Merge branch 'docker_integration' into 'cwl_docker_adrian'

Docker integration

See merge request brilator/samplearc_rnaseq!9

.gitattributes

@@ -5,4 +5,4 @@
 /assays/Talinum_RNASeq_minimal/dataset/DB_103_CAMMD_AGTCAA_L001_R1_001.fastq.gz filter=lfs diff=lfs merge=lfs -text
 /assays/Talinum_RNASeq_minimal/dataset/DB_161_reC3MD_GTCCGC_L001_R1_001.fastq.gz filter=lfs diff=lfs merge=lfs -text
 /assays/Talinum_RNASeq_minimal/dataset/DB_165_re-C3MD_GTGAAA_L002_R1_001.fastq.gz filter=lfs diff=lfs merge=lfs -text
-/runs/kallisto_index/kallisto_index filter=lfs diff=lfs merge=lfs -text
+/runs/kallisto_index/out/kallisto_index filter=lfs diff=lfs merge=lfs -text

runs/kallisto_collect/README.md

@@ -3,19 +3,11 @@
 
 ## First cd into the (runs) folder, with the .yml file
 
-cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/kallisto_collect
+cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq_adrian/runs/kallisto_collect
 
 ## 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_collect.yml
-
 ### run with cwltool
-cwltool ../../workflows/kallisto_collect.cwl kallisto_collect.yml
-
+cwltool run.cwl kallisto_collect.yml
 ```

runs/kallisto_collect/kallisto_collect.yml

 cores: 1
-r_script:
+in_kallisto_results: 
+  class: Directory
+  path: ../kallisto_sleuth/out
+in_metadata_file: 
   class: File
-  path: ../../workflows/kallisto_collect.R
-in_kallisto_results: "runs/no_CWL_yet/kallisto_sleuth/run1/01_kallisto_results"
-in_metadata_file: "runs/merged_isa_metadata/merged_isa.tsv"
+  path: ../merged_isa_metadata/merged_isa.tsv
 in_metadata_sample: "Sample.Name.2"
 in_metadata_factor: "Factor..Photosynthesis.mode."
-out_folder: runs/kallisto_collect
-arc_root: /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq
\ No newline at end of file
+out_folder: out

runs/kallisto_collect/run.cwl

+#!/usr/bin/env cwl-runner
+cwlVersion: v1.2
+class: Workflow
+inputs:
+  in_kallisto_results:
+    type: Directory
+  in_metadata_file:
+    type: File
+  in_metadata_sample:
+    type: string
+  in_metadata_factor:
+    type: string
+  out_folder:
+    type: string
+outputs:
+  out_dir:
+    type:
+      type: array
+      items: Directory
+    outputSource: kallisto_collect/outdir
+steps:
+  kallisto_collect:
+    run: ../../workflows/kallisto_collect/workflow.cwl
+    in:
+      in_kallisto_results: in_kallisto_results
+      in_metadata_file: in_metadata_file
+      in_metadata_sample: in_metadata_sample
+      in_metadata_factor: in_metadata_factor
+      out_folder: out_folder
+    out: [outdir]

runs/kallisto_index/README.md

@@ -3,19 +3,11 @@
 
 ## First cd into the (runs) folder, with the .yml file
 
-cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/kallisto_index
+cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq_adrian/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
-
+cwltool run.cwl kallisto_index.yml
 ```

runs/kallisto_index/kallisto_index.yml

 cores: 1
-sh_script:
+in_genome_ref:
   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/gitlab_dataplant/samplearc_rnaseq
+  path: ../../studies/TalinumGenomeDraft/resources/Talinum.gm.CDS.nt.fa
+out_folder: ./out

runs/kallisto_index/run.cwl

+#!/usr/bin/env cwl-runner
+cwlVersion: v1.2
+class: Workflow
+inputs:
+  in_genome_ref:
+    type: File
+  out_folder:
+    type: string
+outputs:
+  out_dir:
+    type:
+      type: array
+      items: Directory
+    outputSource: kallisto_index/outdir
+steps:
+  kallisto_index:
+    run: ../../workflows/kallisto_index/workflow.cwl
+    in:
+      in_genome_ref: in_genome_ref
+      out_folder: out_folder
+    out: [outdir]

runs/kallisto_quant/README.md

@@ -3,19 +3,11 @@
 
 ## First cd into the (runs) folder, with the .yml file
 
-cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/kallisto_quant
+cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq_adrian/runs/kallisto_quant
 
