From 68c1747104810cc8c58f73d9088990b425ca17d0 Mon Sep 17 00:00:00 2001
From: Dominik Brilhaus <brilhaus@nfdi4plants.org>
Date: Fri, 2 Aug 2024 10:15:05 +0200
Subject: [PATCH] restructure kallisto pipeline
---
.../Talinum_RNASeq_minimal/dataset/.gitkeep | 0
runs/{kallisto_quant => kallisto}/run.yml | 6 +
runs/kallisto_index/run.yml | 8 -
workflows/kallisto/README.md | 7 +
workflows/kallisto/kallisto-index.cwl | 63 ++++++++
workflows/kallisto/kallisto-quant.cwl | 137 ++++++++++++++++++
workflows/kallisto/kallisto-workflow.cwl | 44 ++++++
7 files changed, 257 insertions(+), 8 deletions(-)
delete mode 100644 assays/Talinum_RNASeq_minimal/dataset/.gitkeep
rename runs/{kallisto_quant => kallisto}/run.yml (78%)
delete mode 100644 runs/kallisto_index/run.yml
create mode 100644 workflows/kallisto/README.md
create mode 100644 workflows/kallisto/kallisto-index.cwl
create mode 100755 workflows/kallisto/kallisto-quant.cwl
create mode 100644 workflows/kallisto/kallisto-workflow.cwl
diff --git a/assays/Talinum_RNASeq_minimal/dataset/.gitkeep b/assays/Talinum_RNASeq_minimal/dataset/.gitkeep
deleted file mode 100644
index e69de29..0000000
diff --git a/runs/kallisto_quant/run.yml b/runs/kallisto/run.yml
similarity index 78%
rename from runs/kallisto_quant/run.yml
rename to runs/kallisto/run.yml
index 09afef4..269c202 100644
--- a/runs/kallisto_quant/run.yml
+++ b/runs/kallisto/run.yml
@@ -13,3 +13,9 @@ kallisto_bootstrap: 100
kallisto_threads: 4
kallisto_fragmentLength: 200
kallisto_stdDev: 20
+
+
+
+in_genome_ref:
+ class: File
+ path: ../../studies/TalinumGenomeDraft/resources/Talinum.gm.CDS.nt.fa
\ No newline at end of file
diff --git a/runs/kallisto_index/run.yml b/runs/kallisto_index/run.yml
deleted file mode 100644
index df0c070..0000000
--- a/runs/kallisto_index/run.yml
+++ /dev/null
@@ -1,8 +0,0 @@
-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
diff --git a/workflows/kallisto/README.md b/workflows/kallisto/README.md
new file mode 100644
index 0000000..52f46ea
--- /dev/null
+++ b/workflows/kallisto/README.md
@@ -0,0 +1,7 @@
+
+# Kallisto
+
+
+
+CWL adapted from: https://github.com/common-workflow-library/bio-cwl-tools/commit/91c42fb809ce18eafe16155cca0abf362270c0fe
+
diff --git a/workflows/kallisto/kallisto-index.cwl b/workflows/kallisto/kallisto-index.cwl
new file mode 100644
index 0000000..4e5b609
--- /dev/null
+++ b/workflows/kallisto/kallisto-index.cwl
@@ -0,0 +1,63 @@
+#!/usr/bin/env cwl-runner
+cwlVersion: v1.0
+class: CommandLineTool
+
+hints:
+ DockerRequirement:
+ dockerPull: quay.io/biocontainers/kallisto:0.46.2--h4f7b962_1
+ SoftwareRequirement:
+ packages:
+ kallisto:
+ version: [ "0.46.0" ]
+ specs: [ https://identifiers.org/biotools/kallisto ]
+
+requirements:
+ - class: InlineJavascriptRequirement
+ - class: InitialWorkDirRequirement
+ listing:
+ - entry: "$({class: 'Directory', listing: []})"
+ entryname: $(inputs.IndexOutfolder)
+ writable: true
+
+inputs:
+ InputFiles:
+ type: File[]
+ format: edam:format_1929 # FASTA
+ inputBinding:
+ position: 200
+
+ IndexOutfolder:
+ type: string
+
+ IndexName:
+ type: string
+ inputBinding:
+ prefix: "--index="
+ separate: false
+
+#Optional arguments
+
+ kmerSize:
+ type: int?
+ inputBinding:
+ prefix: "--kmer-size="
+ separate: false
+
+ makeUnique:
+ type: boolean?
