"RNAseq_trimming"

src/RNAseq.config

@@ -11,6 +11,11 @@ profiles {
         cpus = 4
         container = "lbmc/urqt:d62c1f8"
       }
+      withName: fasta_from_bed {
+     container = "lbmc/bedtools:2.25.0"
+     cpus = 1
+   }
+
     }
   }
   singularity {

src/RNAseq.nf

 log.info "fastq files : ${params.fastq}"
+log.info "fasta file : ${params.fasta}"
+log.info "bed file : ${params.bed}"
 
 Channel
   .fromFilePairs( params.fastq )
   .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
   .set { fastq_files }
 
+  params.fasta = "$baseDir/data/fasta/*.fasta"
+  params.bed = "$baseDir/data/annot/*.bed"
+
+  Channel
+    .fromPath( params.fasta )
+    .ifEmpty { error "Cannot find any fasta files matching: ${params.fasta}" }
+    .set { fasta_files }
+  Channel
+    .fromPath( params.bed )
+    .ifEmpty { error "Cannot find any bed files matching: ${params.bed}" }
+    .set { bed_files }
+
 process adaptor_removal {
   tag "$pair_id"
   publishDir "results/fastq/adaptor_removal/", mode: 'copy'
@@ -28,7 +42,7 @@ process trimming {
   publishDir "results/fastq/trimming/", mode: 'copy'
 
   input:
-  set pair_id, file(reads) from fastq_files
+  set pair_id, file(reads) from fastq_files_cut
 
   output:
   set pair_id, "*_trim_R{1,2}.fastq.gz" into fastq_files_trim
@@ -41,3 +55,21 @@ UrQt --t 20 --m ${task.cpus} --gz \
 > ${pair_id}_trimming_report.txt
 """
 }
+
+process fasta_from_bed {
+  tag "${bed.baseName}"
+  publishDir "results/fasta/", mode: 'copy'
+
+  input:
+  file fasta from fasta_files
+  file bed from bed_files
+
+  output:
+  file "*_extracted.fasta" into fasta_files_extracted
+
+  script:
+"""
+bedtools getfasta -name \
+-fi ${fasta} -bed ${bed} -fo ${bed.baseName}_extracted.fasta
+"""
+}