diff --git a/src/bolero.nf b/src/bolero.nf
index cf3605d0115d8daad8fe5370839c745723a23d33..f6462faaf17ed7629b86be920a990d396a2cfe6e 100755
--- a/src/bolero.nf
+++ b/src/bolero.nf
@@ -160,9 +160,11 @@ Channel
// Test pour barcoding process
Channel
- .fromPath(params.pass)
+ .fromPath('/home/alia/pipelines/bolero/results/01_Basecalling/pass/', type: 'dir')
.set{pass}
-
+Channel
+ .fromPath('/home/alia/pipelines/bolero/results/01_Basecalling/sequencing_summary.txt')
+ .set{ss}
/*
****************************************************************
Imports
@@ -182,6 +184,7 @@ if(!params.skipBC) {
}
include { control_basecalling } from "./nf_modules/pycoqc/main.nf"
+include { control_bam } from "./nf_modules/pycoqc/main.nf"
include { concatenate } from "./nf_modules/seqkit/main.nf"
include { cut_5pRACE } from "./nf_modules/cutadapt/main.nf"
include { hbv_genome } from "./nf_modules/minimap2/main.nf"
@@ -217,23 +220,33 @@ workflow {
//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)
- barcoding_gpu(pass)
- barcoding_gpu.out.barcodes
- .flatten()
- .map{it -> [it.name, it]}
- .set{tuples_barcode}
- concatenate(tuples_barcode)
+ basecall_fast5_gpu(input)
+ if(params.kit_barcoding != ""){
+ barcoding_gpu(pass)
+ barcoding_gpu.out.barcodes
+ .flatten()
+ .map{it -> [it.name, it]}
+ .set{tuples_barcode}
+ concatenate(tuples_barcode)
+ }
+ else{
+ concatenate(pass)
+ }
//control_basecalling(basecall_fast5_gpu.out.sequencing_summary)
}
else {
- //basecall_fast5_cpu(input)
- barcoding_cpu(pass)
- barcoding_cpu.out.barcodes
- .flatten()
- .map{it -> [it.name, it]}
- .set{tuples_barcode}
- concatenate(tuples_barcode)
+ basecall_fast5_cpu(input)
+ if(params.kit_barcoding != ""){
+ barcoding_cpu(pass)
+ barcoding_cpu.out.barcodes
+ .flatten()
+ .map{it -> [it.name, it]}
+ .set{tuples_barcode}
+ concatenate(tuples_barcode)
+ }
+ else{
+ concatenate(pass)
+ }
//control_basecalling(basecall_fast5_cpu.out.sequencing_summary)
}
}
@@ -252,9 +265,16 @@ workflow {
//########################## MAPPING ##########################
hbv_genome(cut_5pRACE.out.fastq_cutadapt, genome.collect())
-
sort_index_bam(hbv_genome.out.bam)
+ sort_index_bam.out.indexed_bam
+ .flatten()
+ .filter(~/.*bam$/)
+ .collect()
+ .set{bam_path}
+
+ //control_bam(ss, bam_path)
+
//###################### START POSITIONS #######################
start_position_counts(sort_index_bam.out.indexed_bam)
diff --git a/src/nf_modules/junction_nanosplicer/main.nf b/src/nf_modules/junction_nanosplicer/main.nf
index a48c713e70903f8f604bfa59e5b3ffabbca6737f..6d24d6104c89e392f5d52b2774e891529dbdc35d 100644
--- a/src/nf_modules/junction_nanosplicer/main.nf
+++ b/src/nf_modules/junction_nanosplicer/main.nf
@@ -11,8 +11,7 @@ process junctions_nanosplicer{
}
input:
- tuple val(barcode), path(txt)
- tuple val(barcode), path(csv)
+ tuple val(barcode), path(txt), path(csv)
output:
path("${barcode}/${barcode}_JWR_check_parsed.csv")
diff --git a/src/nf_modules/ont-guppy/main.nf b/src/nf_modules/ont-guppy/main.nf
index e1282c5b8b4b21d7ae5a4c1c6795dc55a6f441d1..5704bb7596e7c1820247724341fb15316704b42f 100644
--- a/src/nf_modules/ont-guppy/main.nf
+++ b/src/nf_modules/ont-guppy/main.nf
@@ -27,7 +27,7 @@ process basecall_fast5_gpu {
errorKit "WARNING ! No kit type given..."
