Skip to content
Snippets Groups Projects
Commit 9214eb5e authored by Dominik Brilhaus's avatar Dominik Brilhaus
Browse files

first steps re-design cwl based analysis

parent 68c17471
No related branches found
No related tags found
1 merge request!1Cwl
Pipeline #2411 passed
**/dataset/** filter=lfs diff=lfs merge=lfs -text
/assays/Talinum_RNASeq_minimal/dataset/DB_097_CAMMD_CAGATC_L001_R1_001.fastq.gz filter=lfs diff=lfs merge=lfs -text
/assays/Talinum_RNASeq_minimal/dataset/DB_163_reC3MD_GTGAAA_L001_R1_001.fastq.gz filter=lfs diff=lfs merge=lfs -text
/assays/Talinum_RNASeq_minimal/dataset/DB_099_CAMMD_CTTGTA_L001_R1_001.fastq.gz filter=lfs diff=lfs merge=lfs -text
/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/out/kallisto_index filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150112_55.D/AcqData/TDASpec.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150112_03.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150112_15.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150112_55.D/AcqData/MSPeak.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150112_55.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150112_15.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_12.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_16.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_11.D/AcqData/TDASpec.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150112_55.D/AcqData/TDASpec.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150112_61.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150112_65.D/AcqData/MSPeak.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150112_65.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150112_65.D/AcqData/TDASpec.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_11.D/AcqData/MSPeak.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_11.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_15.D/AcqData/TDASpec.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_15.D/AcqData/MSPeak.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_15.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_14.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150112_03.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_13.D/AcqData/TDASpec.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_11.D/AcqData/TDASpec.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_12.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_13.D/AcqData/MSPeak.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_13.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150112_65.D/AcqData/TDASpec.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150112_65.D/AcqData/MSPeak.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150112_65.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150112_61.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
studies/TalinumGenomeDraft/resources/Talinum.gm.CDS.nt.fa filter=lfs diff=lfs merge=lfs -text
runs/run1/01_kallisto_results/DB_103/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results_v48_anaconda/DB_163_reC3MD_GTGAAA_L001_R1_001/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/no_CWL_yet/kallisto_sleuth/run1/03_kallisto_sleuthObject.RData filter=lfs diff=lfs merge=lfs -text
runs/kallisto_sleuth/run1/01_kallisto_results/DB_099/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results_v48_anaconda/DB_099_CAMMD_CTTGTA_L001_R1_001/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/no_CWL_yet/kallisto_sleuth/run1/01_kallisto_results/DB_103/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_sleuth/run1/01_kallisto_index filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results/DB_097/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_sleuth/run1/03_kallisto_df.csv filter=lfs diff=lfs merge=lfs -text
runs/no_CWL_yet/kallisto_sleuth/run2/03_kallisto_sleuthObject.RData filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results/DB_163/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_sleuth/sleuth_dge.csv filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_13.D/AcqData/TDASpec.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_14.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_15.D/AcqData/MSPeak.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_15.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_15.D/AcqData/TDASpec.bin filter=lfs diff=lfs merge=lfs -text
/assays/GCqTOF_targets/dataset/150115_16.D/AcqData/TDA.bin filter=lfs diff=lfs merge=lfs -text
/assays/Talinum_RNASeq_minimal/dataset/DB_097_CAMMD_CAGATC_L001_R1_001.fastq.gz filter=lfs diff=lfs merge=lfs -text
/assays/Talinum_RNASeq_minimal/dataset/DB_099_CAMMD_CTTGTA_L001_R1_001.fastq.gz filter=lfs diff=lfs merge=lfs -text
/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_163_reC3MD_GTGAAA_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_collect/kallisto_df.csv filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results_v48_anaconda/DB_165_re-C3MD_GTGAAA_L002_R1_001/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/no_CWL_yet/kallisto_sleuth/run1/01_kallisto_results/DB_163/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/run1/01_kallisto_results/DB_097/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/no_CWL_yet/kallisto_sleuth/run1/01_kallisto_results/DB_161/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results/DB_161_reC3MD_GTCCGC_L001_R1_001/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/run1/01_kallisto_results/DB_161/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results/DB_161/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_sleuth/run1/01_kallisto_results/DB_103/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/run1/01_kallisto_index filter=lfs diff=lfs merge=lfs -text
runs/kallisto_sleuth/run1/01_kallisto_results/DB_163/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/no_CWL_yet/kallisto_sleuth/run2/03_kallisto_df.csv filter=lfs diff=lfs merge=lfs -text
