From: Ward Vandewege Date: Tue, 7 Dec 2021 15:18:20 +0000 (-0500) Subject: Merge branch 'blog-examples' X-Git-Url: https://git.arvados.org/arvados-tutorial.git/commitdiff_plain/cac99e0d9185a3817a89a245921bbf25c946434d?hp=3103cae51ea3f51ef5d4e9827490b2609ab59b3b Merge branch 'blog-examples' refs #18178 Arvados-DCO-1.1-Signed-off-by: Ward Vandewege --- diff --git a/blog-examples/debugging/fastqc/fastqc_blog.cwl b/blog-examples/debugging/fastqc/fastqc_blog.cwl new file mode 100644 index 0000000..340c1ec --- /dev/null +++ b/blog-examples/debugging/fastqc/fastqc_blog.cwl @@ -0,0 +1,53 @@ +cwlVersion: v1.1 +class: CommandLineTool +label: Quality check on FASTQ + +requirements: + DockerRequirement: + dockerPull: biocontainers/fastqc:v0.11.9_cv6 + InitialWorkDirRequirement: + listing: + - $(inputs.fastq1) + - $(inputs.fastq2) + +hints: + SoftwareRequirement: + packages: + FastQC: + specs: [ "https://identifiers.org/rrid/RRID:SCR_014583" ] + version: [ "0.11.9" ] + +inputs: + fastq1: + type: File + label: One of set of pair-end FASTQs (R1) + + fastq2: + type: File + label: One of set of pair-end FASTQs (R2) + +outputs: + out-html: + type: File[] + label: FASTQ QC reports + outputBinding: + glob: "*html" + out-zip: + type: File[] + label: Zip files of FASTQ QC report and associated data + outputBinding: + glob: "*fastqc.zip" + +baseCommand: fastqc + +arguments: + - "--noextract" + - $(inputs.fastq1.basename) + - $(inputs.fastq2.basename) + +s:codeRepository: https://github.com/arvados/arvados-tutorial/blog-examples/debugging +s:license: https://www.gnu.org/licenses/agpl-3.0.en.html + +$namespaces: + s: https://schema.org/ + edam: http://edamontology.org/ diff --git a/blog-examples/debugging/fastqc/fastqc_blog.yml b/blog-examples/debugging/fastqc/fastqc_blog.yml new file mode 100644 index 0000000..0c56a57 --- /dev/null +++ b/blog-examples/debugging/fastqc/fastqc_blog.yml @@ -0,0 +1,7 @@ +fastq1: + class: File + location: keep:be73607762d9948f8da2c1151dc3ef46+70694/ERR2122553_1.fastq.gz + +fastq2: + class: File + location: keep:be73607762d9948f8da2c1151dc3ef46+70694/ERR2122553_2.fastq.gz diff --git a/blog-examples/debugging/fastqc/fastqc_blog_broken.cwl b/blog-examples/debugging/fastqc/fastqc_blog_broken.cwl new file mode 100644 index 0000000..8d3d348 --- /dev/null +++ b/blog-examples/debugging/fastqc/fastqc_blog_broken.cwl @@ -0,0 +1,53 @@ +cwlVersion: v1.1 +class: CommandLineTool +label: Quality check on FASTQ + +requirements: + DockerRequirement: + dockerPull: biocontainers/fastqc:v0.11.9_cv6 + InitialWorkDirRequirement: + listing: + - $(inputs.fastq1) + - $(inputs.fastq2) + +hints: + SoftwareRequirement: + packages: + FastQC: + specs: [ "https://identifiers.org/rrid/RRID:SCR_014583" ] + version: [ "0.11.9" ] + +inputs: + fastq1: + type: Files + label: One of set of pair-end FASTQs (R1) + + fastq2: + type: File + label: One of set of pair-end FASTQs (R2) + +outputs: + out-html: + type: File[] + label: FASTQ QC reports + outputBinding: + glob: "*html" + out-zip: + type: File[] + label: Zip files of FASTQ QC report and associated data + outputBinding: + glob: "*fastqc.zip" + +baseCommand: fastqc + +arguments: + - "--noextract" + - $(inputs.fastq1.basename) + - $(inputs.fastq2.basename) + +s:codeRepository: https://github.com/arvados/arvados-tutorial/blog-examples/debugging +s:license: https://www.gnu.org/licenses/agpl-3.0.en.html + +$namespaces: + s: https://schema.org/ + edam: http://edamontology.org/ diff --git a/blog-examples/debugging/fastqc/fastqc_blog_mismatch.yml b/blog-examples/debugging/fastqc/fastqc_blog_mismatch.yml new file mode 100644 index 0000000..6441654 --- /dev/null +++ b/blog-examples/debugging/fastqc/fastqc_blog_mismatch.yml @@ -0,0 +1,7 @@ +fastq1: + class: Directory + location: keep:be73607762d9948f8da2c1151dc3ef46+70694 + +fastq2: + class: File + location: keep:be73607762d9948f8da2c1151dc3ef46+70694/ERR2122553_2.fastq.gz diff --git a/blog-examples/debugging/star-index/.gitignore b/blog-examples/debugging/star-index/.gitignore new file mode 100644 index 0000000..681307f --- /dev/null +++ b/blog-examples/debugging/star-index/.gitignore @@ -0,0 +1 @@ +rnaseq diff --git a/blog-examples/debugging/star-index/README.md b/blog-examples/debugging/star-index/README.md new file mode 100644 index 0000000..70872ac --- /dev/null +++ b/blog-examples/debugging/star-index/README.md @@ -0,0 +1,16 @@ + +To test this: + + mkdir rnaseq + cd rnaseq + wget --mirror --no-parent --no-host --cut-dirs=1 https://download.jutro.arvadosapi.com/c=9178fe1b80a08a422dbe02adfd439764+925/ + cd .. + +Then: + + arvados-cwl-runner STAR-index-broken.cwl STAR-index.yml + +or: + + arvados-cwl-runner STAR-index.cwl STAR-index.yml + diff --git a/blog-examples/debugging/star-index/STAR-index-broken.cwl b/blog-examples/debugging/star-index/STAR-index-broken.cwl new file mode 100755 index 0000000..10b3fa1 --- /dev/null +++ b/blog-examples/debugging/star-index/STAR-index-broken.cwl @@ -0,0 +1,58 @@ +#!/usr/bin/env cwl-runner +cwlVersion: v1.0 +class: CommandLineTool + +requirements: + DockerRequirement: + dockerPull: "quay.io/biocontainers/star:2.7.5c--0" + +inputs: + + InputFiles: + format: http://edamontology.org/format_1930 + type: File[] + inputBinding: + prefix: "--genomeFastaFiles" + + IndexName: + type: string + inputBinding: + prefix: "--genomeDir" + valueFrom: ./$(self) + +#Optional Inputs + + Gtf: + type: File? + inputBinding: + prefix: "--sjdbGTFfile" + + Overhang: + type: int? + inputBinding: + prefix: "--sjdbOverhang" + + Junctions: + type: File? + inputBinding: + prefix: "--sjdbFileChrStartEnd" + + GenomeSize: + type: int? + inputBinding: + prefix: "--genomeSAindexNbases" + + GenomeBits: + type: int? + inputBinding: + prefix: "--genomeChrBinNbits" + +baseCommand: [STAR, --runMode, genomeGenerate] + +arguments: [--runThreadN, $(runtime.cores)] + +outputs: + indexes: + type: Directory + outputBinding: + glob: ./$(inputs.IndexName)/ diff --git a/blog-examples/debugging/star-index/STAR-index.cwl b/blog-examples/debugging/star-index/STAR-index.cwl new file mode 100755 index 0000000..74ee7db --- /dev/null +++ b/blog-examples/debugging/star-index/STAR-index.cwl @@ -0,0 +1,61 @@ +#!/usr/bin/env cwl-runner +cwlVersion: v1.0 +class: CommandLineTool + +requirements: + DockerRequirement: + dockerPull: "quay.io/biocontainers/star:2.7.5c--0" + ResourceRequirement: + coresMin: 2 + ramMin: 12000 + +inputs: + + InputFiles: + format: http://edamontology.org/format_1930 + type: File[] + inputBinding: + prefix: "--genomeFastaFiles" + + IndexName: + type: string + inputBinding: + prefix: "--genomeDir" + valueFrom: ./$(self) + +#Optional Inputs + + Gtf: + type: File? + inputBinding: + prefix: "--sjdbGTFfile" + + Overhang: + type: int? + inputBinding: + prefix: "--sjdbOverhang" + + Junctions: + type: File? + inputBinding: + prefix: "--sjdbFileChrStartEnd" + + GenomeSize: + type: int? + inputBinding: + prefix: "--genomeSAindexNbases" + + GenomeBits: + type: int? + inputBinding: + prefix: "--genomeChrBinNbits" + +baseCommand: [STAR, --runMode, genomeGenerate] + +arguments: [--runThreadN, $(runtime.cores)] + +outputs: + indexes: + type: Directory + outputBinding: + glob: ./$(inputs.IndexName)/ diff --git a/blog-examples/debugging/star-index/STAR-index.yml b/blog-examples/debugging/star-index/STAR-index.yml new file mode 100644 index 0000000..189faf2 --- /dev/null +++ b/blog-examples/debugging/star-index/STAR-index.yml @@ -0,0 +1,9 @@ +InputFiles: + - class: File + location: rnaseq/reference_data/chr1.fa + format: http://edamontology.org/format_1930 +IndexName: 'hg19-chr1-STAR-index' +Gtf: + class: File + location: rnaseq/reference_data/chr1-hg19_genes.gtf +Overhang: 99