diff --git a/runs/deseq2/results_ma-plot.svg b/runs/deseq2/results/results_ma-plot.svg
similarity index 100%
rename from runs/deseq2/results_ma-plot.svg
rename to runs/deseq2/results/results_ma-plot.svg
diff --git a/runs/deseq2/results_pca-plot.svg b/runs/deseq2/results/results_pca-plot.svg
similarity index 100%
rename from runs/deseq2/results_pca-plot.svg
rename to runs/deseq2/results/results_pca-plot.svg
diff --git a/runs/deseq2/results_stats.csv b/runs/deseq2/results/results_stats.csv
similarity index 100%
rename from runs/deseq2/results_stats.csv
rename to runs/deseq2/results/results_stats.csv
diff --git a/runs/deseq2/run.cwl b/runs/deseq2/run.cwl
index e0fdbf42ee4d373eae50a4e3ccf8fc91ac7229ec..0aadd018989bc587f5cef0da02db2b655968adbe 100644
--- a/runs/deseq2/run.cwl
+++ b/runs/deseq2/run.cwl
@@ -2,11 +2,15 @@
cwlVersion: v1.2
class: Workflow
+requirements:
+ SubworkflowFeatureRequirement: {}
+
inputs:
inKallistoResults: Directory
inMetadataFile: File
inMetadataSample: string
inMetadataFactorList: string[]
+ resultsoutdir: string
steps:
deseq2:
@@ -16,12 +20,14 @@ steps:
inMetadataFile: inMetadataFile
inMetadataSample: inMetadataSample
inMetadataFactorList: inMetadataFactorList
- out: [output]
+ finaloutdir: resultsoutdir
+
+ out: [deseq2_outdir]
outputs:
output:
- type: File[]
- outputSource: deseq2/output
+ type: Directory
+ outputSource: deseq2/deseq2_outdir
$namespaces:
s: https://schema.org/
@@ -34,4 +40,4 @@ $schemas:
s:author:
- class: s:Person
s:name: Dominik Brilhaus
- s:identifier: https://orcid.org/0000-0001-9021-3197
\ No newline at end of file
+ s:identifier: https://orcid.org/0000-0001-9021-3197
diff --git a/runs/deseq2/run.yml b/runs/deseq2/run.yml
index b8e9909794f2554784021064e4914996f866bcc2..60e8b8fc310a0aa7b00b44d8fea1bb113eda7cbb 100644
--- a/runs/deseq2/run.yml
+++ b/runs/deseq2/run.yml
@@ -6,4 +6,5 @@ inMetadataFile:
path: ../../runs/isaSampleToRawDataSeq/rnaseq-samples.csv
inMetadataSample: "Input [Source Name]"
inMetadataFactorList:
- - "Factor [Photosynthesis mode]"
\ No newline at end of file
+ - "Factor [Photosynthesis mode]"
+resultsoutdir: results
diff --git a/workflows/deseq2/deseq2.R b/workflows/deseq2/deseq2.R
index dcad6b63d978ab9e6b6f144549f9095f59d8eaa8..b20545ef2ea581426104565ac860aedf3e04faf4 100644
--- a/workflows/deseq2/deseq2.R
+++ b/workflows/deseq2/deseq2.R
@@ -7,13 +7,6 @@ library("tximport")
library("rhdf5")
library("ggplot2")
-# ## Tests
-
-# inKallistoResults <- "../../runs/kallisto/kallisto_results"
-# inMetadataFile <- "../../runs/isaSampleToRawDataSeq/rnaseq-samples.csv"
-# inMetadataSample <- "Input [Source Name]"
-# inMetadataFactorList <- list("Factor [Photosynthesis mode]")
-
### Read arguments from CLI
args <- commandArgs(trailingOnly = T)
diff --git a/workflows/deseq2/deseq2.cwl b/workflows/deseq2/deseq2.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..7087f6fd43d6655b79d79ecfd2a86067759cd3f4
--- /dev/null
+++ b/workflows/deseq2/deseq2.cwl
@@ -0,0 +1,92 @@
+#!/usr/bin/env cwl-runner
+
+doc: |
+ DESeq2 example workflow for **differential gene expression analysis**
+
+ This workflow runs DESeq2 on the output of the kallisto workflow
+ and the metadata file.