runs/no_CWL_yet/kallisto_sleuth/run1/01_kallisto_results/DB_165/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/no_CWL_yet/kallisto_sleuth/run1/01_kallisto_results/DB_097/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/no_CWL_yet/kallisto_sleuth/run1/03_kallisto_df.csv filter=lfs diff=lfs merge=lfs -text
runs/kallisto_sleuth/run1/01_kallisto_results/DB_161/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results/DB_099_CAMMD_CTTGTA_L001_R1_001/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results_v48_anaconda/DB_103_CAMMD_AGTCAA_L001_R1_001/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_sleuth/sleuth_dge.csv filter=lfs diff=lfs merge=lfs -text
studies/TalinumGenomeDraft/resources/Talinum.gm.CDS.nt.fa filter=lfs diff=lfs merge=lfs -text
runs/kallisto_collect/kallisto_sleuthObject.RData filter=lfs diff=lfs merge=lfs -text
runs/run1/01_kallisto_results/DB_165/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results/DB_099/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_collect/out/kallisto_sleuthObject.RData filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results/DB_103/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results/DB_165/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/no_CWL_yet/kallisto_sleuth/run1/01_kallisto_results/DB_099/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results_v48_anaconda/DB_097_CAMMD_CAGATC_L001_R1_001/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_sleuth/run1/01_kallisto_results/DB_097/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_sleuth/run2/03_kallisto_df.csv filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results/DB_165_re-C3MD_GTGAAA_L002_R1_001/abundance.h5 filter=lfs diff=lfs merge=lfs -text
externals/Talinum.gm.CDS.nt.fa filter=lfs diff=lfs merge=lfs -text
runs/kallisto_sleuth/run1/03_kallisto_sleuthObject.RData filter=lfs diff=lfs merge=lfs -text
runs/kallisto_sleuth/run1/01_kallisto_results/DB_165/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results/DB_103_CAMMD_AGTCAA_L001_R1_001/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_sleuth/run2/03_kallisto_sleuthObject.RData filter=lfs diff=lfs merge=lfs -text
runs/run1/01_kallisto_results/DB_099/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results/DB_097_CAMMD_CAGATC_L001_R1_001/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/run1/03_kallisto_df.csv filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results/DB_163_reC3MD_GTGAAA_L001_R1_001/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/run1/03_kallisto_sleuthObject.RData filter=lfs diff=lfs merge=lfs -text
runs/run1/01_kallisto_results/DB_163/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/kallisto_quant/kallisto_results_v48_anaconda/DB_161_reC3MD_GTCCGC_L001_R1_001/abundance.h5 filter=lfs diff=lfs merge=lfs -text
runs/no_CWL_yet/kallisto_sleuth/run1/01_kallisto_index filter=lfs diff=lfs merge=lfs -text
# Kallisto Workflow
## Executing individual steps
```bash
cd runs/kallisto/
cwltool ../../workflows/kallisto/kallisto-index.cwl index.yml
```
\ No newline at end of file
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
in_genome_ref:
class: File
path: ../../studies/TalinumGenomeDraft/resources/Talinum.gm.CDS.nt.fa
\ No newline at end of file
# 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
```
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
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
InputReads:
- class: File
path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_097_CAMMD_CAGATC_L001_R1_001.fastq.gz
format: edam:format_1930 # FASTQ
InputFiles:
- class: File
path: ../../../studies/TalinumGenomeDraft/resources/Talinum.gm.CDS.nt.fa
format: edam:format_1929 # FASTA
isSingle: true
FragmentLength: 200
StandardDeviation: 20
BootstrapSamples: 30
$namespaces:
edam: https://edamontology.org/
\ No newline at end of file
File added
#!/usr/bin/env cwl-runner
cwlVersion: v1.2
class: CommandLineTool
hints:
DockerRequirement:
dockerPull: quay.io/biocontainers/kallisto:0.46.2--h4f7b962_1
SoftwareRequirement:
packages:
kallisto:
version: [ "0.46.0" ]
specs: [ https://identifiers.org/biotools/kallisto ]
inputs: []
baseCommand: [kallisto, index]
outputs: []
\ No newline at end of file
......@@ -13,11 +13,6 @@ hints:
requirements:
- class: InlineJavascriptRequirement
- class: InitialWorkDirRequirement
listing:
- entry: "$({class: 'Directory', listing: []})"
entryname: $(inputs.IndexOutfolder)
writable: true
inputs:
InputFiles:
......@@ -25,15 +20,13 @@ inputs:
format: edam:format_1929 # FASTA
inputBinding:
position: 200
IndexOutfolder:
type: string
IndexName:
type: string
inputBinding:
prefix: "--index="
separate: false
valueFrom: $(self).kallistoIndex
#Optional arguments
......@@ -51,13 +44,12 @@ inputs:
baseCommand: [kallisto, index]
outputs:
index:
type: Directory
type: File
outputBinding:
glob: $(runtime.outdir)/$(inputs.IndexOutfolder)
glob: $(inputs.IndexName).kallistoIndex
$namespaces:
edam: http://edamontology.org/
edam: https://edamontology.org/
$schemas:
- https://edamontology.org/EDAM_1.18.owl
......@@ -14,7 +14,7 @@ hints:
inputs:
InputReads:
type: File[]
format: edam:format_1930 # FASTA
format: edam:format_1930 # FASTQ
inputBinding:
position: 200
......
......@@ -5,9 +5,7 @@ requirements:
ScatterFeatureRequirement: {}
inputs:
parentDir: Directory
dirNamePattern: string
collectedOut: string
InputReads: []
Index: File
isSingle: boolean
FragmentLength: double?
......@@ -17,28 +15,20 @@ inputs:
steps:
quant:
run: kallisto-quant.cwl
scatter:
- InputReads
- QuantOutfolder
scatterMethod: dotproduct
scatter: InputReads
in:
InputReads: listFiles/inDirFiles
QuantOutfolder: listFiles/inDirBasename
QuantOutfolder:
source: InputReads
valueFrom: $(self.nameroot)
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
outputSource: quant/outFolder
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment