = Channel.of([
+                    [id:'test'],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists:true),
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta.fai', checkIfExists:true)
+                ])
+                input[3] = []
+                input[4] = []
+                input[5] = []
+                input[6] = []
+                input[7] = true
                 """
             }
         }
         then {
             assertAll(
                 { assert workflow.success },
-                { assert snapshot(workflow.out).match() }
+                { assert snapshot(sanitizeOutput(workflow.out)).match() }
             )
         }
     }
@@ -110,13 +177,14 @@ nextflow_workflow {
                 input[4] = []
                 input[5] = []
                 input[6] = []
+                input[7] = false
                 """
             }
         }
         then {
             assertAll(
                 { assert workflow.success },
-                { assert snapshot(workflow.out).match() }
+                { assert snapshot(sanitizeOutput(workflow.out)).match() }
             )
         }
     }