Add porechop and compress all fastq files during the workflow.

src/.docker_modules/porechop/0.2.4/Dockerfile

@@ -30,6 +30,4 @@ RUN python3 setup.py install && \
     apt remove --purge --yes git build-essential && \
     apt autoremove --purge --yes
 
-# Set entrypoint so container can be used as executable
-ENTRYPOINT ["porechop"]
+CMD ["bash"]
\ No newline at end of file
-CMD ["-h"]
\ No newline at end of file

src/.docker_modules/porechop/0.2.4/docker_init.sh

@@ -7,4 +7,4 @@
 # docker pull xgrand/porechop:0.2.4
 docker build src/.docker_modules/porechop/0.2.4 -t 'xgrand/porechop:0.2.4'
 docker push xgrand/porechop:0.2.4
-docker buildx build --platform linux/amd64,linux/arm64 -t "xgrand/porechop:0.2.4" --push src/.docker_modules/porechop/0.2.4
+# docker buildx build --platform linux/amd64,linux/arm64 -t "xgrand/porechop:0.2.4" --push src/.docker_modules/porechop/0.2.4
\ No newline at end of file

src/bolero.nf

@@ -104,7 +104,8 @@ params.kit_barcoding = ""
 params.basecalling_out = "01_basecalling/"
 params.barcoding_out = "02_barcoding/"
 params.fastq_out = "03_fastq/"
-params.seqkit_grep_out = "03_fastq/"
+params.seqkit_grep_out = "14_seqkit/"
+params.porechop_out = "15_porechop/"
 params.cutadapt_out = "04_cutadapt/"
 params.minimap2_genome_out = "05_minimap2/"
 params.start_position_counts_out = "06_start_positions/"
@@ -186,6 +187,7 @@ include { start_position_individuals } from "./nf_modules/start_positions/main.n
 include { jwr_checker } from "./nf_modules/nanosplicer/main.nf"
 include { junctions_nanosplicer } from "./nf_modules/junction_nanosplicer/main.nf"
 include { rna_count } from "./nf_modules/rna_count/main.nf"
+include { porechop } from "./nf_modules/porechop/main.nf"
 
 /*
  ****************************************************************
@@ -244,9 +246,13 @@ workflow {
 
   //Filtration (seqkit_grep looks for the 5'RACE and the gsp patterns in the reads to keep only mature ARNs)
   seqkit_grep(concatenate.out.merged_fastq, params.adapt, params.gsp)
+
+  //Trimming with porechop
+  porechop(seqkit_grep.out.filtered_fastq)
   
   //Cut of the 5'RACE sequence
-  cut_5pRACE(seqkit_grep.out.filtered_fastq, params.adapt)
+  cut_5pRACE(porechop.out.porechoped_fastq, params.adapt)
+  //cut_5pRACE(seqkit_grep.out.filtered_fastq, params.adapt)
 
   //########################## MAPPING ##########################
 

src/nf_modules/cutadapt/main.nf

@@ -15,12 +15,12 @@ process cut_5pRACE {
   val(adapt)
 
   output:
-  tuple val(barcode), path("${barcode}_merged_porechoped_cut_fastq.fastq"), emit: fastq_cutadapt
+  tuple val(barcode), path("${barcode}_merged_porechoped_cut.fastq.gz"), emit: fastq_cutadapt
 
   """
   cutadapt -e 0.2 -g ${adapt} \
    --revcomp \
-   -o "${barcode}_merged_porechoped_cut_fastq.fastq" \
+   -o "${barcode}_merged_porechoped_cut.fastq.gz" \
    ${fastq}
   """
 }
\ No newline at end of file

src/nf_modules/minimap2/main.nf

@@ -108,6 +108,6 @@ process hbv_genome {
   mkdir ${barcode}
   cd ${barcode}/
   minimap2 ${params.mapping_hbv_genome} -t ${task.cpus} -K ${memory} ../${genome} ../${fastq} |
-    samtools view -Shb - > ${barcode}_res.bam
+    samtools view -Shb -F4 -F2048 -F2064 - > ${barcode}_res.bam
   """
 }
\ No newline at end of file

src/nf_modules/porechop/main.nf

 version = "0.2.4"
 container_url = "xgrand/porechop:${version}"
 
