From 6a48c301c4e7d7f77f57d2df8962a6afb8965c35 Mon Sep 17 00:00:00 2001
From: aliarifki <aliarifki@outlook.fr>
Date: Wed, 14 Jun 2023 10:10:44 +0200
Subject: [PATCH] Ajout des barcodes
---
src/bolero.nf | 45 ++++++++++-----------
src/nf_modules/cutadapt/main.nf | 8 ++--
src/nf_modules/junction_nanosplicer/main.nf | 17 ++++----
src/nf_modules/minimap2/main.nf | 11 +++--
src/nf_modules/nanosplicer/main.nf | 26 ++++++++++++
src/nf_modules/rna_count/main.nf | 16 ++++----
src/nf_modules/samtools/main.nf | 24 ++++++-----
src/nf_modules/seqkit/main.nf | 39 ++++++++++--------
src/nf_modules/start_positions/main.nf | 19 +++++----
9 files changed, 124 insertions(+), 81 deletions(-)
create mode 100644 src/nf_modules/nanosplicer/main.nf
diff --git a/src/bolero.nf b/src/bolero.nf
index 3ff3c53..c9851d4 100755
--- a/src/bolero.nf
+++ b/src/bolero.nf
@@ -129,9 +129,9 @@ Channel
.set { input }
Channel
- .of( params.adapt )
- .ifEmpty { error "No adapter sequence defined." }
- .set { adapt }
+ .of( params.adapt )
+ .ifEmpty { error "No adapter sequence defined." }
+ .set { adapt }
Channel
.fromPath( params.genome )
@@ -143,7 +143,10 @@ Channel
.ifEmpty { error "No annotation defined, a gtf file describing transcripts and splice variants." }
.set { gtf }
-// .map( it -> [it.baseName, it])
+Channel
+ .fromPath(params.input+'*/', type: 'dir')
+ .map(it -> [it.baseName, it])
+ .set{barcodes}
/*
****************************************************************
@@ -161,10 +164,8 @@ if(!params.skipBC) {
}
}
-// Replace concatenate by seqkit fct to parallelization:
+include { barecode } from "./nf_modules/barecode/main.nf"
include { concatenate } from "./nf_modules/seqkit/main.nf"
-//include { concatenate } from "./nf_modules/concatenate/main.nf"
-
include { cut_5pRACE } from "./nf_modules/cutadapt/main.nf"
include { hbv_genome } from "./nf_modules/minimap2/main.nf"
include { seqkit_grep } from "./nf_modules/seqkit/main.nf"
@@ -178,9 +179,6 @@ include { junctions_nanosplicer } from "./nf_modules/junction_nanosplicer/main.n
include { rna_count } from "./nf_modules/rna_count/main.nf"
-// creation des fonctions NanoSplicer:
-// include { jwr_check } from "./nf_modules/nanosplicer/main.nf"
-
/*
****************************************************************
Workflow
@@ -189,42 +187,41 @@ include { rna_count } from "./nf_modules/rna_count/main.nf"
workflow {
+
//######################## BASECALLING ########################
- if(params.skipBC) {
- concatenate(params.input)
- // Replace by seqkit scat to parallelization
+ if(params.skipBC) { // we take fastq files as input and skip basecalling
+ concatenate(barcodes)
}
- else {
+
+ //il reste à adapter ça
+ else { // we take fast5 files as input and proceed to basecalling with guppy
if(params.gpu_mode) {
basecall_fast5_gpu(input)
concatenate(basecall_fast5_gpu.out.pass)
- // Replace by seqkit scat to parallelization
}
else {
basecall_fast5_cpu(input)
concatenate(basecall_fast5_cpu.out.pass)
- // Replace by seqkit scat to parallelization
}
}
+
+
+
//####################### PREPROCESSING #######################
-
-
-
+
+
//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)
//Cut of the 5'RACE sequence
cut_5pRACE(seqkit_grep.out.filtered_fastq, params.adapt)
-
-
//########################## MAPPING ##########################
-
- hbv_genome(cut_5pRACE.out.fastq_cutadapt, genome)
+ hbv_genome(cut_5pRACE.out.fastq_cutadapt, genome.collect())
+
sort_index_bam(hbv_genome.out.bam)
- // index_bam(sort_bam_genome.out.sorted_bam.collect())
