From 43934494bd887687d86b548cd93ea9205be40fa2 Mon Sep 17 00:00:00 2001
From: Dominik Brilhaus <brilhaus@nfdi4plants.org>
Date: Tue, 18 Mar 2025 08:50:50 +0100
Subject: [PATCH] add and run fastqc workflow
---
.gitattributes | 14 +++++-
.../Talinum_RNASeq_minimal/dataset/.gitkeep | 0
...B_097_CAMMD_CAGATC_L001_R1_001_fastqc.html | 3 ++
...DB_097_CAMMD_CAGATC_L001_R1_001_fastqc.zip | 3 ++
...B_099_CAMMD_CTTGTA_L001_R1_001_fastqc.html | 3 ++
...DB_099_CAMMD_CTTGTA_L001_R1_001_fastqc.zip | 3 ++
...B_103_CAMMD_AGTCAA_L001_R1_001_fastqc.html | 3 ++
...DB_103_CAMMD_AGTCAA_L001_R1_001_fastqc.zip | 3 ++
..._161_reC3MD_GTCCGC_L001_R1_001_fastqc.html | 3 ++
...B_161_reC3MD_GTCCGC_L001_R1_001_fastqc.zip | 3 ++
..._163_reC3MD_GTGAAA_L001_R1_001_fastqc.html | 3 ++
...B_163_reC3MD_GTGAAA_L001_R1_001_fastqc.zip | 3 ++
...165_re-C3MD_GTGAAA_L002_R1_001_fastqc.html | 3 ++
..._165_re-C3MD_GTGAAA_L002_R1_001_fastqc.zip | 3 ++
runs/fastqc/run.cwl | 24 ++++++++++
runs/fastqc/run.yml | 14 ++++++
workflows/fastqc/collectFilesInDir.cwl | 20 ++++++++
workflows/fastqc/fastqc.cwl | 48 +++++++++++++++++++
workflows/fastqc/workflow.cwl | 32 +++++++++++++
19 files changed, 187 insertions(+), 1 deletion(-)
delete mode 100644 assays/Talinum_RNASeq_minimal/dataset/.gitkeep
create mode 100644 runs/fastqc/results/DB_097_CAMMD_CAGATC_L001_R1_001_fastqc.html
create mode 100644 runs/fastqc/results/DB_097_CAMMD_CAGATC_L001_R1_001_fastqc.zip
create mode 100644 runs/fastqc/results/DB_099_CAMMD_CTTGTA_L001_R1_001_fastqc.html
create mode 100644 runs/fastqc/results/DB_099_CAMMD_CTTGTA_L001_R1_001_fastqc.zip
create mode 100644 runs/fastqc/results/DB_103_CAMMD_AGTCAA_L001_R1_001_fastqc.html
create mode 100644 runs/fastqc/results/DB_103_CAMMD_AGTCAA_L001_R1_001_fastqc.zip
create mode 100644 runs/fastqc/results/DB_161_reC3MD_GTCCGC_L001_R1_001_fastqc.html
create mode 100644 runs/fastqc/results/DB_161_reC3MD_GTCCGC_L001_R1_001_fastqc.zip
create mode 100644 runs/fastqc/results/DB_163_reC3MD_GTGAAA_L001_R1_001_fastqc.html
create mode 100644 runs/fastqc/results/DB_163_reC3MD_GTGAAA_L001_R1_001_fastqc.zip
create mode 100644 runs/fastqc/results/DB_165_re-C3MD_GTGAAA_L002_R1_001_fastqc.html
create mode 100644 runs/fastqc/results/DB_165_re-C3MD_GTGAAA_L002_R1_001_fastqc.zip
create mode 100644 runs/fastqc/run.cwl
create mode 100644 runs/fastqc/run.yml
create mode 100644 workflows/fastqc/collectFilesInDir.cwl
create mode 100644 workflows/fastqc/fastqc.cwl
create mode 100644 workflows/fastqc/workflow.cwl
diff --git a/.gitattributes b/.gitattributes
index 07a4a56..574339b 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -32,4 +32,16 @@ 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/sleuth/kallisto_sleuthObject.RData filter=lfs diff=lfs merge=lfs -text
runs/sleuth/out/kallisto_sleuthObject.RData filter=lfs diff=lfs merge=lfs -text
-runs/kallisto/kallisto_results/** filter=lfs diff=lfs merge=lfs -text
\ No newline at end of file
