alntools: separate transcript length computation

src/nf_modules/alntools/main.nf

@@ -13,16 +13,38 @@ process bam2ec {
 
   input:
     tuple val(file_id), path(bam), path(bam_idx)
-    tuple val(gtf_id), path(gtf)
+    tuple val(transcripts_lengths_id), path(transcripts_lengths)
 
   output:
     tuple val(file_id), path("${bam.simpleName}.bin"), emit: bin
-    tuple val(gtf_id), path("${gtf.simpleName}_transcripts_lengths.tsv"), emit: tsv
+    tuple val(gtf_id), path("${transcripts_lengths}"), emit: tsv
 
   script:
 """
 cp ${bam} file_bam.bam
 cp ${bam_idx} file_bam.bam.bai
+alntools bam2ec ${params.bam2ec} -t ${transcripts_lengths} file_bam.bam ${bam.simpleName}.bin
+"""
+}
+
+params.gtf_to_transcripts_lengths = ""
+params.gtf_to_transcripts_lengths_out = ""
+process gtf_to_transcripts_lengths {
+  container = "${container_url}"
+  label "big_mem_mono_cpus"
+  tag "$file_id"
+  if (params.gtf_to_transcripts_lengths != "") {
+    publishDir "results/${params.gtf_to_transcripts_lengths}", mode: 'copy'
+  }
+
+  input:
+    tuple val(file_id), path(gtf)
+
+  output:
+    tuple val(file_id), path("${gtf.simpleName}_transcripts_lengths.tsv"), emit: tsv
+
+  script:
+"""
 awk -F"[\\t;]" '
 \$3=="exon" {
         ID=gensub(/transcript_id \\"(.*)\\"/, "\\\\1", "g", \$11); 
@@ -33,6 +55,5 @@ END{
         {print i"\\t"LEN[i]}
     }
 ' ${gtf} > ${gtf.simpleName}_transcripts_lengths.tsv
-alntools bam2ec ${params.bam2ec} -t ${gtf.simpleName}_transcripts_lengths.tsv file_bam.bam ${bam.simpleName}.bin
 """
-}
\ No newline at end of file
+}

src/nf_modules/bioawk/main.nf

+version = "1.0"
+container_url = "lbmc/bioawk:${version}"
+
+params.fasta_to_transcripts_lengths = ""
+params.fasta_to_transcripts_lengths_out = ""
+process fasta_to_transcripts_lengths {
+  container = "${container_url}"
+  label "big_mem_mono_cpus"
+  tag "$file_id"
+  if (params.fasta_to_transcripts_lengths_out != "") {
+    publishDir "results/${params.fasta_to_transcripts_lengths_out}", mode: 'copy'
+  }
+
+  input:
+    tuple val(file_id), path(fasta)
+
+  output:
+    tuple val(file_id), path("${fasta.simpleName}_transcripts_lengths.tsv"), emit: tsv
+
+  script:
+"""
+bioawk -c fastx '{print \$name length(\$seq)}' ${fasta} > ${fasta.simpleName}_transcripts_lengths.tsv
+"""
+}
\ No newline at end of file