+params.porechop_out = ""
 process porechop {
     container = "${container_url}"
     label "small_mem_multi_cpus"
-    tag "$file_id"
+    tag "$barcode"
     if (params.porechop_out != "") {
       publishDir "results/${params.porechop_out}", mode: 'copy'
     }
 
   input:
-    path(merged_fastq)
+    tuple val(barcode), path(fastq)
 
   output:
-    path("*"), emit: porechoped_fastq
+    tuple val(barcode), path("*"), emit: porechoped_fastq
   script:
 """
-porechop -i ${merged_fastq} -o merged_porechoped.fastq --threads ${task.cpus}
+porechop --input ${fastq} -o ${barcode}_merged_porechoped.fastq.gz --threads ${task.cpus}
 """
 }
\ No newline at end of file

src/nf_modules/seqkit/main.nf

@@ -40,11 +40,11 @@ process seqkit_grep {
     val(gsp)
 
   output:
-    tuple val(barcode), path("${barcode}/${barcode}_390bp_filtered_5RACE_GSP.fastq"), emit: filtered_fastq
+    tuple val(barcode), path("${barcode}/${barcode}_390bp_filtered_5RACE_GSP.fastq.gz"), emit: filtered_fastq
     path("${barcode}/*.csv")
     path("${barcode}/*.txt")
-    path("${barcode}/${barcode}_filtered_5RACE.fastq")
-    path("${barcode}/${barcode}_filtered_5RACE_GSP.fastq")
+    path("${barcode}/${barcode}_filtered_5RACE.fastq.gz")
+    path("${barcode}/${barcode}_filtered_5RACE_GSP.fastq.gz")
 
   script:
     lgadapt = Math.round(adapt.size().div(10))
@@ -56,13 +56,14 @@ process seqkit_grep {
     echo "mismatch allowed to Gene Specific primer:  ${lggsp}" >> mismatch.txt
     echo ${adapt} > adapt.txt
     echo ${gsp} > gsp.txt
-    seqkit grep -i -f adapt.txt -m ${lgadapt} ../${fastq} -o ${barcode}_filtered_5RACE.fastq -j ${task.cpus}
-    seqkit grep -i -f gsp.txt -m ${lggsp} ${barcode}_filtered_5RACE.fastq -o ${barcode}_filtered_5RACE_GSP.fastq -j ${task.cpus}
-    seqkit seq --min-len 390 --remove-gaps ${barcode}_filtered_5RACE_GSP.fastq -j ${task.cpus} > ${barcode}_390bp_filtered_5RACE_GSP.fastq
+    seqkit grep -i -f adapt.txt -m ${lgadapt} ../${fastq} -o ${barcode}_filtered_5RACE.fastq.gz -j ${task.cpus}
+    seqkit grep -i -f gsp.txt -m ${lggsp} ${barcode}_filtered_5RACE.fastq.gz -o ${barcode}_filtered_5RACE_GSP.fastq.gz -j ${task.cpus}
+    seqkit seq --min-len 390 --remove-gaps ${barcode}_filtered_5RACE_GSP.fastq.gz -j ${task.cpus} > ${barcode}_390bp_filtered_5RACE_GSP.fastq
+    gzip ${barcode}_390bp_filtered_5RACE_GSP.fastq
     seqkit stats ../${fastq} -T -j ${task.cpus} > ${barcode}_seq_stats.csv
-    seqkit stats ${barcode}_filtered_5RACE.fastq -T -j ${task.cpus} | tail -n1 >> ${barcode}_seq_stats.csv
-    seqkit stats ${barcode}_filtered_5RACE_GSP.fastq -T -j ${task.cpus} | tail -n1 >> ${barcode}_seq_stats.csv
-    seqkit stats ${barcode}_390bp_filtered_5RACE_GSP.fastq -T -j ${task.cpus} | tail -n1 >> ${barcode}_seq_stats.csv
+    seqkit stats ${barcode}_filtered_5RACE.fastq.gz -T -j ${task.cpus} | tail -n1 >> ${barcode}_seq_stats.csv
+    seqkit stats ${barcode}_filtered_5RACE_GSP.fastq.gz -T -j ${task.cpus} | tail -n1 >> ${barcode}_seq_stats.csv
+    seqkit stats ${barcode}_390bp_filtered_5RACE_GSP.fastq.gz -T -j ${task.cpus} | tail -n1 >> ${barcode}_seq_stats.csv
     """
 }
 
@@ -91,23 +92,3 @@ process concatenate {
     gzip ${barcode}_merged.fastq
     """
 }
-
-process concatenate_BC {
-  container = "${container_url}"
-  label "big_mem_multi_cpus"
-  tag "${barcode}"
-  if (params.fastq_out != "") {
-    publishDir "results/${params.fastq_out}", mode: 'copy'
-  }
-
-  input:
-    path(path)
-
-  output:
-    path("test.txt")
-
-  script:
-    """
-    echo ${path} \$(readlink -f ${path}) > test.txt
-    """
-}
\ No newline at end of file