//###################### START POSITIONS #######################
diff --git a/src/nf_modules/cutadapt/main.nf b/src/nf_modules/cutadapt/main.nf
index b7ffd3b..7c72b44 100755
--- a/src/nf_modules/cutadapt/main.nf
+++ b/src/nf_modules/cutadapt/main.nf
@@ -4,23 +4,23 @@ container_url = "xgrand/cutadapt:${version}"
process cut_5pRACE {
container = "${container_url}"
label "small_mem_mono_cpus"
- tag "cutadapt"
+ tag "${barcode}"
if (params.cutadapt_out != "") {
publishDir "results/${params.cutadapt_out}", mode: 'copy'
}
input:
- path(fastq)
+ tuple val(barcode), path(fastq)
val(adapt)
output:
- path("*_cut_*"), emit: fastq_cutadapt
+ tuple val(barcode), path("${barcode}_merged_porechoped_cut_fastq.fastq"), emit: fastq_cutadapt
"""
cutadapt -e 0.2 -g ${adapt} \
--revcomp \
- -o "merged_porechoped_cut_fastq.fastq" \
+ -o "${barcode}_merged_porechoped_cut_fastq.fastq" \
${fastq}
"""
}
\ No newline at end of file
diff --git a/src/nf_modules/junction_nanosplicer/main.nf b/src/nf_modules/junction_nanosplicer/main.nf
index 9f0a209..337ed6f 100644
--- a/src/nf_modules/junction_nanosplicer/main.nf
+++ b/src/nf_modules/junction_nanosplicer/main.nf
@@ -5,23 +5,24 @@ params.nanosplicer_out = ""
process junctions_nanosplicer{
container = "${container_url}"
label "small_mem_mono_cpus"
- tag "identification de variants d'épissage"
+ tag "${barcode}"
if (params.nanosplicer_out != "") {
publishDir "results/${params.nanosplicer_out}", mode: 'copy'
}
input:
- path(txt)
- path(csv)
+ tuple val(barcode), path(txt)
+ tuple val(barcode), path(csv)
output:
- path("Rplots.pdf")
- path("JWR_check_parsed.csv")
- path("*.png")
- path("identified_SPvariants.csv"), emit: identified_SPvariants
+ path("${barcode}/JWR_check_parsed.csv")
+ tuple val(barcode), path("${barcode}/${barcode}_identified_SPvariants.csv"), emit: identified_SPvariants
script:
"""
- Rscript /Junctions_NanoSplicer.R -c ${txt} -j ${csv}
+ mkdir ${barcode}
+ cd ${barcode}/
+ Rscript /Junctions_NanoSplicer.R -c ../${txt} -j ../${csv}
+ mv identified_SPvariants.csv ${barcode}_identified_SPvariants.csv
"""
}
\ No newline at end of file
diff --git a/src/nf_modules/minimap2/main.nf b/src/nf_modules/minimap2/main.nf
index 5e101b7..91c9193 100755
--- a/src/nf_modules/minimap2/main.nf
+++ b/src/nf_modules/minimap2/main.nf
@@ -89,22 +89,25 @@ params.mapping_hbv_genome = "-ax splice --secondary=no -G 1650 -u n --eqx"
process hbv_genome {
container = "${container_url}"
label "big_mem_multi_cpus"
+ tag "${barcode}"
if (params.minimap2_genome_out != "") {
publishDir "results/${params.minimap2_genome_out}", mode: 'copy'
}
input:
- path(fastq)
+ tuple val(barcode), path(fastq)
path(genome)
output:
- path("*"), emit: bam
+ tuple val(barcode), path("${barcode}/${barcode}_res.bam"), emit: bam
script:
memory = "${task.memory}" - ~/\s*GB/
memory = memory.toInteger() / (task.cpus + 1.0)
"""
- minimap2 ${params.mapping_hbv_genome} -t${task.cpus} -K ${memory} ${genome} ${fastq} |
- samtools view -Shb - > res.bam
+ mkdir ${barcode}
+ cd ${barcode}/
+ minimap2 ${params.mapping_hbv_genome} -t ${task.cpus} -K ${memory} ../${genome} ../${fastq} |
+ samtools view -Shb - > ${barcode}_res.bam
"""
}
\ No newline at end of file
diff --git a/src/nf_modules/nanosplicer/main.nf b/src/nf_modules/nanosplicer/main.nf
new file mode 100644
index 0000000..71908d7
--- /dev/null
+++ b/src/nf_modules/nanosplicer/main.nf
@@ -0,0 +1,26 @@
+version = "1.0"
+container_url = "xgrand/nanosplicer:${version}"
+
+params.nanosplicer_out = ""
+process jwr_checker {