+runs/kallisto/kallisto_results/** filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_097_CAMMD_CAGATC_L001_R1_001_fastqc.zip filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_163_reC3MD_GTGAAA_L001_R1_001_fastqc.html filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_097_CAMMD_CAGATC_L001_R1_001_fastqc.html filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_099_CAMMD_CTTGTA_L001_R1_001_fastqc.html filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_099_CAMMD_CTTGTA_L001_R1_001_fastqc.zip filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_103_CAMMD_AGTCAA_L001_R1_001_fastqc.html filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_103_CAMMD_AGTCAA_L001_R1_001_fastqc.zip filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_161_reC3MD_GTCCGC_L001_R1_001_fastqc.html filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_161_reC3MD_GTCCGC_L001_R1_001_fastqc.zip filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_163_reC3MD_GTGAAA_L001_R1_001_fastqc.zip filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_165_re-C3MD_GTGAAA_L002_R1_001_fastqc.html filter=lfs diff=lfs merge=lfs -text
+runs/fastqc/results/DB_165_re-C3MD_GTGAAA_L002_R1_001_fastqc.zip filter=lfs diff=lfs merge=lfs -text
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/fastqc/results/DB_097_CAMMD_CAGATC_L001_R1_001_fastqc.html b/runs/fastqc/results/DB_097_CAMMD_CAGATC_L001_R1_001_fastqc.html
new file mode 100644
index 0000000..51bd550
--- /dev/null
+++ b/runs/fastqc/results/DB_097_CAMMD_CAGATC_L001_R1_001_fastqc.html
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:496b053b05cdbff7213e1ce93e168c9aae01830b875ba4f140f0445add3a4c9d
+size 608772
diff --git a/runs/fastqc/results/DB_097_CAMMD_CAGATC_L001_R1_001_fastqc.zip b/runs/fastqc/results/DB_097_CAMMD_CAGATC_L001_R1_001_fastqc.zip
new file mode 100644
index 0000000..9cf6ee9
--- /dev/null
+++ b/runs/fastqc/results/DB_097_CAMMD_CAGATC_L001_R1_001_fastqc.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:453098e0f3046efe2317023867e5859e92ee91b254da02f4c84c6a569a12c358
+size 423523
diff --git a/runs/fastqc/results/DB_099_CAMMD_CTTGTA_L001_R1_001_fastqc.html b/runs/fastqc/results/DB_099_CAMMD_CTTGTA_L001_R1_001_fastqc.html
new file mode 100644
index 0000000..141b06f
--- /dev/null
+++ b/runs/fastqc/results/DB_099_CAMMD_CTTGTA_L001_R1_001_fastqc.html
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d20c29bba7d056d66f6a6516c4d1044cdb26184971499eb8814de46ebcbaf6c
+size 610809
diff --git a/runs/fastqc/results/DB_099_CAMMD_CTTGTA_L001_R1_001_fastqc.zip b/runs/fastqc/results/DB_099_CAMMD_CTTGTA_L001_R1_001_fastqc.zip
new file mode 100644
index 0000000..3424223
--- /dev/null
+++ b/runs/fastqc/results/DB_099_CAMMD_CTTGTA_L001_R1_001_fastqc.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c51133d51ff8d98ddaf9df5373e5dc832a66de48b603fc1fca788b75fc9314f8
+size 425882
diff --git a/runs/fastqc/results/DB_103_CAMMD_AGTCAA_L001_R1_001_fastqc.html b/runs/fastqc/results/DB_103_CAMMD_AGTCAA_L001_R1_001_fastqc.html
new file mode 100644
index 0000000..1bbad97
--- /dev/null
+++ b/runs/fastqc/results/DB_103_CAMMD_AGTCAA_L001_R1_001_fastqc.html
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462d62cb603020068aff4606f26b62d818d2bfb56eb1894dc993638a5763c7ae