errorKit.view()
}
-/*
+
if (params.config_file != "") {
options = "-c /opt/ont/guppy/data/${params.config_file}"
}
@@ -35,7 +35,7 @@ process basecall_fast5_gpu {
options = "--flowcell ${params.flowcell} \
--kit ${params.kit} "
}
-*/
+
input:
path(fast5_folder)
@@ -60,8 +60,7 @@ guppy_basecaller --compress_fastq \
--gpu_runners_per_device ${params.gpu_runners_per_device} \
--num_callers ${params.num_callers} \
--chunks_per_runner ${params.chunks_per_runner} \
- --flowcell ${params.flowcell} \
- --kit ${params.kit}
+ ${options}
"""
}
@@ -84,6 +83,14 @@ process basecall_fast5_cpu {
errorKit.view()
}
+ if (params.config_file != "") {
+ options = "-c /opt/ont/guppy/data/${params.config_file}"
+ }
+ else {
+ options = "--flowcell ${params.flowcell} \
+--kit ${params.kit} "
+ }
+
input:
val(fast5_folder)
@@ -95,16 +102,20 @@ process basecall_fast5_cpu {
script:
"""
-echo "Start basecalling using CPUs."
-find ${fast5_folder} -type f -name "*.fast5" > allfast5files.txt
+echo "Start basecalling using G=CPUs."
+# guppy_basecaller --print_workflows
+path=\$(readlink -f ${fast5_folder})
+find \${path} -type f -name "*.fast5" > allfast5files.txt
guppy_basecaller --compress_fastq \
-i / \
--input_file_list allfast5files.txt \
-s . \
- --cpu_threads_per_caller ${params.cpu_threads_per_caller} \
+ -x "cuda:all" \
+ --min_qscore ${params.min_qscore} \
+ --cpu_runners_per_device ${params.cpu_runners_per_device} \
--num_callers ${params.num_callers} \
- --flowcell ${params.flowcell} \
- --kit ${params.kit}
+ --chunks_per_runner ${params.chunks_per_runner} \
+ ${options}
"""
}
@@ -112,7 +123,7 @@ params.kit_barcoding = "EXP-PBC001"
process barcoding_gpu {
container = "${container_url}"
label "gpus"
- tag "$fast5_folder"
+ tag "$pass_path"
if (params.barcoding_out != "") {
publishDir "results/${params.barcoding_out}", mode: 'copy'
}
@@ -140,7 +151,7 @@ guppy_barcoder \
process barcoding_cpu {
container = "${container_url}"
label "big_mem_multi_cpus"
- tag "$fast5_folder"
+ tag "$pass_path"
if (params.barcoding_out != "") {
publishDir "results/${params.barcoding_out}", mode: 'copy'
}
diff --git a/src/nf_modules/pycoqc/main.nf b/src/nf_modules/pycoqc/main.nf
index 1503479e5b4cd10a973d2c512a5f7831cddfe871..de9db1f18c24137e9ed39103b2f11a27405c7757 100644
--- a/src/nf_modules/pycoqc/main.nf
+++ b/src/nf_modules/pycoqc/main.nf
@@ -36,7 +36,8 @@ process control_bam {
path("*.txt")
"""
- find results/${params.minimap2_genome_out} -type f -name "*sorted.bam" > allbamfiles.txt
- #pycoQC -f ${txt} -a ${path_bam} -o Control_mapping.html
+ mkdir bam/
+ mv ${path_bam} bam/
+ pycoQC -f ${txt} -a bam/ -o Control_mapping.html
"""
}
\ No newline at end of file
diff --git a/src/nf_modules/rna_count/main.nf b/src/nf_modules/rna_count/main.nf
index 448f5986a596a4a5f0d8a6a0d80ff538daf208d0..bc858b2fcc26bb603757f9eaa8c85ada9e65f79d 100644
--- a/src/nf_modules/rna_count/main.nf
+++ b/src/nf_modules/rna_count/main.nf
@@ -11,8 +11,7 @@ process rna_count{
}
input:
- tuple val(barcode), path(spvariants)
- tuple val(barcode), path(classification)
+ tuple val(barcode), path(spvariants), path(classification)
output:
path("${barcode}/*.csv")
diff --git a/src/nf_modules/seqkit/main.nf b/src/nf_modules/seqkit/main.nf
index 683c924fe37a357baa16860c4520bcb800e16144..87792e5cb181e76c25495747cad2517fa2aab8d8 100755
--- a/src/nf_modules/seqkit/main.nf
+++ b/src/nf_modules/seqkit/main.nf
@@ -87,4 +87,24 @@ process concatenate {
seqkit scat -j ${task.cpus} -f \${path} --gz-only > ${barcode}_merged.fastq
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