+ It runs an R script, deseq2.R, which ideally should be split into three sub scripts and accordingly three workflow steps
+ 1. Read kallsito data
+ 2. Prep / run deseq2
+ 3. Plot results
+
+ ## DESeq2 docs:
+ https://bioconductor.org/packages/release/bioc/html/DESeq2.html
+
+ ## Importing kallisto output with tximport
+ https://bioconductor.org/packages/release/bioc/vignettes/tximport/inst/doc/tximport.html#kallisto
+
+ ## Multi-package containers
+ - R and combinations of library dependencies are available as multi-package containers from [BioContainers](https://github.com/BioContainers/multi-package-containers)
+ - Searched for `repo:BioContainers/multi-package-containers deseq2 tximport rhdf5`
+ - and found `quay.io/biocontainers/mulled-v2-05fd88b9ac812a9149da2f2d881d62f01cc49835:a10f0e3a7a70fc45494f8781d33901086d2214d0-0` :tada:
+
+cwlVersion: v1.2
+class: CommandLineTool
+hints:
+ DockerRequirement:
+ dockerPull: quay.io/biocontainers/mulled-v2-05fd88b9ac812a9149da2f2d881d62f01cc49835:a10f0e3a7a70fc45494f8781d33901086d2214d0-0
+ SoftwareRequirement:
+ packages:
+ - package: R
+ version: [ "4.1.1" ]
+ specs:
+ - https://identifiers.org/rrid/RRID:SCR_001905
+ - https://identifiers.org/biotools/r
+ - https://anaconda.org/bioconda/r
+ - package: DESeq2
+ version: [ "1.34.0" ]
+ specs:
+ - https://identifiers.org/rrid/RRID:SCR_015687
+ - https://identifiers.org/biotools/deseq2
+requirements:
+ - class: InitialWorkDirRequirement
+ listing:
+ - entryname: deseq2.R
+ entry:
+ $include: deseq2.R
+baseCommand: [Rscript, deseq2.R]
+inputs:
+ inKallistoResults:
+ type: Directory
+ inputBinding:
+ position: 1
+ inMetadataFile:
+ type: File
+ inputBinding:
+ position: 2
+ inMetadataSample:
+ type: string
+ inputBinding:
+ position: 3
+ inMetadataFactorList:
+ type: string[]
+ inputBinding:
+ position: 4
+
+outputs:
+ results_stats:
+ type: File
+ outputBinding:
+ glob: "results_stats.csv"
+ results_ma-plot:
+ type: File
+ outputBinding:
+ glob: "results_ma-plot.svg"
+ results_pca-plot:
+ type: File
+ outputBinding:
+ glob: "results_pca-plot.svg"
+
+$namespaces:
+ s: https://schema.org/
+ edam: http://edamontology.org/
+
+$schemas:
+ - https://schema.org/version/latest/schemaorg-current-https.rdf
+ - http://edamontology.org/EDAM_1.25.owl
+
+s:author:
+ - class: s:Person
+ s:name: Dominik Brilhaus
+ s:identifier: https://orcid.org/0000-0001-9021-3197
diff --git a/workflows/deseq2/gather-files.cwl b/workflows/deseq2/gather-files.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..67d23ec72e90012c4e07b2f2ebaf3b2d102308c8
--- /dev/null
+++ b/workflows/deseq2/gather-files.cwl
@@ -0,0 +1,24 @@
+cwlVersion: v1.2
+class: ExpressionTool
+label: Gather files
+doc: |
+ Helper tool to organize workflow outputs
+
+ Takes an array of files (e.g. from a workflow step) and yields them in a destination directory.
+
+ Adapted from: https://github.com/common-workflow-language/cwl-v1.1/blob/a22b7580c6b50e77c0a181ca59d3828dd5c69143/tests/dir7.cwl
+requirements:
+ - class: InlineJavascriptRequirement
+inputs:
+ inFiles: File[]
+ destination: string
+expression: |
+ ${
+ return {"outDir": {
+ "class": "Directory",
+ "basename": inputs.destination,
+ "listing": inputs.inFiles
+ } };
+ }
+outputs:
+ outDir: Directory
\ No newline at end of file
diff --git a/workflows/deseq2/workflow.cwl b/workflows/deseq2/workflow.cwl
index 0f1d68dfbb3bf401270f8f0b49a4706f0f571455..18af3a16861ee832d544e2533d06644c4b406ebb 100644
--- a/workflows/deseq2/workflow.cwl
+++ b/workflows/deseq2/workflow.cwl
@@ -1,62 +1,57 @@
#!/usr/bin/env cwl-runner
-
-doc: |
- DESeq2 example workflow for **differential gene expression analysis**
-
- This workflow runs DESeq2 on the output of the kallisto workflow
- and the metadata file.