+ inputBinding:
+ prefix: "--make-unique"
+
+baseCommand: [kallisto, index]
+
+outputs:
+
+ index:
+ type: Directory
+ outputBinding:
+ glob: $(runtime.outdir)/$(inputs.IndexOutfolder)
+
+$namespaces:
+ edam: http://edamontology.org/
+$schemas:
+ - https://edamontology.org/EDAM_1.18.owl
diff --git a/workflows/kallisto/kallisto-quant.cwl b/workflows/kallisto/kallisto-quant.cwl
new file mode 100755
index 0000000..a5c3b3e
--- /dev/null
+++ b/workflows/kallisto/kallisto-quant.cwl
@@ -0,0 +1,137 @@
+#!/usr/bin/env cwl-runner
+cwlVersion: v1.0
+class: CommandLineTool
+
+hints:
+ DockerRequirement:
+ dockerPull: quay.io/biocontainers/kallisto:0.46.2--h4f7b962_1
+ SoftwareRequirement:
+ packages:
+ kallisto:
+ version: [ "0.46.0" ]
+ specs: [ https://identifiers.org/biotools/kallisto ]
+
+inputs:
+ InputReads:
+ type: File[]
+ format: edam:format_1930 # FASTA
+ inputBinding:
+ position: 200
+
+ QuantOutfolder:
+ type: string
+
+ Index:
+ type: File
+ inputBinding:
+ position: 1
+ prefix: "--index"
+
+ isSingle:
+ type: boolean
+ inputBinding:
+ position: 2
+ prefix: "--single"
+
+ #Optional Inputs
+
+ isBias:
+ type: boolean?
+ inputBinding:
+ prefix: "--bias"
+
+ isFusion:
+ type: boolean?
+ inputBinding:
+ prefix: "--fusion"
+
+ isSingleOverhang:
+ type: boolean?
+ inputBinding:
+ prefix: "--single-overhang"
+
+ FragmentLength:
+ type: double?
+ inputBinding:
+ separate: false
+ prefix: "--fragment-length="
+
+ StandardDeviation:
+ type: double?
+ inputBinding:
+ prefix: "--sd"
+
+ BootstrapSamples:
+ type: int?
+ inputBinding:
+ separate: false
+ prefix: "--bootstrap-samples="
+
+ Seed:
+ type: int?
+ inputBinding:
+ prefix: "--seed"
+
+#Using record inputs to create mutually exclusive inputs
+ Strand:
+ type:
+ - "null"
+ - type: record
+ name: forward
+ fields:
+ forward:
+ type: boolean
+ inputBinding:
+ prefix: "--fr-stranded"
+
+ - type: record
+ name: reverse
+ fields:
+ reverse:
+ type: boolean
+ inputBinding:
+ prefix: "--rf-stranded"
+
+ PseudoBam:
+ type: boolean?
+ inputBinding:
+ prefix: "--pseudobam"
+
+#Using record inputs to create dependent inputs
+
+ GenomeBam:
+ type:
+ - "null"
+ - type: record
+ name: genome_bam
+ fields:
+ genomebam:
+ type: boolean
+ inputBinding:
+ prefix: "--genomebam"
+
+ gtf:
+ type: File
+ inputBinding:
+ prefix: "--gtf"
+
+ chromosomes:
+ type: File
+ inputBinding:
+ prefix: "--chromosomes"
+
+baseCommand: [ kallisto, quant ]
+
+arguments: [ "--output-dir", $(inputs.QuantOutfolder) ]
+
+outputs:
+
+ outFolder:
+ type: Directory
+ outputBinding:
+ glob: $(runtime.outdir)/$(inputs.QuantOutfolder)
+
+$namespaces:
+ edam: http://edamontology.org/
+$schemas:
+ - https://edamontology.org/EDAM_1.18.owl
diff --git a/workflows/kallisto/kallisto-workflow.cwl b/workflows/kallisto/kallisto-workflow.cwl
new file mode 100644
index 0000000..5f65dfc
--- /dev/null
+++ b/workflows/kallisto/kallisto-workflow.cwl
@@ -0,0 +1,44 @@
+cwlVersion: v1.2
+class: Workflow
+
+requirements:
+ ScatterFeatureRequirement: {}
+
+inputs:
+ parentDir: Directory
+ dirNamePattern: string
+ collectedOut: string
+ Index: File
+ isSingle: boolean
+ FragmentLength: double?
+ StandardDeviation: double?
+ BootstrapSamples: int?
+
+steps:
+ quant:
+ run: kallisto-quant.cwl
+ scatter:
+ - InputReads
+ - QuantOutfolder
+ scatterMethod: dotproduct
+ in:
+ InputReads: listFiles/inDirFiles
+ QuantOutfolder: listFiles/inDirBasename
+ Index: Index
+ isSingle: isSingle
+ FragmentLength: FragmentLength
+ StandardDeviation: StandardDeviation
+ BootstrapSamples: BootstrapSamples
+ out: [outFolder]
+ collect:
+ run: ../_aux-tools/yield-dirInDestination.cwl
+ scatter: inDir
+ in:
+ inDir: quant/outFolder
+ destinationDir: collectedOut
+ out: [outDir]
+
+outputs:
+ finalOut:
+ type: Directory[]
+ outputSource: collect/outDir
--
GitLab