CW-1167: error if conditionsheet and sample sheet dont match

CHANGELOG.md

@@ -10,6 +10,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Added
 - Demo differential expression data in repository.
 - Improved DE explanation in docs
+### Fixed
+- Error if condition sheet and sample sheet don't match.
 
 ## [v0.1.5]
 ### Added

README.md

@@ -206,14 +206,14 @@ Differential Expression requires at least 2 replicates of each sample to compare
 
 #### Condition sheet
 The condition sheet should be a .tsv with two columns.
-- The sample column will need to match the 6 directories in the input fastq directory.
+- The sample_id column will need to match the 6 directories in the input fastq directory, if you are additionally using a sample_sheet they will need to correspond to the sample_ids in that.
 - The condition column will need to contain one of two keys to indicate the two samples being compared.
 
 In the default `condition_sheet.tsv` available in the test_data directory we have used the following.
 
 eg. condition_sheet.tsv
 ```
-sample,condition
+sample_id,condition
 barcode01,untreated
 barcode02,untreated
 barcode03,untreated

bin/de_analysis.R

@@ -7,7 +7,8 @@ cat("Loading counts, conditions and parameters.\n")
 cts <- as.matrix(read.csv("merged/all_counts.tsv", sep="\t", row.names="Reference", stringsAsFactors=FALSE))
 
 # Set up sample data frame:
-coldata <- read.csv("de_analysis/coldata.tsv", row.names="sample", sep=",", stringsAsFactors=TRUE)
+#changed this to sample_id
+coldata <- read.csv("de_analysis/coldata.tsv", row.names="sample_id", sep=",", stringsAsFactors=TRUE)
 
 coldata$sample_id <- rownames(coldata)
 coldata$condition <- factor(coldata$condition, levels=rev(levels(coldata$condition)))

bin/plot_dtu_results.R

@@ -5,7 +5,7 @@ suppressMessages(library(ggplot2))
 suppressMessages(library(tidyr))
 
 # Set up sample data frame:
-coldata <- read.csv("de_analysis/coldata.tsv", row.names="sample", sep=",")
+coldata <- read.csv("de_analysis/coldata.tsv", row.names="sample_id", sep=",")
 coldata$sample_id <- rownames(coldata)
 coldata$condition <- factor(coldata$condition, levels=rev(levels(coldata$condition)))
 coldata$type <-NULL

docs/quickstart.md

@@ -124,14 +124,14 @@ Differential Expression requires at least 2 replicates of each sample to compare
 
 #### Condition sheet
 The condition sheet should be a .tsv with two columns.
-- The sample column will need to match the 6 directories in the input fastq directory.
+- The sample_id column will need to match the 6 directories in the input fastq directory, if you are additionally using a sample_sheet they will need to correspond to the sample_ids in that.
 - The condition column will need to contain one of two keys to indicate the two samples being compared.
 
 In the default `condition_sheet.tsv` available in the test_data directory we have used the following.
 
 eg. condition_sheet.tsv
 ```
-sample,condition
+sample_id,condition
 barcode01,untreated
 barcode02,untreated
 barcode03,untreated

main.nf

@@ -471,6 +471,11 @@ workflow pipeline {
                 transcriptome = ref_transcriptome
                 gtf = Channel.fromPath(ref_annotation)
             }
+            check_match = Channel.fromPath(params.condition_sheet)
+            check_condition_sheet = check_match.splitCsv(header: true).map{ row -> tuple(
+                row.sample_id)
+            }
+            check_condition_sheet.join(summariseConcatReads.out.input_reads, failOnMismatch: true)
             de = differential_expression(transcriptome, summariseConcatReads.out.input_reads, condition_sheet, gtf)
             de_report = de.all_de
             count_transcripts_file = de.count_transcripts

test_data/condition_sheet.tsv

@@ -1,6 +1,7 @@
-sample,condition
+sample_id,condition
 barcode01,untreated
 barcode02,untreated
+barcode03,untreated
 barcode04,treated
 barcode05,treated
 barcode06,treated