- It runs an R script, deseq2.R, which ideally should be split into three sub scripts and accordingly three workflow steps
- 1. Read kallsito data
- 2. Prep / run deseq2
- 3. Plot results
-
- ## DESeq2 docs:
- https://bioconductor.org/packages/release/bioc/html/DESeq2.html
-
- ## Importing kallisto output with tximport
- https://bioconductor.org/packages/release/bioc/vignettes/tximport/inst/doc/tximport.html#kallisto
-
- ## Multi-package containers
- - R and combinations of library dependencies are available as multi-package containers from [BioContainers](https://github.com/BioContainers/multi-package-containers)
- - Searched for `repo:BioContainers/multi-package-containers deseq2 tximport rhdf5`
- - and found `quay.io/biocontainers/mulled-v2-05fd88b9ac812a9149da2f2d881d62f01cc49835:a10f0e3a7a70fc45494f8781d33901086d2214d0-0` :tada:
-
cwlVersion: v1.2
-class: CommandLineTool
-hints:
- DockerRequirement:
- dockerPull: quay.io/biocontainers/mulled-v2-05fd88b9ac812a9149da2f2d881d62f01cc49835:a10f0e3a7a70fc45494f8781d33901086d2214d0-0
+class: Workflow
+
requirements:
- - class: InitialWorkDirRequirement
- listing:
- - entryname: deseq2.R
- entry:
- $include: deseq2.R
- - class: NetworkAccess
- networkAccess: true
-baseCommand: [Rscript, deseq2.R]
+ ScatterFeatureRequirement: {}
+ SubworkflowFeatureRequirement: {}
+ MultipleInputFeatureRequirement: {}
+
inputs:
- inKallistoResults:
+ inKallistoResults: Directory
+ inMetadataFile: File
+ inMetadataSample: string
+ inMetadataFactorList: string[]
+ finaloutdir: string
+
+steps:
+ deseq2:
+ run: deseq2.cwl
+ in:
+ inKallistoResults: inKallistoResults
+ inMetadataFile: inMetadataFile
+ inMetadataSample: inMetadataSample
+ inMetadataFactorList: inMetadataFactorList
+ out:
+ - results_stats
+ - results_ma-plot
+ - results_pca-plot
+ collectFiles:
+ run: ./gather-files.cwl
+ in:
+ inFiles:
+ source:
+ - deseq2/results_stats
+ - deseq2/results_ma-plot
+ - deseq2/results_pca-plot
+ linkMerge: merge_flattened
+ destination: finaloutdir
+ out: [outDir]
+
+outputs:
+ deseq2_outdir:
type: Directory
- inputBinding:
- position: 1
- inMetadataFile:
- type: File
- inputBinding:
- position: 2
- inMetadataSample:
- type: string
- inputBinding:
- position: 3
- inMetadataFactorList:
- type: string[]
- inputBinding:
- position: 4
+ outputSource: collectFiles/outDir
-outputs:
- output:
- type: File[]
- outputBinding:
- glob:
- - "*.svg"
- - "*.csv"
+$namespaces:
+ s: https://schema.org/
+ edam: http://edamontology.org/
+
+$schemas:
+ - https://schema.org/version/latest/schemaorg-current-https.rdf
+ - http://edamontology.org/EDAM_1.18.owl
+
+s:author:
+ - class: s:Person
+ s:name: Dominik Brilhaus
+ s:identifier: https://orcid.org/0000-0001-9021-3197
diff --git a/workflows/sleuth/sleuth.cwl b/workflows/sleuth/sleuth.cwl
index 3ffc997b43ebf3e8525d7828be0197c9cf8d28e0..00a174971c83fd83dd61d7130ccd445e28635e7b 100644
--- a/workflows/sleuth/sleuth.cwl
+++ b/workflows/sleuth/sleuth.cwl
@@ -79,7 +79,7 @@ $namespaces:
$schemas:
- https://schema.org/version/latest/schemaorg-current-https.rdf
- - http://edamontology.org/EDAM_1.18.owl
+ - http://edamontology.org/EDAM_1.25.owl
s:author:
- class: s:Person