diff --git a/src/.docker_modules/r-bolero/1.0/HBV_RNAs_count.R b/src/.docker_modules/r-bolero/1.0/HBV_RNAs_count.R
index 16d67f3f8dd8a9161ff7006c410bda1291d45e63..16d8b1d8cbbc7aff4d56551a04e78cb060980aea 100644
--- a/src/.docker_modules/r-bolero/1.0/HBV_RNAs_count.R
+++ b/src/.docker_modules/r-bolero/1.0/HBV_RNAs_count.R
@@ -13,7 +13,9 @@ option_list = list(
make_option(c("-s", "--SPvariants"), type="character", default=NULL,
help="input identified SP variants table (.csv)", metavar="character"),
make_option(c("-c", "--classification"), type="character", default=NULL,
- help="input classification of reads file (.txt)", metavar="character"))
+ help="input classification of reads file (.txt)", metavar="character"),
+ make_option(c("-b", "--barcode"), type="character", default=NULL,
+ help="input barcode", metavar="character"))
opt_parser = OptionParser(option_list=option_list)
opt = parse_args(opt_parser)
@@ -85,7 +87,7 @@ ggplot(countSP, aes(x = "percent",
scale_fill_manual(values = countSP$teinte) +
labs(fill = "spliced-variants")
-ggsave(file = "SP_proportion_camembert.png",
+ggsave(file = paste0(opt$barcode, "_SP_proportion_piechart.png"),
scale = 2,
width = 1920,
height = 1080,
@@ -100,7 +102,7 @@ ggplot(countSP, aes(x = nom, y = proportion, fill = nom)) +
xlab(label = "spliced-variants") +
ylab(label = "percent")
-ggsave(file = "SP_proportion.png",
+ggsave(file = paste0(opt$barcode, "_SP_proportion.png"),
scale = 2,
width = 1920,
height = 1080,
@@ -127,7 +129,7 @@ count_species <- df_species %>% count(species)
count_species <- dplyr::mutate(count_species,
percent = (as.numeric(n)/sum(as.numeric(n))*100))
#print(count_species)
-write.table(df_species, file = "All_reads_identified.csv",
+write.table(df_species, file = paste0(opt$barcode, "_all_reads_identified.csv"),
sep = "\t", quote = FALSE, row.names = FALSE)
# Null dataset:
@@ -165,7 +167,7 @@ count_species_SPxx <- dplyr::mutate(count_species_SPxx,
percent=(as.numeric(n)/sum(as.numeric(n))*100))
#print(count_species_SPxx)
# save the tab:
-write.csv(count_species_SPxx, file = "Count_canonical_species_SPxx.csv")
+write.csv(count_species_SPxx, file = paste0(opt$barcode, "_count_canonical_species_SPxx.csv"))
# prepare to plot:
count_species_SPxx <- dplyr::inner_join(palette_complete,
@@ -176,7 +178,7 @@ count_species_SPxx <- dplyr::inner_join(palette_complete,
count_species_SPxx$nom <- factor(count_species_SPxx$nom, levels = all_species_name)
# Save:
-write.csv(count_species, file = "Count_species.csv")
+write.csv(count_species, file = paste0(opt$barcode, "_count_species.csv"))
# RNA species composition all species:
count_species <- dplyr::inner_join(palette_complete, count_species,
@@ -194,7 +196,7 @@ ggplot(count_species,
labs(fill = "RNA species & spliced-variants") +
xlab(label = "RNA species & spliced-variants")
-ggsave(file = "Count_RNAs_species.png",
+ggsave(file = paste0(opt$barcode, "_count_RNAs_species.png"),
scale = 2,
width = 1920,
height = 1080,
@@ -220,7 +222,7 @@ ggplot(count_species_clear,
