enhance module fastp: add save_merged (#598) (#614)

* enhance module fastp: add `save_merged` (#598)

* removed md5sum checks from log and json

modules/fastp/main.nf

@@ -21,14 +21,16 @@ process FASTP {
     input:
     tuple val(meta), path(reads)
     val   save_trimmed_fail
+    val   save_merged
 
     output:
-    tuple val(meta), path('*.trim.fastq.gz'), emit: reads
-    tuple val(meta), path('*.json')         , emit: json
-    tuple val(meta), path('*.html')         , emit: html
-    tuple val(meta), path('*.log')          , emit: log
-    path '*.version.txt'                    , emit: version
-    tuple val(meta), path('*.fail.fastq.gz'), optional:true, emit: reads_fail
+    tuple val(meta), path('*.trim.fastq.gz')  , emit: reads
+    tuple val(meta), path('*.json')           , emit: json
+    tuple val(meta), path('*.html')           , emit: html
+    tuple val(meta), path('*.log')            , emit: log
+    path '*.version.txt'                      , emit: version
+    tuple val(meta), path('*.fail.fastq.gz')  , optional:true, emit: reads_fail
+    tuple val(meta), path('*.merged.fastq.gz'), optional:true, emit: reads_merged
 
     script:
     // Added soft-links to original fastqs for consistent naming in MultiQC
@@ -50,7 +52,8 @@ process FASTP {
         echo \$(fastp --version 2>&1) | sed -e "s/fastp //g" > ${software}.version.txt
         """
     } else {
-        def fail_fastq = save_trimmed_fail ? "--unpaired1 ${prefix}_1.fail.fastq.gz --unpaired2 ${prefix}_2.fail.fastq.gz" : ''
+        def fail_fastq  = save_trimmed_fail ? "--unpaired1 ${prefix}_1.fail.fastq.gz --unpaired2 ${prefix}_2.fail.fastq.gz" : ''
+        def merge_fastq = save_merged ? "-m --merged_out ${prefix}.merged.fastq.gz" : ''
         """
         [ ! -f  ${prefix}_1.fastq.gz ] && ln -s ${reads[0]} ${prefix}_1.fastq.gz
         [ ! -f  ${prefix}_2.fastq.gz ] && ln -s ${reads[1]} ${prefix}_2.fastq.gz
@@ -62,6 +65,7 @@ process FASTP {
             --json ${prefix}.fastp.json \\
             --html ${prefix}.fastp.html \\
             $fail_fastq \\
+            $merge_fastq \\
             --thread $task.cpus \\
             --detect_adapter_for_pe \\
             $options.args \\

modules/fastp/meta.yml

@@ -30,7 +30,7 @@ output:
         e.g. [ id:'test', single_end:false ]
   - reads:
       type: file
-      description: The trimmed/modified fastq reads
+      description: The trimmed/modified/unmerged fastq reads
       pattern: "*trim.fastq.gz"
   - json:
       type: file
@@ -52,6 +52,10 @@ output:
       type: file
       description: Reads the failed the preprocessing
       pattern: "*fail.fastq.gz"
+  - reads_merged:
+      type: file
+      description: Reads that were successfully merged
+      pattern: "*.{merged.fastq.gz}"
 authors:
   - "@drpatelh"
   - "@kevinmenden"

tests/modules/fastp/main.nf

@@ -12,8 +12,9 @@ workflow test_fastp_single_end {
               [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) ]
             ]
     save_trimmed_fail = false
+    save_merged       = false
 
-    FASTP ( input, save_trimmed_fail )
+    FASTP ( input, save_trimmed_fail, save_merged )
 }
 
 //
@@ -25,8 +26,9 @@ workflow test_fastp_paired_end {
                 file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ]
             ]
     save_trimmed_fail = false
+    save_merged       = false
 
-    FASTP ( input, save_trimmed_fail )
+    FASTP ( input, save_trimmed_fail, save_merged )
 }
 
 //
@@ -37,8 +39,9 @@ workflow test_fastp_single_end_trim_fail {
               [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) ]
             ]
     save_trimmed_fail = true
+    save_merged       = false
 
-    FASTP ( input, save_trimmed_fail )
+    FASTP ( input, save_trimmed_fail, save_merged )
 }
 
 //
@@ -50,6 +53,21 @@ workflow test_fastp_paired_end_trim_fail {
                 file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ]
             ]
     save_trimmed_fail = true
+    save_merged       = false
 
-    FASTP ( input, save_trimmed_fail )
+    FASTP ( input, save_trimmed_fail, save_merged )
+}
+
+//
+// Test with paired-end data with merging
+//
+workflow test_fastp_paired_end_merged {
+    input = [ [ id:'test', single_end:false ], // meta map
+              [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+                file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ]
+            ]
+    save_trimmed_fail = false
+    save_merged       = true
+
+    FASTP ( input, save_trimmed_fail, save_merged )
 }

tests/modules/fastp/test.yml

@@ -81,3 +81,28 @@
       md5sum: e62ff0123a74adfc6903d59a449cbdb0
     - path: output/fastp/test_2.fail.fastq.gz
       md5sum: f52309b35a7c15cbd56a9c3906ef98a5
+
+- name: fastp test_fastp_paired_end_merged
+  command: nextflow run tests/modules/fastp -entry test_fastp_paired_end_merged -c tests/config/nextflow.config
+  tags:
+    - fastp
+  files:
+    - path: output/fastp/test.fastp.html
+      contains:
+        - "<div id='After_filtering__merged__quality'>"
+    - path: output/fastp/test.fastp.json
+      contains:
+        - '"merged_and_filtered": {'
+        - '"total_reads": 75'
+        - '"total_bases": 13683'
+    - path: output/fastp/test.fastp.log
+      contains:
+        - "Merged and filtered:"
+        - "total reads: 75"
+        - "total bases: 13683"
+    - path: output/fastp/test.merged.fastq.gz
+      md5sum: ce88539076ced5aff11f866836ea1f40
+    - path: output/fastp/test_1.trim.fastq.gz
+      md5sum: 65d75c13abbfbfd993914e1379634100
+    - path: output/fastp/test_2.trim.fastq.gz
+      md5sum: 0d87ce4d8ef29fb35f337eb0f6c9fcb4