Merge pull request nf-core#124 from zifornd/hotfix-check-names

Stop R converting sample names with '-' in string
fhausmann · Feb 23, 2024 · 5560492 · 5560492
2 parents be1e0f2 + 561f14b
commit 5560492
Show file tree

Hide file tree

Showing 6 changed files with 15 additions and 10 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,6 +3,11 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## v1.0.3 - 2024-02-23
+
+- Improved TPM file splitting performance (Issue #120).
+- Fixed an issue where R scripts altered sample names upon loading (Issue #122).
+
 ## v1.0.2 - 2024-01-08
 
 Patch for run_stager.R (#108) and template update v2.11.1 (#109).

diff --git a/bin/run_dexseq_dtu.R b/bin/run_dexseq_dtu.R
@@ -77,21 +77,21 @@ vectorToDataFrame <- function(x) {
 
 # Read samples table
 
-samples <- read.delim(samples, stringsAsFactors = TRUE)
+samples <- read.delim(samples, stringsAsFactors = TRUE, check.names = FALSE)
 
 colnames(samples) <- c("sample", "condition")
 
 
 # Read contrasts table
 
-contrasts <- read.csv(contrasts)
+contrasts <- read.csv(contrasts, check.names = FALSE)
 
 contrasts <- contrasts[, c("contrast", "treatment", "control"), drop = FALSE]
 
 
 # Read counts table
 
-counts <- read.table(counts, sep = "\t", header = TRUE)
+counts <- read.table(counts, sep = "\t", header = TRUE, check.names = FALSE)
 
 annotation <- data.frame(
     featureID = counts$feature_id,

diff --git a/bin/run_dexseq_exon.R b/bin/run_dexseq_exon.R
@@ -99,15 +99,15 @@ write.plotDEXSeq <- function(x, file, ntop = 10) {
 
 # Read samples table
 
-samples <- read.csv(samples, stringsAsFactors = TRUE)
+samples <- read.csv(samples, stringsAsFactors = TRUE, check.names = FALSE)
 
 samples <- samples[, c("sample", "condition"), drop = FALSE]
 
 samples <- unique(samples)
 
 # Read contrasts table
 
-contrasts <- read.csv(contrasts)
+contrasts <- read.csv(contrasts, check.names = FALSE)
 
 contrasts <- contrasts[, c("contrast", "treatment", "control"), drop = FALSE]
 

diff --git a/bin/run_drimseq_filter.R b/bin/run_drimseq_filter.R
@@ -43,7 +43,7 @@ tx2gene <- read.csv(tximport_tx2gene, sep="\t", header = TRUE)
 ######################################
 
 # Read in Sample sheet
-samps <- read.csv(samplesheet, sep=",", header = TRUE)
+samps <- read.csv(samplesheet, sep=",", header = TRUE, check.names = FALSE)
 
 # check header of sample sheet
 if (!c("sample") %in% colnames(samps) | !c("condition") %in% colnames(samps)) {

diff --git a/bin/run_edger_exon.R b/bin/run_edger_exon.R
@@ -28,7 +28,7 @@ library(edgeR)
 
 # Read samples table
 
-samples <- read.csv(samplesheet)
+samples <- read.csv(samplesheet, check.names = FALSE)
 
 samples <- samples[, c("sample", "condition"), drop = FALSE]
 
@@ -37,7 +37,7 @@ samples <- unique(samples)
 
 # Read contrasts table
 
-contrasts <- read.csv(contrastsheet)
+contrasts <- read.csv(contrastsheet, check.names = FALSE)
 
 contrasts <- contrasts[, c("contrast", "treatment", "control"), drop = FALSE]
 

diff --git a/bin/suppa_split_file.R b/bin/suppa_split_file.R
@@ -39,14 +39,14 @@ if (length(args) == 5){
 ######### Read in input file #########
 ######################################
 
-input_data <- read.csv(input_file, sep="\t", header=TRUE)
+input_data <- read.csv(input_file, sep = "\t", header = TRUE, check.names = FALSE)
 
 ######################################
 ####### Process samplesheet ##########
 ######################################
 
 # Read in samplesheet
-samplesheet <- read.csv(samplesheet, header = TRUE)
+samplesheet <- read.csv(samplesheet, header = TRUE, check.names = FALSE)
 
 # check header of sample sheet
 if (!c("sample") %in% colnames(samplesheet) | !c("condition") %in% colnames(samplesheet)) {