labs(fill = "RNA species & spliced-variants") +
xlab(label = "RNA species & spliced-variants")
-ggsave(file = "Count_RNAs_species_clear.png",
+ggsave(file = paste0(opt$barcode, "_count_RNAs_species_clear.png"),
scale = 2,
width = 1920,
height = 1080,
@@ -246,7 +248,7 @@ ggplot(count_clear, aes(x = "percent",
scale_fill_manual(values = count_clear$teinte) +
labs(fill = "spliced-variants")
-ggsave(file = "SP_clear_proportion_camembert.png",
+ggsave(file = paste0(opt$barcode, "_SP_clear_proportion_piechart.png"),
scale = 2,
width = 1920,
height = 1080,
@@ -263,7 +265,7 @@ ggplot(count_clear, aes(x = nom,
xlab(label = "spliced-variants") +
ylab(label = "percent")
-ggsave(file = "SP_clear_proportion.png",
+ggsave(file = paste0(opt$barcode, "_SP_clear_proportion.png"),
scale = 2,
width = 1920,
height = 1080,
@@ -281,7 +283,7 @@ ggplot(count_species_SPxx, aes(x = "species",
ylab(label = "TSS usage") +
xlab(label = "percent")
-ggsave(file = "Count_RNAs_species_camembert.png",
+ggsave(file = paste0(opt$barcode, "_count_RNAs_species_piechart.png"),
scale = 2,
width = 1920,
height = 1080,
diff --git a/src/.docker_modules/r-bolero/1.0/Junctions_NanoSplicer.R b/src/.docker_modules/r-bolero/1.0/Junctions_NanoSplicer.R
index 5567a378b0c61e716092c77a7702f2360b2bf2b2..0685a2199e4d9c4ea60464b46dceabd6cb2d07a6 100644
--- a/src/.docker_modules/r-bolero/1.0/Junctions_NanoSplicer.R
+++ b/src/.docker_modules/r-bolero/1.0/Junctions_NanoSplicer.R
@@ -15,7 +15,9 @@ option_list = list(
make_option(c("-c", "--classification"), type="character", default="./classification.txt",
help="input classification or reads file (.txt)", metavar="character"),
make_option(c("-j", "--jwr"), type="character", default=NULL,
- help="input nanosplicer results table (.csv)", metavar="character"))
+ help="input nanosplicer results table (.csv)", metavar="character"),
+ make_option(c("-b", "--barcode"), type="character", default=NULL,
+ help="input barcode", metavar="character"))
opt_parser = OptionParser(option_list=option_list)
opt = parse_args(opt_parser)
reads_pos <- read.table(opt$classification,
@@ -113,7 +115,7 @@ df$acceptor_site <- sapply(df$pg_acceptor, assignation_acceptor)
df <- dplyr::mutate(df,
junction = paste0(donor_site, acceptor_site))
-write.table(df, file = "JWR_check_parsed.csv", row.names = FALSE, sep = "\t")
+write.table(df, file = paste0(opt$barcode, "_JWR_check_parsed.csv"), row.names = FALSE, sep = "\t")
duplicated2 <- function(x){
if (sum(dup <- duplicated(x))==0)
@@ -293,107 +295,8 @@ SP_variant_unique <- df_SPvariants %>% select(id, SP_name)
SP_variant_unique <- SP_variant_unique[!duplicated(SP_variant_unique$id),] # distinct(SP_variant_unique, id)
write.table(df_SPvariants,
- "identified_SPvariants.csv",
+ paste0(opt$barcode, "_identified_SPvariants.csv"),
row.names = FALSE,
sep = "\t",
quote = FALSE)
-ggplot(df, aes(x=pg_donor)) +
- geom_histogram(aes(y=after_stat(density)),color="darkblue", fill="lightblue") +
- geom_density(alpha=.2, fill="lightblue") +