+ container = "${container_url}"
+ label "big_mem_multi_cpus"
+ tag "${barcode}"
+ if (params.nanosplicer_out != "") {
+ publishDir "results/${params.nanosplicer_out}", mode: 'copy'
+ }
+
+ input:
+ tuple val(barcode), path(bam), path(index)
+
+ output:
+ tuple val(barcode), path("${barcode}/${barcode}_JWR_check.h5.csv"), emit: nanosplicer_jwr
+
+ script:
+ """
+ mkdir ${barcode}
+ cd ${barcode}/
+ python3 /NanoSplicer/bin/JWR_checker.py --output_csv ../${bam} ${barcode}_JWR_check.h5
+ """
+}
+
diff --git a/src/nf_modules/rna_count/main.nf b/src/nf_modules/rna_count/main.nf
index a2ae2ce..06afba6 100644
--- a/src/nf_modules/rna_count/main.nf
+++ b/src/nf_modules/rna_count/main.nf
@@ -5,22 +5,24 @@ params.rna_count_out = ""
process rna_count{
container = "${container_url}"
label "small_mem_mono_cpus"
- tag "RNA quantification"
+ tag "${barcode}"
if (params.rna_count_out != "") {
publishDir "results/${params.rna_count_out}", mode: 'copy'
}
input:
- path(spvariants)
- path(classification)
+ tuple val(barcode), path(spvariants)
+ tuple val(barcode), path(classification)
output:
- path("*.csv")
- path("*.pdf")
- path("*.png")
+ path("${barcode}/*.csv")
+ path("${barcode}/*.pdf")
+ path("${barcode}/*.png")
script:
"""
- Rscript /HBV_RNAs_count.R -s ${spvariants} -c ${classification}
+ mkdir ${barcode}
+ cd ${barcode}/
+ Rscript /HBV_RNAs_count.R -s ../${spvariants} -c ../${classification}
"""
}
diff --git a/src/nf_modules/samtools/main.nf b/src/nf_modules/samtools/main.nf
index 0b48cd5..d44804b 100755
--- a/src/nf_modules/samtools/main.nf
+++ b/src/nf_modules/samtools/main.nf
@@ -24,21 +24,23 @@ samtools sort -@ ${task.cpus} ${bam} -O BAM -o ${bam.simpleName}_sorted.bam
params.start_position_counts_out = ""
process start_position_counts {
- tag "Start positions count"
+ tag "${barcode}"
label "big_mem_multi_cpus"
publishDir "results/${params.start_position_counts_out}", mode: 'copy'
input:
- tuple path(bam), path(index)
+ tuple val(barcode), path(bam), path(index)
output:
- path "*", emit: count
+ tuple val(barcode), path("${barcode}/${barcode}_start_positions_counts.txt"), emit: count
script:
"""
-samtools view -F 260 ${bam} |
+mkdir ${barcode}
+cd ${barcode}/
+samtools view -F 260 ../${bam} |
cut -f 1,4 |
- sort > Start_positions_counts.txt
+ sort > ${barcode}_start_positions_counts.txt
"""
}
@@ -67,20 +69,22 @@ params.indexed_bam_out =""
process sort_index_bam {
container = "${container_url}"
label "big_mem_multi_cpus"
- tag "sorting"
+ tag "${barcode}"
if (params.indexed_bam_out != "") {
publishDir "results/${params.indexed_bam_out}", mode: 'copy'
}
input:
- path(bam)
+ tuple val(barcode), path(bam)
output:
- tuple path("*sorted.bam"), path("*.bai"), emit: indexed_bam
+ tuple val(barcode), path("${barcode}/*sorted.bam"), path("${barcode}/*.bai"), emit: indexed_bam
script:
"""
-samtools sort -@ ${task.cpus} ${bam} -o ${bam.simpleName}_sorted.bam
-samtools index -@ ${task.cpus} ${bam.simpleName}_sorted.bam
+mkdir ${barcode}
+cd ${barcode}/
+samtools sort -@ ${task.cpus} ../${bam} -o ${barcode}_sorted.bam
+samtools index -@ ${task.cpus} ${barcode}_sorted.bam
"""
}
\ No newline at end of file
diff --git a/src/nf_modules/seqkit/main.nf b/src/nf_modules/seqkit/main.nf
index e6d7e6b..683c924 100755
--- a/src/nf_modules/seqkit/main.nf
+++ b/src/nf_modules/seqkit/main.nf
@@ -29,35 +29,37 @@ params.seqkit_grep_out = ""
process seqkit_grep {
container = "${container_url}"
label "small_mem_multi_cpus"
- tag "Filter_reads"
+ tag "${barcode}"
