diff --git a/README.md b/README.md
index 7a6343fa29335b865c7a5cde87056a9934162cdb..0fc960c4032ab95cfe4dc5efc5aedcdc40cfe494 100644
--- a/README.md
+++ b/README.md
@@ -91,4 +91,12 @@ DB_161 \
DB_163 \
DB_165
cd $arc_root
-```
\ No newline at end of file
+```
+
+## Make workflows a bit more representative and reproducible (24.03.2022)
+
+## generate a common arc_root pointer
+
+```bash
+echo "~/03DataPLANT_gitlab/samplearc_rnaseq/" > workflows/_arc_local_wd
+```
diff --git a/assays/Talinum_RNASeq_minimal/README.md b/assays/Talinum_RNASeq_minimal/README.md
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/assays/Talinum_RNASeq_minimal/isa.assay.xlsx b/assays/Talinum_RNASeq_minimal/isa.assay.xlsx
index 3e2dc03464a66d388eeb2dd3b6aafe7f8ca214b0..972482f26819554c1205dea5173d66ca2e5b9af4 100644
Binary files a/assays/Talinum_RNASeq_minimal/isa.assay.xlsx and b/assays/Talinum_RNASeq_minimal/isa.assay.xlsx differ
diff --git a/assays/Talinum_RNASeq_minimal/protocols/README.md b/assays/Talinum_RNASeq_minimal/protocols/README.md
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/assays/Talinum_RNASeq_minimal/protocols/02_RNAex_libraries.md b/assays/Talinum_RNASeq_minimal/protocols/RNAex_libraries.md
similarity index 100%
rename from assays/Talinum_RNASeq_minimal/protocols/02_RNAex_libraries.md
rename to assays/Talinum_RNASeq_minimal/protocols/RNAex_libraries.md
diff --git a/studies/TalinumFacultativeCAM/README.md b/studies/TalinumFacultativeCAM/README.md
deleted file mode 100644
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..0000000000000000000000000000000000000000
diff --git a/studies/TalinumFacultativeCAM/protocols/01_plant_material.md b/studies/TalinumFacultativeCAM/protocols/plant_material.md
similarity index 100%
rename from studies/TalinumFacultativeCAM/protocols/01_plant_material.md
rename to studies/TalinumFacultativeCAM/protocols/plant_material.md
diff --git a/studies/TalinumGenomeDraft/isa.study.xlsx b/studies/TalinumGenomeDraft/isa.study.xlsx
index 0019946e56767e3aa5a2bd47735e9b9a5f9df58e..a12118f2e0c76cb2611156271ad11f47f1bd6a25 100644
Binary files a/studies/TalinumGenomeDraft/isa.study.xlsx and b/studies/TalinumGenomeDraft/isa.study.xlsx differ
diff --git a/workflows/.Rhistory b/workflows/.Rhistory
deleted file mode 100644
index 2682a56b8b7906d6b98e05c70905cc6584d6c11f..0000000000000000000000000000000000000000
--- a/workflows/.Rhistory
+++ /dev/null
@@ -1 +0,0 @@
-ARC_root="~/03_DataPLANT_gitlab/samplearc_rnaseq/"
diff --git a/workflows/01_KallistoQuant.sh b/workflows/01_KallistoQuant.sh
index 5cb91b5a2c750299f29c5fac895a7b26b0d6d858..c63f4647df1232f6a847f964b318953ba9f9e3d8 100644
--- a/workflows/01_KallistoQuant.sh
+++ b/workflows/01_KallistoQuant.sh
@@ -3,11 +3,12 @@
#### To be replaced by CWL routine
########################
-ARC_root=~/samplearc_rnaseq/
-cd $ARC_root'workflows/'
-
+# Execute within <ARC root>/workflows
# chmod a+x 01_KallistoQuant.sh
# ./01_KallistoQuant.sh > $ARC_root'runs/01_kallisto.log' 2>&1 &
+# pointers to and from `runs` need to be replaced
+
+ARC_root=$(cat ./_arc_local_wd)
########################
@@ -21,7 +22,7 @@ kallisto cite
### Build index
-kall_ref=$ARC_root'externals/Talinum.gm.CDS.nt.fa'
+kall_ref=$ARC_root'studies/TalinumGenomeDraft/resources/Talinum.gm.CDS.nt.fa'
kallisto index -i $ARC_root'runs/01_kallisto_index' $kall_ref
### Align reads
@@ -32,11 +33,11 @@ mkdir $ARC_root'/runs/01_kallisto_results/'
for j in $ILLUMINASAMPLES; do
- sampleName=$(echo $j | sed -e 's|.*/||' | cut -c -6) # cut away path. retain only first six chars of file name
- echo $sampleName
-
- kallisto quant --single -b 100 -t 30 -l 200 -s 20 -i $ARC_root'/runs/01_kallisto_index' -o $ARC_root'/runs/01_kallisto_results/'$sampleName $j
+ sampleName=$(echo $j | sed -e 's|.*/||' | cut -c -6) # cut away path. retain only first six chars of file name
