From 8561de6881624dc0c536c4f5896fdceb919feeff Mon Sep 17 00:00:00 2001
From: xgrand <xavier.grand@ens-lyon.fr>
Date: Fri, 4 Aug 2023 14:51:13 +0200
Subject: [PATCH] Debug r-bolero scripts and Docker
---
src/.docker_modules/r-bolero/1.0/HBV_RNAs_count.R | 15 ++++++++-------
.../r-bolero/1.0/Install_packages.R | 2 +-
.../r-bolero/1.0/Junctions_NanoSplicer.R | 14 +++++++++-----
.../r-bolero/1.0/Start_positions.R | 6 ++----
4 files changed, 20 insertions(+), 17 deletions(-)
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 e3ef7f8..5d0d29c 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
@@ -2,7 +2,6 @@
# Packages loading
library(ggplot2, quietly = TRUE)
library(tidyr, quietly = TRUE)
-library(plyr, quietly = TRUE)
library(dplyr, quietly = TRUE)
library(stringr, quietly = TRUE)
library(RColorBrewer)
@@ -135,7 +134,7 @@ write.table(df_species, file = paste0(opt$barcode, "_all_reads_identified.csv"),
# Null dataset:
species <- c(TSS_species, SPvariants, new_SP_candidates)
-canonical_species <- TSS_species[c(1:3,5)]
+# canonical_species <- TSS_species[c(1:3,5)]
null_count <- data.frame(species = species,
n = rep(0, times = length(species)),
@@ -158,16 +157,17 @@ count_species_SPxx <- data.frame(species = "SPvariants",
%in% SPvariants,]$n))
count_species_SPxx <- rbind.data.frame(count_species_SPxx,
count_species[count_species$species
- %in% c(canonical_species,
+ %in% c(TSS_species,
SPvariants), 1:2],
stringsAsFactors = FALSE)
count_species_SPxx <- count_species_SPxx[count_species_SPxx$species %in%
- all_species_name[c(1:3,5,35)],]
+ all_species_name[c(1:5,35)],] # c(1:3,5,35)
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 = paste0(opt$barcode, "_count_canonical_species_SPxx.csv"))
+write.csv(count_species_SPxx,
+ file = paste0(opt$barcode, "_count_canonical_species_SPxx.csv"))
# prepare to plot:
count_species_SPxx <- dplyr::inner_join(palette_complete,
@@ -175,7 +175,8 @@ count_species_SPxx <- dplyr::inner_join(palette_complete,
by = c("nom" = "species"))
#names(palette_complete)
#names(count_species_SPxx)
-count_species_SPxx$nom <- factor(count_species_SPxx$nom, levels = all_species_name)
+count_species_SPxx$nom <- factor(count_species_SPxx$nom,
+ levels = all_species_name)
# Save:
write.csv(count_species, file = paste0(opt$barcode, "_count_species.csv"))
@@ -204,7 +205,7 @@ ggsave(file = paste0(opt$barcode, "_count_RNAs_species.png"),
dpi = 300)
# Filter RNA species canonical + SPvariants:
-count_species_clear <- count_species[count_species$species %in% c(canonical_species, SPvariants),]
+count_species_clear <- count_species[count_species$nom %in% c(TSS_species, SPvariants),]
# RNA species composition all species:
count_species_clear <- dplyr::inner_join(palette_complete, count_species_clear,
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 384435c..01ade6f 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", "plyr", "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")
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 0685a21..3b6a147 100644
--- a/src/.docker_modules/r-bolero/1.0/Junctions_NanoSplicer.R
+++ b/src/.docker_modules/r-bolero/1.0/Junctions_NanoSplicer.R
@@ -5,7 +5,6 @@
################################################################################
library(ggplot2, quietly = TRUE)
library(tidyr, quietly = TRUE)
-library(plyr, quietly = TRUE)
library(dplyr, quietly = TRUE)
library(stringr, quietly = TRUE)
library(optparse)
@@ -165,10 +164,15 @@ SP_assignation_single <- function(site, promoter) {
}
}
-single_junction <- ddply(single_junction,
- .(id),
- mutate,
- SP_name = SP_assignation_single(junction, promoter))
+#dplyr version:
+single_junction <- single_junction %>% dplyr::group_by(id) %>%
+ dplyr::mutate(SP_name = SP_assignation_single(junction, promoter))
+
+#plyr version
+# single_junction <- ddply(single_junction,
+# .(id),
+# mutate,
+# SP_name = SP_assignation_single(junction, promoter))
SP_assignation_multiple <- function(read_id, combinaison, promoter) {
if (promoter == "pgRNA" | promoter == "preCore") {
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 fcffb8e..9a4890a 100644
--- a/src/.docker_modules/r-bolero/1.0/Start_positions.R
+++ b/src/.docker_modules/r-bolero/1.0/Start_positions.R
@@ -187,9 +187,7 @@ formated_start_promoters <- pivot_longer(resultats_start_promoters,
names_to = "Barcodes",
values_to = "nb_reads")
-mycolors <- colorRampPalette(brewer.pal(10, "Paired"))(10)
-mycolors5 <- c("#712E80", "#006695", "#3B9746", "#1F4F25", "#F5751A")
-mycolors6 <- c("#A6CEE3", "#3362ff", "#33c5ff", "#6A3D9A", "#d60000")
+mycolors <- c("#712E80", "#006695", "#3B9746", "#1F4F25", "#F5751A")
plot_camembert <- function(barcode, df, tot) {
camembert <- ggplot(df[df$Barcodes == barcode,], aes(x = barcode,
@@ -197,7 +195,7 @@ plot_camembert <- function(barcode, df, tot) {
fill=promoters)) +
geom_col() +
coord_polar("y") +
- scale_fill_manual(values = mycolors5) +
+ scale_fill_manual(values = mycolors) +
labs(title = paste0("#reads = ", tot[1,barcode]), x=element_blank(), y=element_blank()) +
theme_light()
--
GitLab