+size 611722
diff --git a/runs/fastqc/results/DB_103_CAMMD_AGTCAA_L001_R1_001_fastqc.zip b/runs/fastqc/results/DB_103_CAMMD_AGTCAA_L001_R1_001_fastqc.zip
new file mode 100644
index 0000000..3ebe761
--- /dev/null
+++ b/runs/fastqc/results/DB_103_CAMMD_AGTCAA_L001_R1_001_fastqc.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7d78a994d307c6a57adbb4b41d22207d0ae7ebf2ace568f9fbe70aa606da03
+size 424835
diff --git a/runs/fastqc/results/DB_161_reC3MD_GTCCGC_L001_R1_001_fastqc.html b/runs/fastqc/results/DB_161_reC3MD_GTCCGC_L001_R1_001_fastqc.html
new file mode 100644
index 0000000..25b6a55
--- /dev/null
+++ b/runs/fastqc/results/DB_161_reC3MD_GTCCGC_L001_R1_001_fastqc.html
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e689e4f749d29fff8ec52ada03471255579e43f04e49191bb8b19896348e576
+size 608061
diff --git a/runs/fastqc/results/DB_161_reC3MD_GTCCGC_L001_R1_001_fastqc.zip b/runs/fastqc/results/DB_161_reC3MD_GTCCGC_L001_R1_001_fastqc.zip
new file mode 100644
index 0000000..545e4ba
--- /dev/null
+++ b/runs/fastqc/results/DB_161_reC3MD_GTCCGC_L001_R1_001_fastqc.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1772958d490994dabde1091c2506c634b78d12698027b37e9d8e15d20a72fbc1
+size 420951
diff --git a/runs/fastqc/results/DB_163_reC3MD_GTGAAA_L001_R1_001_fastqc.html b/runs/fastqc/results/DB_163_reC3MD_GTGAAA_L001_R1_001_fastqc.html
new file mode 100644
index 0000000..9df6845
--- /dev/null
+++ b/runs/fastqc/results/DB_163_reC3MD_GTGAAA_L001_R1_001_fastqc.html
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f54fd0ae336e95fa780a9b0fb097beb1f50cdbbc24610d6247066eba3b0454a
+size 610537
diff --git a/runs/fastqc/results/DB_163_reC3MD_GTGAAA_L001_R1_001_fastqc.zip b/runs/fastqc/results/DB_163_reC3MD_GTGAAA_L001_R1_001_fastqc.zip
new file mode 100644
index 0000000..d94d295
--- /dev/null
+++ b/runs/fastqc/results/DB_163_reC3MD_GTGAAA_L001_R1_001_fastqc.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be44017bdb5956ac2b479115fd26a5f605b493b3224050bb0a0af6deb53786ac
+size 424179
diff --git a/runs/fastqc/results/DB_165_re-C3MD_GTGAAA_L002_R1_001_fastqc.html b/runs/fastqc/results/DB_165_re-C3MD_GTGAAA_L002_R1_001_fastqc.html
new file mode 100644
index 0000000..5c6ddb7
--- /dev/null
+++ b/runs/fastqc/results/DB_165_re-C3MD_GTGAAA_L002_R1_001_fastqc.html
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24474916df5d793336d0806f8ae28754e3ce1c03c3c3979f91a37550f26eb126
+size 609445
diff --git a/runs/fastqc/results/DB_165_re-C3MD_GTGAAA_L002_R1_001_fastqc.zip b/runs/fastqc/results/DB_165_re-C3MD_GTGAAA_L002_R1_001_fastqc.zip
new file mode 100644
index 0000000..1e9c80d
--- /dev/null
+++ b/runs/fastqc/results/DB_165_re-C3MD_GTGAAA_L002_R1_001_fastqc.zip
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7efe5eb2d68cb409f26228692e0b0d19da26787a2a3716faafd6f88722fdb0
+size 426039
diff --git a/runs/fastqc/run.cwl b/runs/fastqc/run.cwl
new file mode 100644
index 0000000..974e992
--- /dev/null
+++ b/runs/fastqc/run.cwl
@@ -0,0 +1,24 @@
+cwlVersion: v1.2
+class: Workflow
+
+requirements:
+ SubworkflowFeatureRequirement: {}
