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 af077b27a950e5f7af809c14690819db6c5ea880..9f86d2f5aac28f20f962586804286221857953aa 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
@@ -4,8 +4,13 @@ library(ggplot2, quietly = TRUE)
library(tidyr, quietly = TRUE)
library(dplyr, quietly = TRUE)
library(stringr, quietly = TRUE)
-library(RColorBrewer)
-library(optparse)
+library(RColorBrewer, quietly = TRUE)
+library(optparse, quietly = TRUE)
+library(conflicted, quietly = TRUE)
+
+# Résolution de conflits entre les bibliothèques dplyr et stats
+conflict_prefer("filter", "dplyr")
+conflict_prefer("lag", "dplyr")
# Load files
option_list = list(
diff --git a/src/.docker_modules/r-bolero/1.0/Install_packages.R b/src/.docker_modules/r-bolero/1.0/Install_packages.R
index 01ade6ff3cada50c7dbbfc1db835287d2397103e..1716eee62b8459a845bc574f181c2f026e36cadd 100644
--- a/src/.docker_modules/r-bolero/1.0/Install_packages.R
+++ b/src/.docker_modules/r-bolero/1.0/Install_packages.R
@@ -1,3 +1,3 @@
-list.of.packages <- c("ggplot2", "tidyr", "dplyr", "tidyverse", "stringr", "optparse", "RColorBrewer", "conflicted", "BiocManager", "resshape2", "R.utils")
+list.of.packages <- c("ggplot2", "tidyr", "dplyr", "tidyverse", "stringr", "optparse", "RColorBrewer", "conflicted", "BiocManager", "resshape2", "R.utils", "conflicted", "future", "future.apply")
new.packages <- list.of.packages[!(list.of.packages %in% installed.packages()[,"Package"])]
if(length(new.packages)) install.packages(new.packages, dependencies = T)
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 0efefc1e77e8d72d214d28d18d6a4ff9c7f05bc6..78824c5fea433a1e555c2ebde6c9664f5c2ab52b 100644
--- a/src/.docker_modules/r-bolero/1.0/Junctions_NanoSplicer.R
+++ b/src/.docker_modules/r-bolero/1.0/Junctions_NanoSplicer.R
@@ -1,14 +1,19 @@
#!/bin/Rscript
-
-################################################################################
-### NEED TO ADD A CASE OF NO SPLICED-VARIANTS ARE IDENTIFIED !!!!!!!!!!!!!!! ###
-### PROBLEM IF THERE IS ONLY MULTIPLE JUNCTIONS CONTAINING READS ###############
-################################################################################
library(ggplot2, quietly = TRUE)
library(tidyr, quietly = TRUE)
library(dplyr, quietly = TRUE)
library(stringr, quietly = TRUE)
-library(optparse)
+library(optparse, quietly = TRUE)
+library(future, quietly = TRUE)
+library(future.apply)
+library(conflicted, quietly = TRUE)
+
+# Set up parallel processing plan
+plan("multisession", workers = 18)
+
+# Résolution de conflits entre les bibliothèques dplyr et stats
+conflict_prefer("filter", "dplyr")
+conflict_prefer("lag", "dplyr")
# Load classification per promoter:
option_list = list(
@@ -118,8 +123,8 @@ assignation_acceptor <- function(pg_acceptor) {
return(acceptor_site)
}
-df$donor_site <- sapply(df$pg_donor, assignation_donor)
-df$acceptor_site <- sapply(df$pg_acceptor, assignation_acceptor)
+df$donor_site <- future_sapply(df$pg_donor, assignation_donor)
+df$acceptor_site <- future_sapply(df$pg_acceptor, assignation_acceptor)
df <- dplyr::mutate(df,
junction = paste0(donor_site, acceptor_site))
@@ -286,19 +291,48 @@ SP_assignation_multiple <- function(read_id, combinaison, promoter) {
return(SP_name)
}
-tmp <- multiple_junction %>% select(id, junction, promoter)
-df_combinaison <- data.frame(matrix(nrow = 0, ncol = 2))
-colnames(df_combinaison) <- c("id", "SP_name")
+tmp <- multiple_junction %>% select(all_of(c("id", "junction", "promoter")))
-for (read_id in list_read_multiple) {
+# Create an empty data frame with appropriate column names
+df_combinaison <- data.frame(id = character(0), SP_name = character(0))
+
+# Function to process each read_id
+process_read_id <- function(read_id) {
SP_name_computed <- SP_assignation_multiple(read_id,
tmp[tmp$id == read_id,]$junction,
tmp[tmp$id == read_id,]$promoter[1])
- res_vector <- data.frame(t(c(read_id, SP_name_computed)))
- colnames(res_vector) <- colnames(df_combinaison)
- df_combinaison <- rbind(df_combinaison, res_vector)
+ data.frame(id = read_id, SP_name = SP_name_computed)
+}
+
