From 85178ec6baba442caef061c19a052e6c265cc2d0 Mon Sep 17 00:00:00 2001
From: Dominik Brilhaus <dominik.brilhaus@hhu.de>
Date: Tue, 9 Aug 2022 10:39:36 +0200
Subject: [PATCH] there must be a better way for that arcRoot
---
runs/merged_isa_metadata/README.md | 24 ++++++++++++++++++-
.../merge_isa_metadata.yml | 2 --
.../merge_isa_metadata_rooted.yml | 8 +++++++
workflows/merge_isa_metadata.R | 17 ++++++-------
4 files changed, 38 insertions(+), 13 deletions(-)
create mode 100644 runs/merged_isa_metadata/merge_isa_metadata_rooted.yml
diff --git a/runs/merged_isa_metadata/README.md b/runs/merged_isa_metadata/README.md
index ceeaf9b..9319c2e 100644
--- a/runs/merged_isa_metadata/README.md
+++ b/runs/merged_isa_metadata/README.md
@@ -1,4 +1,26 @@
+# cwltool README
+## First cd into the (runs) folder, with the .yml file
-cwltool ../../workflows/merge_isa_metadata.cwl merge_isa_metadata.yml
\ No newline at end of file
+cd /Users/dominikbrilhaus/03_DataPLANT_gitlab/samplearc_rnaseq/runs/merged_isa_metadata
+
+## Let it flow
+
+```bash
+
+### store arc root (two levels up from here) as variable
+arc_root=$(echo ${PWD%/*/*})
+
+# arc_root=/Users/dominikbrilhaus/03_DataPLANT_gitlab/samplearc_rnaseq/
+
+### write a temporary yml
+cat merge_isa_metadata.yml > merge_isa_metadata_rooted.yml
+
+### add the arc root to that yml
+printf "\narc_root: $arc_root\n" >> merge_isa_metadata_rooted.yml
+
+### run with cwltool
+cwltool ../../workflows/merge_isa_metadata.cwl merge_isa_metadata_rooted.yml
+
+```
diff --git a/runs/merged_isa_metadata/merge_isa_metadata.yml b/runs/merged_isa_metadata/merge_isa_metadata.yml
index 0a2a9fd..450d89f 100644
--- a/runs/merged_isa_metadata/merge_isa_metadata.yml
+++ b/runs/merged_isa_metadata/merge_isa_metadata.yml
@@ -2,8 +2,6 @@ cores: 1
r_script:
class: File
path: ../../workflows/merge_isa_metadata.R
-# arc_root: ../
-arc_root: /Users/dominikbrilhaus/03_DataPLANT_gitlab/samplearc_rnaseq/
in_isa_study: studies/TalinumFacultativeCAM/isa.study.xlsx:plant_growth
in_isa_assay: assays/Talinum_RNASeq_minimal/isa.assay.xlsx:2EXT01_RNA:3ASY01_RNASeq
out_folder: runs/merged_isa_metadata
\ No newline at end of file
diff --git a/runs/merged_isa_metadata/merge_isa_metadata_rooted.yml b/runs/merged_isa_metadata/merge_isa_metadata_rooted.yml
new file mode 100644
index 0000000..2f282e0
--- /dev/null
+++ b/runs/merged_isa_metadata/merge_isa_metadata_rooted.yml
@@ -0,0 +1,8 @@
+cores: 1
+r_script:
+ class: File
+ path: ../../workflows/merge_isa_metadata.R
+in_isa_study: studies/TalinumFacultativeCAM/isa.study.xlsx:plant_growth
+in_isa_assay: assays/Talinum_RNASeq_minimal/isa.assay.xlsx:2EXT01_RNA:3ASY01_RNASeq
+out_folder: runs/merged_isa_metadata
+arc_root: /Users/dominikbrilhaus/03_DataPLANT_gitlab/samplearc_rnaseq
diff --git a/workflows/merge_isa_metadata.R b/workflows/merge_isa_metadata.R
index c629683..50746cd 100644
--- a/workflows/merge_isa_metadata.R
+++ b/workflows/merge_isa_metadata.R
@@ -26,8 +26,6 @@ in_isa_study <- args[2]
in_isa_assay <- args[3]
out_folder <- args[4]
-# setwd(arc_root)
-
################################################
#### Read metadata from isa excel workbooks
################################################
@@ -36,12 +34,12 @@ isa_study <- unlist(strsplit(paste(arc_root, in_isa_study, sep = "/"), split = "
isa_assay <- unlist(strsplit(paste(arc_root, in_isa_assay, sep = "/"), split = ":"))
isa_sheets <- list()
-for(i in 2:length(isa_study))
+for (i in 2:length(isa_study))
{
isa_sheets[[length(isa_sheets) + 1]] <- readWorkbook(isa_study[1], isa_study[i], startRow = 1)
}
-for(i in 2:length(isa_assay))
+for (i in 2:length(isa_assay))
{
isa_sheets[[length(isa_sheets) + 1]] <- readWorkbook(isa_assay[1], isa_assay[i], startRow = 1)
}
@@ -52,20 +50,19 @@ for(i in 2:length(isa_assay))
isa_merged <- isa_sheets[[1]]
-for(j in 2:length(isa_sheets))
+for (j in 2:length(isa_sheets))
# for(j in 2)
{
isa_merged <- merge(isa_merged,
- isa_sheets[[j]],
- by.x = "Sample.Name",
- by.y = "Source.Name",
+ isa_sheets[[j]],
+ by.x = "Sample.Name",
+ by.y = "Source.Name",
)
# Rename duplicated Sample.Name column
colnames(isa_merged)[which(colnames(isa_merged) == "Sample.Name")] <- paste("Sample.Name", j, sep = ".")
colnames(isa_merged)[which(colnames(isa_merged) == "Sample.Name.y")] <- "Sample.Name"
-
}
@@ -87,4 +84,4 @@ dir.create(paste(arc_root, out_folder, sep = "/"), recursive = T, showWarnings =
#### Write table to file
################################################
-write.table(isa_merged, file = paste(arc_root, out_folder, "merged_isa.tsv", sep = "/"), sep = "\t")
\ No newline at end of file
+write.table(isa_merged, file = paste(arc_root, out_folder, "merged_isa.tsv", sep = "/"), sep = "\t")
--
GitLab