change collate step to collate by species

src/main.nf

@@ -3,7 +3,7 @@ nextflow.enable.dsl=2
 /*
 Testing pipeline for marseq scRNASeq analysis
 */
-params.kmer_size = 31
+params.kmer_size = 12
 
 include { SPLIT } from "./modules/split"
 include { FASTKMERS } from "./modules/fastkmers"
@@ -24,5 +24,5 @@ workflow {
   SPLIT(fastq.r1.mix(fastq.r2))
   FASTKMERS(SPLIT.out.fastq.transpose())
   MERGEKMER(FASTKMERS.out.csv.groupTuple())
-  COLLATEKMER(MERGEKMER.out.csv.map{it -> it[1]}.collect())
+  COLLATEKMER(MERGEKMER.out.csv.map{it -> [it[0].specie, it[1]] }.groupTuple())
 }

src/modules/fastkmers.nf

 process FASTKMERS {
     tag "$meta.id"
     label 'big_mem_mono_cpus'
-    publishDir "results/${meta.specie}/${meta.sex}/${meta.read}/", mode: 'copy'
 
     container "lbmc/fastkmers:025efdf"
 

src/modules/kmc.nf

@@ -4,7 +4,6 @@
 process KMC {
     tag "$meta.id"
     label 'process_single'
-    publishDir "results/${meta.specie}/${meta.sex}/${meta.read}/", mode: 'copy'
 
     container "lbmc/kmc:3.2.2"
 

src/modules/mergekmer.nf

 process MERGEKMER {
     tag "$meta.id"
     label 'big_mem_mono_cpus'
-    publishDir "results/${meta.specie}/${meta.sex}/${meta.read}/", mode: 'copy'
 
     container "lbmc/mergekmer:0.1.2"
 
@@ -26,14 +25,14 @@ process MERGEKMER {
 }
 
 process COLLATEKMER {
-    tag "$csv"
+    tag "$specie"
     label 'big_mem_mono_cpus'
-    publishDir "results/", mode: 'copy'
+    publishDir "results/${specie}/", mode: 'copy'
 
     container "lbmc/mergekmer:0.1.2"
 
     input:
-    path(csv)
+    tuple val(specie), path(csv)
 
     output:
     path("*.csv"), emit: csv
@@ -42,7 +41,7 @@ process COLLATEKMER {
     script:
     def args = task.ext.args ?: ''
     """
-    mergekmer --csv ${csv} --output fusion.csv --collate
+    mergekmer --csv ${csv} --output ${specie}.csv --collate
 
 
     cat <<-END_VERSIONS > versions.yml