+if (length(multiple_junction$promoter) != 0) {
+ for (read_id in list_read_multiple) {
+ SP_name_computed <- SP_assignation_multiple(read_id,
+ tmp[tmp$id == read_id,]$junction,
+ tmp[tmp$id == read_id,]$promoter[1])
+ res_vector <- data.frame(t(c(read_id, SP_name_computed)))
+ colnames(res_vector) <- colnames(df_combinaison)
+ df_combinaison <- rbind(df_combinaison, res_vector)
+ }
+
+ df_combinaison <- df_combinaison[2:length(df_combinaison$id),]
}
+# Parallel processing using future_apply:
+# results <- future_apply(multiple_junction$id, 2, FUN = process_read_id,
+# future.seed = FALSE, future.progress = FALSE)
+# Combine the results into a single data frame
+# df_combinaison <- do.call(rbind, results)
+
+# Old loop:
+# for (read_id in list_read_multiple) {
+# SP_name_computed <- SP_assignation_multiple(read_id,
+# tmp[tmp$id == read_id,]$junction,
+# tmp[tmp$id == read_id,]$promoter[1])
+# res_vector <- data.frame(t(c(read_id, SP_name_computed)))
+# colnames(res_vector) <- colnames(df_combinaison)
+# df_combinaison <- rbind(df_combinaison, res_vector)
+# }
+
# df_combinaison <- df_combinaison[2:length(df_combinaison$id),]
multiple_junction <- merge(multiple_junction, df_combinaison, by="id")
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 9a4890a9c672256820a60a027108adfa423d2ddc..79fe46fad26ba8521d1a0746fd008c5e2c42e103 100644
--- a/src/.docker_modules/r-bolero/1.0/Start_positions.R
+++ b/src/.docker_modules/r-bolero/1.0/Start_positions.R
@@ -1,11 +1,16 @@
#!/bin/Rscript
# Packages loading
-library(dplyr)
-library(ggplot2)
-library(RColorBrewer)
-library(conflicted)
-library(optparse)
-library(tidyverse)
+library(dplyr, quietly = TRUE)
+library(ggplot2, quietly = TRUE)
+library(RColorBrewer, quietly = TRUE)
+library(conflicted, quietly = TRUE)
+library(optparse, quietly = TRUE)
+library(tidyverse, quietly = TRUE)
+library(future, quietly = TRUE)
+library(future.apply)
+
+# Set up parallel processing plan
+plan("multisession", workers = 18)
# Résolution de conflits entre les bibliothèques dplyr et stats
conflict_prefer("filter", "dplyr")
@@ -16,17 +21,14 @@ option_list = list(
make_option(c("-i", "--input"), type="character", default=NULL,
help="input start position file (.txt)", metavar="character"),
make_option(c("-b", "--barcode"), type="character", default=NULL,
- help="input barcode", metavar="character")
+ help="input barcode", metavar="character"),
+ make_option(c("-s", "--start-positions"), type = "character",
+ default = "103,117,276,1106,1221,1455,1632,2550,2968")
)
opt_parser = OptionParser(option_list=option_list)
opt = parse_args(opt_parser)
-#opt = ("/home/alia/scripts/Start_position/Start_positions_counts.txt")
-#list_file <- list.files(path=".",
-# pattern="*.txt",
-# all.files=FALSE,
-# full.names=FALSE)
file_to_load <- opt$input
splitted <- strsplit(opt$input, split = "[/]")[[1]]
filename <- strsplit(splitted[length(splitted)], split = "[.]")[[1]][1]
@@ -107,7 +109,7 @@ classify_reads <- function(read_info) {
}
colnames(sam_bc01) <- c("read_ID", "start_position", "barcode")
-sam_bc01$promoter <- sapply(sam_bc01$start_position,
+sam_bc01$promoter <- future_sapply(sam_bc01$start_position,
classify_reads)
write.table(sam_bc01,
@@ -159,7 +161,7 @@ promoters <- factor(c("preCore", "pgRNA", "preS1", "preS2/S", "HBx"),
levels = c("preCore", "pgRNA", "preS1", "preS2/S", "HBx"))
abs_count_reads <- data.frame()
-abs_count_reads <- sapply(list_name_samples,
+abs_count_reads <- future_sapply(list_name_samples,
abscount_promoter_reads,
df_parsed)
abs_count_reads <- cbind(c(as.vector(promoters),"total"), abs_count_reads)
@@ -171,7 +173,7 @@ write.table(abs_count_reads,
sep = "\t",
row.names = FALSE)
-resultats_start_promoters <- lapply(list_name_samples,
+resultats_start_promoters <- future_lapply(list_name_samples,
count_promoter_reads,
df_parsed)
@@ -210,4 +212,4 @@ plot_camembert <- function(barcode, df, tot) {
dpi = 300)
}
-lapply(list_name_samples, plot_camembert, formated_start_promoters, totalCountSample)
+future_lapply(list_name_samples, plot_camembert, formated_start_promoters, totalCountSample)