- geom_vline(aes(xintercept=median(pg_donor)),
- color="blue", linetype="dashed", linewidth=1) +
- geom_vline(aes(xintercept=quantile(pg_donor, 0.025)),
- linetype="dashed", linewidth=0.25) +
- geom_vline(aes(xintercept=quantile(pg_donor, 0.975)),
- linetype="dashed", linewidth=0.25) +
- geom_vline(aes(xintercept=quantile(pg_donor, 0.01)),
- color="green", linetype="dashed", linewidth=0.25) +
- geom_vline(aes(xintercept=quantile(pg_donor, 0.99)),
- color="green", linetype="dashed", linewidth=0.25) +
- geom_vline(aes(xintercept=(median(pg_donor)+sd(pg_donor))),
- color="red", linewidth=0.5) +
- geom_vline(aes(xintercept=(median(pg_donor)-sd(pg_donor))),
- color="red", linewidth=0.5) +
- scale_x_continuous(breaks=c(min(df$pg_donor),
- quantile(df$pg_donor, 0.025),
- quantile(df$pg_donor, 0.005),
- median(df$pg_donor)-sd(df$pg_donor),
- median(df$pg_donor),
- median(df$pg_donor)+sd(df$pg_donor),
- quantile(df$pg_donor, 0.975),
- quantile(df$pg_donor, 0.995),
- max(df$pg_donor)),
- label = c(min(df$pg_donor),
- floor(quantile(df$pg_donor, 0.025)),
- floor(quantile(df$pg_donor, 0.005)),
- round(median(df$pg_donor)-sd(df$pg_donor)),
- median(df$pg_donor),
- round(median(df$pg_donor)+sd(df$pg_donor)),
- floor(quantile(df$pg_donor, 0.975))+1,
- round(quantile(df$pg_donor, 0.995))+1,
- max(df$pg_donor))) +
- theme(axis.text.x = element_text(angle = 45))
-
-ggsave(filename = "Donor_curve.png",
- device = "png",
- scale = 1,
- width = 1920,
- height = 1080,
- units = "px",
- dpi = 320)
-
-ggplot(df, aes(x=pg_acceptor)) +
- geom_histogram(aes(y=after_stat(density)),color="red", fill="darksalmon") +
- geom_density(alpha=.2, fill="darksalmon") +
- geom_vline(aes(xintercept=median(pg_acceptor)),
- color="red", linetype="dashed", linewidth=1) +
- geom_vline(aes(xintercept=quantile(pg_acceptor, 0.025)),
- linetype="dashed", linewidth=0.25) +
- geom_vline(aes(xintercept=quantile(pg_acceptor, 0.975)),
- linetype="dashed", linewidth=0.25) +
- geom_vline(aes(xintercept=quantile(pg_acceptor, 0.005)),
- color="green", linetype="dashed", linewidth=0.25) +
- geom_vline(aes(xintercept=quantile(pg_acceptor, 0.995)),
- color="green", linetype="dashed", linewidth=0.25) +
- geom_vline(aes(xintercept=(median(pg_acceptor)+sd(pg_acceptor))),
- color="blue", linewidth=0.5) +
- geom_vline(aes(xintercept=(median(pg_acceptor)-sd(pg_acceptor))),
- color="blue", linewidth=0.5) +
- scale_x_continuous(breaks=c(min(df$pg_acceptor),
- quantile(df$pg_acceptor, 0.025),
- quantile(df$pg_acceptor, 0.005),
- median(df$pg_acceptor)-sd(df$pg_acceptor),
- median(df$pg_acceptor),
- median(df$pg_acceptor)+sd(df$pg_acceptor),
- quantile(df$pg_acceptor, 0.975),
- quantile(df$pg_acceptor, 0.995),
- max(df$pg_acceptor)),
- label = c(min(df$pg_acceptor),
- floor(quantile(df$pg_acceptor, 0.025)),
- floor(quantile(df$pg_acceptor, 0.005)),
- round(median(df$pg_acceptor)-sd(df$pg_acceptor)),
- median(df$pg_acceptor),
- round(median(df$pg_acceptor)+sd(df$pg_acceptor)),
- floor(quantile(df$pg_acceptor, 0.975))+1,