if (params.seqkit_grep_out != "") {
publishDir "results/${params.seqkit_grep_out}", mode: 'copy'
}
input:
- path(fastq)
+ tuple val(barcode), path(fastq)
val(adapt)
val(gsp)
output:
- path("filtered_5RACE_GSP.fastq"), emit: filtered_fastq
- path("seq_stats.csv")
- path("*.txt")
- path("filtered_5RACE.fastq")
+ tuple val(barcode), path("${barcode}/${barcode}_filtered_5RACE_GSP.fastq"), emit: filtered_fastq
+ path("${barcode}/*.csv")
+ path("${barcode}/*.txt")
+ path("${barcode}/${barcode}_filtered_5RACE.fastq")
script:
lgadapt = Math.round(adapt.size().div(10))
lggsp = Math.round(gsp.size().div(10))
"""
+ mkdir ${barcode}
+ cd ${barcode}/
echo "mismatch allowed to 5'RACE adapter: ${lgadapt}" > mismatch.txt
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 filtered_5RACE.fastq -j ${task.cpus}
- seqkit grep -i -f gsp.txt -m ${lggsp} filtered_5RACE.fastq -o filtered_5RACE_GSP.fastq -j ${task.cpus}
- seqkit stats ${fastq} -T -j ${task.cpus} > seq_stats.csv
- seqkit stats filtered_5RACE.fastq -T -j ${task.cpus} | tail -n1 >> seq_stats.csv
- seqkit stats filtered_5RACE_GSP.fastq -T -j ${task.cpus} | tail -n1 >> seq_stats.csv
+ 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 ${task.cpus}
+ seqkit stats ../${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 >> ${barcode}_seq_stats.csv
"""
}
@@ -65,21 +67,24 @@ params.fastq_out = ""
process concatenate {
container = "${container_url}"
label "big_mem_multi_cpus"
- tag "Concatenate_reads"
+ tag "${barcode}"
if (params.fastq_out != "") {
publishDir "results/${params.fastq_out}", mode: 'copy'
}
input:
- path fastq
+ tuple val(barcode), path(fastq)
output:
- path "merged.fastq.gz", emit: merged_fastq
+ tuple val(barcode), path("${barcode}/${barcode}_merged.fastq.gz"), emit: merged_fastq
script:
"""
- path=\$(readlink -f ${fastq})
- seqkit scat -j ${task.cpus} -f \${path} --gz-only > merged.fastq
- gzip merged.fastq
+ mv ${fastq} path_${fastq}
+ mkdir ${barcode}
+ cd ${barcode}/
+ path=\$(readlink -f ../path_${fastq})
+ seqkit scat -j ${task.cpus} -f \${path} --gz-only > ${barcode}_merged.fastq
+ gzip ${barcode}_merged.fastq
"""
}
\ No newline at end of file
diff --git a/src/nf_modules/start_positions/main.nf b/src/nf_modules/start_positions/main.nf
index 27b8ebf..49f14e6 100644
--- a/src/nf_modules/start_positions/main.nf
+++ b/src/nf_modules/start_positions/main.nf
@@ -5,21 +5,26 @@ params.start_position_counts_out =""
process start_position_individuals{
container = "${container_url}"
label "small_mem_mono_cpus"
- tag "start positions"
+ tag "${barcode}"
if (params.start_position_counts_out != "") {
publishDir "results/${params.start_position_counts_out}", mode: 'copy'
}
input:
- path(start_position_counts)
+ tuple val(barcode), path(start_position_counts)
output:
- path("Rplots.pdf")
- path("*.png")
- path("Count_reads_per_promoter.tsv")
- path("classification_of_reads_per_RNA.txt"), emit: classification_of_reads
+ path("${barcode}/*.pdf")
+ path("${barcode}/*.png")
+ path("${barcode}/*.tsv")
+ tuple val(barcode), path("${barcode}/${barcode}_classification_of_reads_per_RNA.txt"), emit: classification_of_reads
script:
"""
- Rscript /Start_positions.R -i ${start_position_counts}
+ mkdir ${barcode}
+ cd ${barcode}/
+ Rscript /Start_positions.R -i ../${start_position_counts}
+ mv classification_of_reads_per_RNA.txt ${barcode}_classification_of_reads_per_RNA.txt
+ mv Count_reads_per_promoter.tsv ${barcode}_count_reads_per_promoter.tsv
+ mv Rplots.pdf ${barcode}_Rplots.pdf
"""
}
\ No newline at end of file
--
GitLab