Merge branch 'ConvertToCWL' into 'main'

cwl kallisto_index

See merge request brilator/samplearc_rnaseq!5

runs/kallisto_index/README.md

+
+# cwltool README
+
+## First cd into the (runs) folder, with the .yml file
+
+cd /Users/dominikbrilhaus/03_DataPLANT_gitlab/samplearc_rnaseq/runs/kallisto_index
+
+## Let it flow
+
+```bash
+### store arc root (two levels up from here) as variable
+arc_root=$(echo ${PWD%/*/*})
+
+### replace arc root line in yml (specific to the machine from where this is run)
+### not sure, if this works on linux... 
+sed -i '' "s|^arc_root:.*|arc_root: $arc_root|g" kallisto_index.yml
+
+### run with cwltool
+cwltool ../../workflows/kallisto_index.cwl kallisto_index.yml
+
+```

runs/kallisto_index/kallisto_index.yml

+cores: 1
+sh_script:
+  class: File
+  path: ../../workflows/kallisto_index.sh
+in_genome_ref: studies/TalinumGenomeDraft/resources/Talinum.gm.CDS.nt.fa
+out_folder: runs/kallisto_index
+arc_root: /Users/dominikbrilhaus/03_DataPLANT_gitlab/samplearc_rnaseq

workflows/_dependencies/install_kallisto.md

+
+# Kallisto
+
+## Manual
+
+http://pachterlab.github.io/kallisto/manual.html
+
+## MacOS Installation
+
+```bash
+ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)"
+brew install kallisto
+```
+
+```bash
+git clone https://github.com/pachterlab/kallisto.git
+cd kallisto
+mkdir build
+cd build
+cmake  .. -DUSE_HDF5=ON
+```

workflows/_dependencies/install_r_packages.R

+#!/usr/bin/env Rscript
+
+########################
+# Installation of R dependencies
+########################
+
+### sleuth installation
+
+if (!requireNamespace("BiocManager", quietly = TRUE)){install.packages("BiocManager")}
+if(!"BiocManager" %in% row.names(installed.packages())){BiocManager::install()}
+if(!"devtools" %in% row.names(installed.packages())){BiocManager::install("devtools")}
+
+# BiocManager::install("pachterlab/sleuth")
+# There's currently (early 2022) an issue with sleuth installation. 
+# Using this workaround from https://github.com/pachterlab/sleuth/issues/259#issuecomment-1001076030
+
+if(!"sleuth" %in% row.names(installed.packages())){remotes::install_github("pachterlab/sleuth#260")}
+
+library(sleuth)
+
+### other packages
+
+library(tidyverse)
+library(jsonlite)
+library(openxlsx)
+
+required_packages <- 
+  c('tidyverse',  ## data wrangling and plotting
+    'jsonlite',   ## read/write json files
+    'openxlsx')   ## read/write xlsx files
+
+for(package in required_packages)
+{
+  ## Check if package is installed. If not, install
+  if(!package %in% row.names(installed.packages())){install.packages(package,
+                                                                     repos ="https://cran.uni-muenster.de/")}
+  # ## Check if package is up to date. If not, update
+  # update.packages(package, repos = "https://cran.uni-muenster.de/")
+  ## Load package
+  library(package, character.only = T)
+  print(paste("installed R package", package))
+}
+

workflows/kallisto_index.cwl

+#!/usr/bin/env cwl-runner
+
+cwlVersion: v1.2
+class: CommandLineTool
+
+inputs:
+- id: sh_script
+  type: File
+  inputBinding:
+    position: 0
+- id: arc_root
+  type: string
+  inputBinding:
+    position: 1
+- id: in_genome_ref
+  type: string
+  inputBinding:
+    position: 2
+- id: out_folder
+  type: string
+  inputBinding:
+    position: 3
+
+outputs:
+- id: outdir
+  type:
+    type: array
+    items: Directory
+  outputBinding:
+    glob: $(runtime.outdir)/$(inputs.out_folder)
+
+baseCommand:
+- bash
\ No newline at end of file

workflows/kallisto_index.sh

+#!/usr/bin/env bash
+
+### Build kallisto index 
+
+################################################
+#### Read arguments from CLI
+################################################
+
+arc_root=$1
+in_genome_ref=$2
+out_folder=$3
+
+################################################
+#### Print version and citation to test kallisto 
+################################################
+
+kallisto version
+kallisto cite
+
+################################################
+#### If it does not exist, create out dir
+################################################
+
+mkdir -p "$arc_root/$out_folder/"
+
+
+################################################
+#### Build kallisto index
+################################################
+
+kallisto index -i "$arc_root/$out_folder/kallisto_index" "$arc_root/$in_genome_ref"