 ## 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_quant.yml
-
 ### run with cwltool
-cwltool ../../workflows/kallisto_quant.cwl kallisto_quant.yml
-
+cwltool run.cwl kallisto_quant.yml
 ```

runs/kallisto_quant/kallisto_quant.yml

 cores: 4
-sh_script:
+out_folder: ./kallisto_results
+in_kallisto_index:
   class: File
-  path: ../../workflows/kallisto_quant.sh
-arc_root: /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq
-out_folder: runs/kallisto_quant/kallisto_results
-in_kallisto_index: runs/kallisto_index/kallisto_index
-in_fastq_folder: assays/Talinum_RNASeq_minimal/dataset
+  path: ../kallisto_index/out/kallisto_index
+in_fastq_dir: 
+  class: Directory
+  path: ../../assays/Talinum_RNASeq_minimal/dataset
 kallisto_bootstrap: 100
 kallisto_threads: 4
 kallisto_fragmentLength: 200
-kallisto_stdDev: 20
\ No newline at end of file
+kallisto_stdDev: 20

runs/kallisto_quant/run.cwl

+#!/usr/bin/env cwl-runner
+cwlVersion: v1.2
+class: Workflow
+inputs:
+  out_folder:
+    type: string
+  in_kallisto_index:
+    type: File
+  in_fastq_dir:
+    type: Directory
+  kallisto_bootstrap:
+    type: int
+  kallisto_threads:
+    type: int
+  kallisto_fragmentLength:
+    type: int
+  kallisto_stdDev:
+    type: int
+outputs:
+  out_dir:
+    type:
+      type: array
+      items: Directory
+    outputSource: kallisto_quant/outdir
+steps:
+  kallisto_quant:
+    run: ../../workflows/kallisto_quant/workflow.cwl
+    in:
+      out_folder: out_folder
+      in_kallisto_index: in_kallisto_index
+      in_fastq_dir: in_fastq_dir
+      kallisto_bootstrap: kallisto_bootstrap
+      kallisto_threads: kallisto_threads
+      kallisto_fragmentLength: kallisto_fragmentLength
+      kallisto_stdDev: kallisto_stdDev
+    out: [outdir]

runs/kallisto_sleuth/README.md

@@ -3,19 +3,11 @@
 
 ## First cd into the (runs) folder, with the .yml file
 
-cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/kallisto_sleuth
+cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq_adrian/runs/kallisto_sleuth
 
 ## 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_sleuth.yml
-
 ### run with cwltool
-cwltool ../../workflows/kallisto_sleuth.cwl kallisto_sleuth.yml
-
+cwltool run.cwl kallisto_sleuth.yml
 ```

runs/kallisto_sleuth/kallisto_sleuth.yml

 cores: 1
-r_script:
+in_sleuth:
   class: File
-  path: ../../workflows/kallisto_sleuth.R
-in_sleuth: runs/kallisto_collect/kallisto_sleuthObject.RData
-out_folder: runs/kallisto_sleuth
-arc_root: /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq
\ No newline at end of file
+  path: ../kallisto_collect/kallisto_sleuthObject.RData
+out_folder: out

runs/kallisto_sleuth/run.cwl

+#!/usr/bin/env cwl-runner
+cwlVersion: v1.2
+class: Workflow
+inputs:
+  in_sleuth:
+    type: File
+  out_folder:
+    type: string
+outputs:
+  out_dir:
+    type:
+      type: array
+      items: Directory
+    outputSource: kallisto_sleuth/outdir
+steps:
+  kallisto_sleuth:
+    run: ../../workflows/kallisto_sleuth/workflow.cwl
+    in:
+      in_sleuth: in_sleuth
+      out_folder: out_folder
+    out: [outdir]

runs/merged_isa_metadata/README.md

@@ -3,21 +3,12 @@
 
 ## First cd into the (runs) folder, with the .yml file
 
-cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/merged_isa_metadata
+cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq_adrian/runs/merged_isa_metadata
 
 
 ## 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" merge_isa_metadata.yml
-
 ### run with cwltool
-cwltool ../../workflows/merge_isa_metadata.cwl merge_isa_metadata.yml
-
+cwltool run.cwl merge_isa_metadata.yml
 ```

runs/merged_isa_metadata/merge_isa_metadata.yml

 cores: 1
-r_script:
+in_isa_study: 
   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/gitlab_dataplant/samplearc_rnaseq
\ No newline at end of file
+  path: ../../studies/TalinumFacultativeCAM/isa.study.xlsx
+in_isa_assay: 
+  class: File
+  path: ../../assays/Talinum_RNASeq_minimal/isa.assay.xlsx
+out_folder: out

runs/merged_isa_metadata/run.cwl

+#!/usr/bin/env cwl-runner
+cwlVersion: v1.2
+class: Workflow
+inputs:
+  in_isa_study:
+    type: File
+  in_isa_assay:
+    type: File
+  out_folder:
+    type: string
+outputs:
+  out_dir:
+    type:
+      type: array
+      items: Directory
+    outputSource: merge_isa_metadata/outdir
+steps:
+  merge_isa_metadata:
+    run: ../../workflows/merge_isa_metadata/workflow.cwl
+    in:
+      in_isa_study: in_isa_study
+      in_isa_assay: in_isa_assay
+      out_folder: out_folder
+    out: [outdir]

runs/shiny_prep/README.md

@@ -3,19 +3,11 @@
 
 ## First cd into the (runs) folder, with the .yml file
 
-cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/kallisto_sleuth
+cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq_adrian/runs/shiny_prep
 
 ## 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_sleuth.yml
-
 ### run with cwltool
-cwltool ../../workflows/kallisto_sleuth.cwl kallisto_sleuth.yml
-
+cwltool run.cwl shiny_prep.yml
 ```