- floor(quantile(df$pg_acceptor, 0.995))+1,
- max(df$pg_acceptor))) +
- theme(axis.text.x = element_text(angle = 45))
-
-ggsave(filename = "Acceptor_curve.png",
- device = "png",
- scale = 1,
- width = 1920,
- height = 1080,
- units = "px",
- dpi = 320)
-
-# Graphs and tests:
-
-# sink("test_shapiro.txt")
-# print("Normality test: Shapiro-Wilk")
-# print("Donor site:")
-# print(shapiro.test(df$pg_donor))
-# print("Acceptor site:")
-# print(shapiro.test(df$pg_acceptor))
-# sink()
\ No newline at end of file
diff --git a/src/.docker_modules/r-bolero/1.0/Start_positions.R b/src/.docker_modules/r-bolero/1.0/Start_positions.R
index 830c52e07598df6019bacf72c72128f99688a3d9..fcffb8ef479643092c27285ef0706dc6fbdcc87c 100644
--- a/src/.docker_modules/r-bolero/1.0/Start_positions.R
+++ b/src/.docker_modules/r-bolero/1.0/Start_positions.R
@@ -14,7 +14,9 @@ conflict_prefer("lag", "dplyr")
# Load Start_positions_count files:
option_list = list(
make_option(c("-i", "--input"), type="character", default=NULL,
- help="input start position file (.txt)", metavar="character")
+ help="input start position file (.txt)", metavar="character"),
+ make_option(c("-b", "--barcode"), type="character", default=NULL,
+ help="input barcode", metavar="character")
)
opt_parser = OptionParser(option_list=option_list)
@@ -109,7 +111,7 @@ sam_bc01$promoter <- sapply(sam_bc01$start_position,
classify_reads)
write.table(sam_bc01,
- file = "classification_of_reads_per_RNA.txt",
+ file = paste0(opt$barcode, "_classification_of_reads_per_RNA.txt"),
quote = FALSE,
sep = "\t",
row.names = FALSE)
@@ -164,7 +166,7 @@ abs_count_reads <- cbind(c(as.vector(promoters),"total"), abs_count_reads)
colnames(abs_count_reads) <- c("promoter", "read_number")
write.table(abs_count_reads,
- file = "Count_reads_per_promoter.tsv",
+ file = paste0(opt$barcode, "_count_reads_per_promoter.tsv"),
quote = FALSE,
sep = "\t",
row.names = FALSE)
@@ -201,7 +203,7 @@ plot_camembert <- function(barcode, df, tot) {
print(camembert)
- ggsave(filename = paste0("./Reads_start_promoters_", barcode, "_camembert.png"),
+ ggsave(filename = paste0("./", opt$barcode, "_reads_start_promoters_piechart.png"),
plot = last_plot(),
scale = 1,
width = 1920,
diff --git a/src/bolero.nf b/src/bolero.nf
index 3ff3c53e85c17a21141a0f132b670b91291db2d2..0e7e3fa1f410be53b1172ce7118491d028742ee4 100755
--- a/src/bolero.nf
+++ b/src/bolero.nf
@@ -31,8 +31,8 @@ def helpMessage() {
Mandatory arguments:
--input [path] Path to the folder containing fast5 files.
If skip basecalling option enabled, path to fastq files folder.
- --adapt [str] Sequence of 5'RACE adapter.
- --gsp [str] Sequence of gene-specific primer used in 5'RACE amplification step.
+ --adapt [file] Path to the txt/fasta file containing the sequence of 5'RACE adapter.
+ --gsp [file] Path to the txt/fasta file containing the sequence of gene-specific primer used in 5'RACE amplification step.
References:
--genome [file] Path to the fasta file containing the genome.
