Merge branch 'cwl_without_docker' into 'main'

Cwl without docker

See merge request brilator/samplearc_rnaseq!10

.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

-
-# cwltool README
-
-## First cd into the (runs) folder, with the .yml file
-
-cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/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
-
-```

runs/kallisto_collect/kallisto_collect.yml

-cores: 1
-r_script:
-  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"
-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

workflows/kallisto_collect.cwl → runs/kallisto_collect/run.cwl

@@ -8,30 +8,26 @@ inputs:
   type: File
   inputBinding:
     position: 0
-- id: arc_root
-  type: string
-  inputBinding:
-    position: 1
 - id: in_kallisto_results
-  type: string
+  type: Directory
   inputBinding:
-    position: 2
+    position: 1
 - id: in_metadata_file
-  type: string
+  type: File
   inputBinding:
-    position: 3
+    position: 2
 - id: in_metadata_sample
   type: string
   inputBinding:
-    position: 4
+    position: 3
 - id: in_metadata_factor
   type: string
   inputBinding:
-    position: 5
+    position: 4
 - id: out_folder
   type: string
   inputBinding:
-    position: 6
+    position: 5
 
 outputs:
 - id: outdir
@@ -42,4 +38,4 @@ outputs:
     glob: $(runtime.outdir)/$(inputs.out_folder)
 
 baseCommand:
-- Rscript
+- Rscript
\ No newline at end of file

runs/kallisto_collect/run.yml

+cores: 1
+r_script:
+  class: File
+  path: ../../workflows/kallisto_collect/kallisto_collect.R
+in_kallisto_results: 
+  class: Directory
+  path: ../kallisto_sleuth/out
+in_metadata_file: 
+  class: File
+  path: ../merged_isa_metadata/out/merged_isa.tsv
+in_metadata_sample: "Sample.Name.2"
+in_metadata_factor: "Factor..Photosynthesis.mode."
+out_folder: out

runs/kallisto_index/README.md

-
-# cwltool README
-
-## First cd into the (runs) folder, with the .yml file
-
-cd /Users/dominikbrilhaus/gitlab_dataplant/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/gitlab_dataplant/samplearc_rnaseq

workflows/kallisto_index.cwl → runs/kallisto_index/run.cwl

@@ -8,12 +8,8 @@ inputs:
   type: File
   inputBinding:
     position: 0
-- id: arc_root
-  type: string
-  inputBinding:
-    position: 1
 - id: in_genome_ref
-  type: string
+  type: File
   inputBinding:
     position: 2
 - id: out_folder
@@ -30,4 +26,4 @@ outputs:
     glob: $(runtime.outdir)/$(inputs.out_folder)
 
 baseCommand:
-- bash
+- bash
\ No newline at end of file

runs/kallisto_index/run.yml

+cores: 1
+sh_script:
+  class: File
+  path: ../../workflows/kallisto_index/kallisto_index.sh
+in_genome_ref:
+  class: File
+  path: ../../studies/TalinumGenomeDraft/resources/Talinum.gm.CDS.nt.fa
+out_folder: ./out

runs/kallisto_quant/README.md

-
-# cwltool README
-
-## First cd into the (runs) folder, with the .yml file
-
-cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/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
-
-```

runs/kallisto_quant/kallisto_quant.yml

-cores: 4
-sh_script:
-  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
-kallisto_bootstrap: 100
-kallisto_threads: 4
-kallisto_fragmentLength: 200
-kallisto_stdDev: 20
\ No newline at end of file

workflows/kallisto_quant.cwl → runs/kallisto_quant/run.cwl

@@ -8,38 +8,34 @@ inputs:
   type: File
   inputBinding:
     position: 0
-- id: arc_root
+- id: out_folder
   type: string
   inputBinding:
     position: 1
-- id: out_folder
-  type: string
+- id: in_kallisto_index
+  type: File
   inputBinding:
     position: 2
-- id: in_kallisto_index
-  type: string
+- id: in_fastq_dir
+  type: Directory
   inputBinding:
     position: 3
-- id: in_fastq_folder
-  type: string
-  inputBinding:
-    position: 4
 - id: kallisto_bootstrap
   type: int
   inputBinding:
-    position: 5
+    position: 4
 - id: kallisto_threads
   type: int
   inputBinding:
-    position: 6
+    position: 5
 - id: kallisto_fragmentLength
   type: int
   inputBinding:
-    position: 7
+    position: 6
 - id: kallisto_stdDev
   type: int
   inputBinding:
-    position: 8
+    position: 7
 
 outputs:
 - id: outdir

runs/kallisto_quant/run.yml

+cores: 4
+sh_script:
+  class: File
+  path: ../../workflows/kallisto_quant/kallisto_quant.sh
+out_folder: ./kallisto_results
+in_kallisto_index:
+  class: File
+  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

runs/kallisto_sleuth/README.md

-
-# cwltool README
-
-## First cd into the (runs) folder, with the .yml file
-
-cd /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/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
-
-```

runs/kallisto_sleuth/kallisto_sleuth.yml

-cores: 1
-r_script:
-  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