add sample_reads.nf: subworkflow to make number of reads equal between Male and Female

src/modules/sample_reads.nf

@@ -3,13 +3,45 @@ workflow SUBSAMPLE_READ {
       fastq
     main:
       COUNT_READS(fastq)
-      COUNT_READS.out.fastq
-        .groupTuple(by: [2, 3], sort: true)
-        .view()
-      SAMPLE_READS(fastq_to_sample)
+      SORT_READS(
+        COUNT_READS.out.count
+            .map{
+                it ->
+                [
+                    it[0].specie,
+                    it[1]
+                ]
+            }
+            .groupTuple()
+      )
+      SAMPLE_READS(SORT_READS.out.count
+        .cross(
+            fastq
+                .map{
+                    item ->
+                    [
+                        item[0].specie,
+                        item
+                    ]
+                }
+        )
+        .map{
+            it -> 
+            [
+                it[1][1][0],
+                it[1][1][1],
+                it[0][1]
+            ]
+        }
+        .join(
+            COUNT_READS.out.count
+        )
+      )
     emit:
-      fastq: SAMPLE_READS.out.reads
-      version: SAMPLE_READS.out.version.mix(COUNT_READS.version)
+      fastq = SAMPLE_READS.out.reads
+      version = COUNT_READS.out.versions
+        .mix(SAMPLE_READS.out.versions)
+        .mix(SORT_READS.out.versions)
 }
 
 process COUNT_READS {
@@ -22,13 +54,37 @@ process COUNT_READS {
     tuple val(meta), path(fastq)
 
     output:
-    tuple val(meta), stdout, path("*.fastq.gz"), emit: fastq
+    tuple val(meta), path("${meta.id}.csv"), emit: count 
     path "versions.yml"           , emit: versions
 
     script:
     def args = task.ext.args ?: ''
     """
-    zcat ${fastq} | wc -l 
+    zcat ${fastq} | wc -l > ${meta.id}.csv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        split: v1.35.0
+    END_VERSIONS
+    """
+}
+
+process SORT_READS {
+    tag "$specie"
+    label 'small_mem_mono_cpus'
+    container "lbmc/alpine:3.17"
+
+    input:
+    tuple val(specie), path(count)
+
+    output:
+    tuple val(specie), path("count.csv"), emit: count
+    path "versions.yml"           , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    cat ${count} | sort -u -k1n | head -n 1 > count.csv
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -40,14 +96,15 @@ process COUNT_READS {
 process SAMPLE_READS {
     tag "$meta.id"
     label 'small_mem_mono_cpus'
+    debug true
 
-    container "quay.io/biocontainers/seqtk:1.3--h5bf99c6_3"
+    container "lbmc/alpine:3.17"
 
     input:
-    tuple val(meta), path(reads), val(sample_size)
+    tuple val(meta), path(reads), path(sample_size), path(read_number)
 
     output:
-    tuple val(meta), path("*.fastq.gz"), emit: reads
+    tuple val(meta), path("sample_${reads}"), emit: reads
     path "versions.yml"                , emit: versions
 
     when:
@@ -63,15 +120,11 @@ process SAMPLE_READS {
         error "SEQTK/SAMPLE must have a sample_size value included"
     }
     """
-    printf "%s\\n" $reads | while read f;
-    do
-        seqtk \\
-            sample \\
-            $args \\
-            \$f \\
-            $sample_size \\
-            | gzip --no-name > ${prefix}_\$(basename \$f)
-    done
+    if [\$(cat $sample_size | tr -d '\\n') -eq \$(cat $read_number | tr -d '\\n')]; then
+        ln -s ${reads} sample_${reads}
+    else
+        zcat ${reads} | head -n \$(cat $sample_size | tr -d '\\n') | gzip -c > sample_${reads}
+    fi
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":