From ca26a64844c37d8fee1ecd9964e1b924ab8e437b Mon Sep 17 00:00:00 2001
From: aliarifki <aliarifki@outlook.fr>
Date: Wed, 14 Jun 2023 10:47:10 +0200
Subject: [PATCH] Ajout des barcodes en option pour les noms de fichiers
---
.../r-bolero/1.0/HBV_RNAs_count.R | 24 ++--
.../r-bolero/1.0/Junctions_NanoSplicer.R | 107 +-----------------
.../r-bolero/1.0/Start_positions.R | 10 +-
3 files changed, 24 insertions(+), 117 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 16d67f3..16d8b1d 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 5567a37..0685a21 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 830c52e..fcffb8e 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,
--
GitLab