+ echo $sampleName
+
+ kallisto quant --single -b 100 -t 30 -l 200 -s 20 -i $ARC_root'/runs/01_kallisto_index' -o $ARC_root'/runs/01_kallisto_results/'$sampleName $j
- echo 'Kallisto done'
+ echo 'Kallisto done'
done
\ No newline at end of file
diff --git a/workflows/03_KallistoCollect.R b/workflows/03_KallistoCollect.R
index 796a61218717e37e36b59cb01da0e0f5c738e875..a103b38f3e9c422bd1550f867cf259e670be1237 100644
--- a/workflows/03_KallistoCollect.R
+++ b/workflows/03_KallistoCollect.R
@@ -4,8 +4,12 @@
#### To be replaced by CWL routine
########################
-ARC_root="~/Hackathon_ARCexample_rnaseq/"
-setwd(paste0(ARC_root, 'workflows/'))
+# Execute within <ARC root>/workflows
+# Rscript 03_KallistoCollect.R
+# pointers to and from `runs` need to be replaced
+
+ARC_root=readLines("./_arc_local_wd")
+
########################
@@ -29,23 +33,29 @@ library(openxlsx)
## read experimental metadata from isa.assay wb
-isa_assay <- paste0(ARC_root, 'assays/Talinum_RNASeq_minimal/assay.isa.xlsx')
+isa_assay <- paste0(ARC_root, 'assays/Talinum_RNASeq_minimal/isa.assay.xlsx')
+isa_study <- paste0(ARC_root, 'studies/TalinumFacultativeCAM/isa.study.xlsx')
-assay_data <- merge(readWorkbook(isa_assay, "1SPL01_plants", startRow = 2),
- readWorkbook(isa_assay, "3ASY01_RNASeq", startRow = 2),
- by = "Sample.Name"
+study_data <- readWorkbook(isa_study, "plant_growth", startRow = 1)
+
+assay_data <- merge(readWorkbook(isa_assay, "2EXT01_RNA", startRow = 1),
+ readWorkbook(isa_assay, "3ASY01_RNASeq", startRow = 1),
+ by.x = "Sample.Name",
+ by.y = "Source.Name"
)
+assay_data <- merge(study_data, assay_data, by.x = "Sample.Name", by.y = "Source.Name")
+
## remove empty cols
assay_data <- assay_data[, !apply(assay_data, 2, function(x){sum(is.na(x)) == nrow(assay_data)})]
# Pointer to kallisto results folder
-base_dir <- paste0(ARC_root, '/runs/01_kallisto_results/')
+base_dir <- paste0(ARC_root, 'runs/01_kallisto_results/')
# A list of paths to the kallisto results indexed by the sample IDs is collated with
kal_dirs <- dir(base_dir, full.names = T) ## Sleuth requires full paths
-s2c <- assay_data[order(assay_data$Sample.Name), c('Sample.Name', "Characteristics.[Photosynthesis.mode]")]
+s2c <- assay_data[order(assay_data$Sample.Name), c('Sample.Name', "Factor.[Photosynthesis.mode]")]
# For kallisto / sleuth: 's2c' (sample_to_covariates) must contain a column named 'sample'
colnames(s2c) <- c("sample", "Photosynthesis.mode")
diff --git a/workflows/04_Sleuth.R b/workflows/04_Sleuth.R
index ab2f5791cc20d8343cee2f934443d87b5e317c8e..97894a987cea97fea991ce67b889f70544a637f0 100644
--- a/workflows/04_Sleuth.R
+++ b/workflows/04_Sleuth.R
@@ -4,8 +4,11 @@
#### To be replaced by CWL routine
########################
-ARC_root="~/Hackathon_ARCexample_rnaseq/"
-setwd(paste0(ARC_root, 'workflows/'))
+# Execute within <ARC root>/workflows
+# Rscript 04_Sleuth.R
+# pointers to and from `runs` need to be replaced
+
+ARC_root=readLines("./_arc_local_wd")
########################
diff --git a/workflows/05_plot_shinyPrep.R b/workflows/05_plot_shinyPrep.R
index e0b2fe554819c1c0f21057a7cf283c021319de3f..075c567040119d7ce18e546a49accca8af4494b5 100644
--- a/workflows/05_plot_shinyPrep.R
+++ b/workflows/05_plot_shinyPrep.R
@@ -4,8 +4,11 @@
#### To be replaced by CWL routine
########################
-ARC_root="~/Hackathon_ARCexample_rnaseq/"
-setwd(paste0(ARC_root, 'workflows/'))
+# Execute within <ARC root>/workflows
+# Rscript 05_plot_shinyPrep.R
+# pointers to and from `runs` need to be replaced
+
+ARC_root=readLines("./_arc_local_wd")
########################
diff --git a/workflows/_arc_local_wd b/workflows/_arc_local_wd
new file mode 100644
index 0000000000000000000000000000000000000000..aca1e009538a1e623f7c13a9f169d4a707c39a6b
--- /dev/null
+++ b/workflows/_arc_local_wd
@@ -0,0 +1 @@
+~/03DataPLANT_gitlab/samplearc_rnaseq/