@@ -128,10 +128,17 @@ Channel
.ifEmpty { error "No fast5/q folder defined." }
.set { input }
+/*
+Channel
+ .fromPath( params.adapt )
+ .ifEmpty { error "No adapter sequence defined." }
+ .set { adapt }
+
Channel
- .of( params.adapt )
- .ifEmpty { error "No adapter sequence defined." }
- .set { adapt }
+ .fromPath( params.gsp )
+ .ifEmpty { error "No adapter sequence defined." }
+ .set { gsp }
+*/
Channel
.fromPath( params.genome )
@@ -143,7 +150,10 @@ 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 +171,7 @@ if(!params.skipBC) {
}
}
-// Replace concatenate by seqkit fct to parallelization:
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 +185,6 @@ 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
@@ -191,40 +195,38 @@ 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/nextflow.config b/src/nextflow.config
index 0ffe3409875cf9b59d9374ab076491e99395affd..698aee8ce7792caf41a9726e7cc8c11f67424dbd 100755
--- a/src/nextflow.config
+++ b/src/nextflow.config
@@ -18,7 +18,7 @@ profiles {
docker.enabled = true
process {
errorStrategy = 'finish'
- memory = '16GB'
+ memory = '12GB'
withLabel: big_mem_mono_cpus {
cpus = 1
}
@@ -47,7 +47,7 @@ profiles {
podman.enabled = true
process {
errorStrategy = 'finish'
- memory = '16GB'
+ memory = '12GB'
withLabel: big_mem_mono_cpus {
cpus = 1
}
@@ -72,13 +72,45 @@ profiles {
}
}
}
+ pollux {
+ singularity.enabled = true
+ singularity.cacheDir = "./bin/"
+ singularity.bind = "/home"
+ process {
+ errorStrategy = 'finish'
+ memory = '32GB'
+ withLabel: big_mem_mono_cpus {
+ cpus = 1
+ }
+ withLabel: big_mem_multi_cpus {
+ cpus = 16
+ }
+ withLabel: small_mem_mono_cpus {
+ cpus = 1
+ memory = '2GB'
+ }
+ withLabel: small_mem_multi_cpus {
+ cpus = 8
+ memory = '2GB'
+ }
+ withLabel: mid_mem_mono_cpus {
+ cpus = 1
+ memory = '8GB'
+ }
+ withLabel: mid_mem_multi_cpus {
+ cpus = 8
+ memory = '8GB'
+ }
+ }
+ }
+
singularity {
singularity.enabled = true
singularity.cacheDir = "./bin/"
singularity.bind = "/home"
process {
errorStrategy = 'finish'
- memory = '16GB'
+ memory = '12GB'
withLabel: big_mem_mono_cpus {
cpus = 1
}
diff --git a/src/nf_modules/cutadapt/main.nf b/src/nf_modules/cutadapt/main.nf
index b7ffd3b37ab7288d518cb350524e07881458a5b0..7c72b448f940835231dab6dc00b05bbfb75cb7bb 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" \
${fastq}
"""
}
\ No newline at end of file
diff --git a/src/nf_modules/junction_nanosplicer/main.nf b/src/nf_modules/junction_nanosplicer/main.nf
index 9f0a209ea7f5d158f1d0e277ad30294ead8b4d69..fb391396b8bee9ee39bee4a80818d7db4947e586 100644
--- a/src/nf_modules/junction_nanosplicer/main.nf
+++ b/src/nf_modules/junction_nanosplicer/main.nf
@@ -5,23 +5,23 @@ params.nanosplicer_out = ""
process junctions_nanosplicer{
container = "${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 ../${csv}
"""
}
\ No newline at end of file
diff --git a/src/nf_modules/minimap2/main.nf b/src/nf_modules/minimap2/main.nf
index 5e101b78394ec6a73c34017d532df408400274f2..91c91931b131b820a327686623a614cd26b4ab7a 100755
--- a/src/nf_modules/minimap2/main.nf
+++ b/src/nf_modules/minimap2/main.nf
