Merge branch 'cwl' into 'main'

Cwl

See merge request !1

runs/kallisto/single-steps/README.md

+# Kallisto
+
+## Executing individual steps
+
+### Create genome index
+
+```bash
+cwltool ../../../workflows/kallisto/kallisto-index.cwl index.yml
+
+```
+
+### Quantification of a single sample
+
+```bash
+cwltool ../../../workflows/kallisto/kallisto-quant.cwl quant.yml
+```

runs/kallisto/single-steps/index.yml

+InputFiles:
+  - class: File
+    path: ../../../studies/TalinumGenomeDraft/resources/Talinum.gm.CDS.nt.fa
+    format: edam:format_1929 # FASTA
+IndexName: "Talinum.gm.CDS"
+
+$namespaces:
+  edam: https://edamontology.org/
\ No newline at end of file

runs/kallisto/single-steps/quant.yml

+InputReads: 
+  - class: File
+    path: ../../../assays/Talinum_RNASeq_minimal/dataset/DB_097_CAMMD_CAGATC_L001_R1_001.fastq.gz
+    format: edam:format_1930 # FASTA
+QuantOutfolder: DB_097
+Index:
+  class: File
+  path: ./Talinum.gm.CDS.kallistoIndex
+isSingle: true
+FragmentLength: 200
+StandardDeviation: 20
+BootstrapSamples: 30
+
+$namespaces:
+  edam: https://edamontology.org/
\ No newline at end of file

runs/kallisto/workflow.yml

+## Genome file to build kallisto Index
+IndexInput:
+  - class: File
+    path: ../../studies/TalinumGenomeDraft/resources/Talinum.gm.CDS.nt.fa
+    format: edam:format_1929 # FASTA
+
+## Fastq files to be mapped
+# The `InputReadsMultipleSamples` looks more complicated than needed
+# It's an array of File arrays to generically allow multiple fastq files per sample
+
+InputReadsMultipleSamples:
+  - 
+    - class: File
+      path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_097_CAMMD_CAGATC_L001_R1_001.fastq.gz
+      format: edam:format_1930 # FASTQ
+  - 
+    - class: File
+      path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_099_CAMMD_CTTGTA_L001_R1_001.fastq.gz
+      format: edam:format_1930 # FASTQ
+  - 
+    - class: File
+      path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_103_CAMMD_AGTCAA_L001_R1_001.fastq.gz
+      format: edam:format_1930 # FASTQ
+  - 
+    - class: File
+      path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_161_reC3MD_GTCCGC_L001_R1_001.fastq.gz
+      format: edam:format_1930 # FASTQ
+  - 
+    - class: File
+      path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_163_reC3MD_GTGAAA_L001_R1_001.fastq.gz
+      format: edam:format_1930 # FASTQ
+  - 
+    - class: File
+      path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_165_re-C3MD_GTGAAA_L002_R1_001.fastq.gz
+      format: edam:format_1930 # FASTQ
+
+### Kallisto quant Parameters
+isSingle: true
+FragmentLength: 200
+StandardDeviation: 20
+BootstrapSamples: 30
+
+resultsFolder: kallisto_results
+
+$namespaces:
+  edam: https://edamontology.org/
\ No newline at end of file

runs/kallisto_collect/README.md

+
+
+```bash
+cd runs/kallisto_collect/
+cwltool ../../workflows/kallisto_collect/kallisto_collect.cwl run.yml > $(date +"%Y-%m-%d_%H-%M").log 2>&1 &
+```

runs/kallisto_collect/run.yml

-cores: 1
-r_script:
-  class: File
-  path: ../../workflows/kallisto_collect/kallisto_collect.R
-in_kallisto_results: 
+in_kallisto_results:
   class: Directory
-  path: ../kallisto_sleuth/out
+  path: ../runs/kallisto/kallisto_results
 in_metadata_file: 
   class: File
   path: ../merged_isa_metadata/out/merged_isa.tsv

runs/kallisto_index/run.cwl

-#!/usr/bin/env cwl-runner
-
-cwlVersion: v1.2
-class: CommandLineTool
-
-inputs:
-- id: sh_script
-  type: File
-  inputBinding:
-    position: 0
-- id: in_genome_ref
-  type: File
-  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

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/kallisto_results/DB_097_CAMMD_CAGATC_L001_R1_001/run_info.json

-{
-	"n_targets": 31434,
-	"n_bootstraps": 100,
-	"n_processed": 11071656,
-	"n_pseudoaligned": 7663654,
-	"n_unique": 7522185,
-	"p_pseudoaligned": 69.2,
-	"p_unique": 67.9,
-	"kallisto_version": "0.48.0",
-	"index_version": 10,
-	"start_time": "Wed Aug 10 18:21:29 2022",
-	"call": "kallisto quant --single -b 100 -t 4 -l 200 -s 20 -i /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/kallisto_index/kallisto_index -o /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/kallisto_quant/kallisto_results/DB_097_CAMMD_CAGATC_L001_R1_001 /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/assays/Talinum_RNASeq_minimal/dataset/DB_097_CAMMD_CAGATC_L001_R1_001.fastq.gz"
-}

runs/kallisto_quant/kallisto_results/DB_099_CAMMD_CTTGTA_L001_R1_001/run_info.json

-{
-	"n_targets": 31434,
-	"n_bootstraps": 100,
-	"n_processed": 14332278,
-	"n_pseudoaligned": 10066506,
-	"n_unique": 9848811,
-	"p_pseudoaligned": 70.2,
-	"p_unique": 68.7,
-	"kallisto_version": "0.48.0",
-	"index_version": 10,
-	"start_time": "Wed Aug 10 18:22:23 2022",
-	"call": "kallisto quant --single -b 100 -t 4 -l 200 -s 20 -i /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/kallisto_index/kallisto_index -o /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/kallisto_quant/kallisto_results/DB_099_CAMMD_CTTGTA_L001_R1_001 /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/assays/Talinum_RNASeq_minimal/dataset/DB_099_CAMMD_CTTGTA_L001_R1_001.fastq.gz"
-}

runs/kallisto_quant/kallisto_results/DB_103_CAMMD_AGTCAA_L001_R1_001/run_info.json

-{
-	"n_targets": 31434,
-	"n_bootstraps": 100,
-	"n_processed": 13083957,
-	"n_pseudoaligned": 9007720,
-	"n_unique": 8828236,
-	"p_pseudoaligned": 68.8,
-	"p_unique": 67.5,
-	"kallisto_version": "0.48.0",
-	"index_version": 10,
-	"start_time": "Wed Aug 10 18:23:36 2022",
-	"call": "kallisto quant --single -b 100 -t 4 -l 200 -s 20 -i /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/kallisto_index/kallisto_index -o /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/runs/kallisto_quant/kallisto_results/DB_103_CAMMD_AGTCAA_L001_R1_001 /Users/dominikbrilhaus/gitlab_dataplant/samplearc_rnaseq/assays/Talinum_RNASeq_minimal/dataset/DB_103_CAMMD_AGTCAA_L001_R1_001.fastq.gz"
-}