@@ -89,22 +89,25 @@ params.mapping_hbv_genome = "-ax splice --secondary=no -G 1650 -u n --eqx"
process hbv_genome {
container = "${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 - > ${barcode}_res.bam
"""
}
\ No newline at end of file
diff --git a/src/nf_modules/nanosplicer/main.nf b/src/nf_modules/nanosplicer/main.nf
new file mode 100644
index 0000000000000000000000000000000000000000..71908d7e556563781f6c44d6a8483c51488a3bd6
--- /dev/null
+++ b/src/nf_modules/nanosplicer/main.nf
@@ -0,0 +1,26 @@
+version = "1.0"
+container_url = "xgrand/nanosplicer:${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/ont-guppy/main.nf b/src/nf_modules/ont-guppy/main.nf
index b4ea29f9fbdf61b947cbc6f0d8f6ba16f0365184..f6fddc94e1b44bc71d9ef11e3eb76c876b2d9aa5 100644
--- a/src/nf_modules/ont-guppy/main.nf
+++ b/src/nf_modules/ont-guppy/main.nf
@@ -39,8 +39,10 @@ process basecall_fast5_gpu {
"""
echo "Start basecalling using GPUs."
# guppy_basecaller --print_workflows
+find -type f -name "*.fast5" > allfast5files.txt
guppy_basecaller --compress_fastq \
-i ${fast5_folder} \
+ --input_file_list allfast5files.txt \
-s . \
--flowcell ${params.flowcell} \
--kit ${params.kit} \
@@ -82,8 +84,10 @@ process basecall_fast5_cpu {
script:
"""
echo "Start basecalling using CPUs."
+find ${fast5_folder} -type f -name "*.fast5" > allfast5files.txt
guppy_basecaller --compress_fastq \
- -i ${fast5_folder} \
+ -i / \
+ --input_file_list allfast5files.txt \
-s . \
--cpu_threads_per_caller ${params.cpu_threads_per_caller} \
--num_callers ${params.num_callers} \
diff --git a/src/nf_modules/rna_count/main.nf b/src/nf_modules/rna_count/main.nf
index a2ae2ce641efe1f9829f2d6712720cb9dea743af..06afba66cb2379922e83b700cbe43fab3b21b9c8 100644
--- a/src/nf_modules/rna_count/main.nf
+++ b/src/nf_modules/rna_count/main.nf
@@ -5,22 +5,24 @@ params.rna_count_out = ""
process rna_count{
container = "${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 0b48cd511948cf0319496c7088dc2473fd7d40b2..d44804b71bb4d0b3953ca1cf078e78882393d943 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} ${barcode}_sorted.bam
"""
}
\ No newline at end of file
diff --git a/src/nf_modules/seqkit/main.nf b/src/nf_modules/seqkit/main.nf
index e6d7e6b2396f486301b08d03328e05b5dd264685..683c924fe37a357baa16860c4520bcb800e16144 100755
--- a/src/nf_modules/seqkit/main.nf
+++ b/src/nf_modules/seqkit/main.nf
@@ -29,35 +29,37 @@ params.seqkit_grep_out = ""
process seqkit_grep {
container = "${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 ${barcode}_merged.fastq
"""
}
\ No newline at end of file
diff --git a/src/nf_modules/start_positions/main.nf b/src/nf_modules/start_positions/main.nf
index 27b8ebf35ef66e41db2de2a114008883e26e04d6..668d50a5726464764d78c9d73061b12452631263 100644
--- a/src/nf_modules/start_positions/main.nf
+++ b/src/nf_modules/start_positions/main.nf
@@ -5,21 +5,24 @@ params.start_position_counts_out =""
process start_position_individuals{
container = "${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 Rplots.pdf ${barcode}_Rplots.pdf
"""
}
\ No newline at end of file