+ ScatterFeatureRequirement: {}
+ MultipleInputFeatureRequirement: {}
+
+inputs:
+ fastq: File[]
+ finaloutdir: string
+
+steps:
+ fastqc:
+ run: ../../workflows/fastqc/workflow.cwl
+ in:
+ fastq: fastq
+ finaloutdir: finaloutdir
+ out: [outdir]
+
+outputs:
+ outdir:
+ type: Directory
+ outputSource: fastqc/outdir
\ No newline at end of file
diff --git a/runs/fastqc/run.yml b/runs/fastqc/run.yml
new file mode 100644
index 0000000..d9744cf
--- /dev/null
+++ b/runs/fastqc/run.yml
@@ -0,0 +1,14 @@
+finaloutdir: "results"
+fastq:
+ - class: File
+ path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_097_CAMMD_CAGATC_L001_R1_001.fastq.gz
+ - class: File
+ path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_099_CAMMD_CTTGTA_L001_R1_001.fastq.gz
+ - class: File
+ path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_103_CAMMD_AGTCAA_L001_R1_001.fastq.gz
+ - class: File
+ path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_161_reC3MD_GTCCGC_L001_R1_001.fastq.gz
+ - class: File
+ path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_163_reC3MD_GTGAAA_L001_R1_001.fastq.gz
+ - class: File
+ path: ../../assays/Talinum_RNASeq_minimal/dataset/DB_165_re-C3MD_GTGAAA_L002_R1_001.fastq.gz
\ No newline at end of file
diff --git a/workflows/fastqc/collectFilesInDir.cwl b/workflows/fastqc/collectFilesInDir.cwl
new file mode 100644
index 0000000..39f9ff8
--- /dev/null
+++ b/workflows/fastqc/collectFilesInDir.cwl
@@ -0,0 +1,20 @@
+cwlVersion: v1.2
+class: ExpressionTool
+label: Collect files in a directory
+doc: |
+ Takes Files (e.g. from a workflow step) and yields them in a desired directory.
+requirements:
+ - class: InlineJavascriptRequirement
+inputs:
+ files: File[]
+ destination: string
+expression: |
+ ${
+ return {"outDir": {
+ "class": "Directory",
+ "basename": inputs.destination,
+ "listing": inputs.files
+ } };
+ }
+outputs:
+ outDir: Directory
\ No newline at end of file
diff --git a/workflows/fastqc/fastqc.cwl b/workflows/fastqc/fastqc.cwl
new file mode 100644
index 0000000..a2e408d
--- /dev/null
+++ b/workflows/fastqc/fastqc.cwl
@@ -0,0 +1,48 @@
+#!/usr/bin/env cwl-runner
+cwlVersion: v1.2
+class: CommandLineTool
+
+label: Run fastqc on raw reads in FASTQ format (single or paired end) or aligned reads in BAM.
+
+doc: |
+ simplified from: https://github.com/common-workflow-library/bio-cwl-tools/blob/66f620da5b0a11e934a6da83272205a2516bcd91/fastqc/fastqc_1.cwl
+
+ Run fastqc on raw reads in FASTQ format (single or paired end) or aligned reads in BAM.
+
+hints:
+ ResourceRequirement:
+ coresMin: 1
+ ramMin: 5000
+ DockerRequirement:
+ dockerPull: quay.io/biocontainers/fastqc:0.11.9--hdfd78af_1
+ SoftwareRequirement:
+ packages:
+ fastqc:
+ specs: [ https://identifiers.org/biotools/fastqc ]
+ version: [ "0.11.9" ]
+
+
+baseCommand: "fastqc"
+arguments:
+ - valueFrom: $(runtime.outdir)
+ prefix: "-o"
+ - valueFrom: "--noextract"
+
+inputs:
+ fastq:
+ type: File
+ inputBinding:
+ position: 1
+
+outputs:
+ fastqc_zip:
+ doc: all data e.g. figures
+ type: File
+ outputBinding:
+ glob: "*_fastqc.zip"
+ fastqc_html:
+ doc: html report showing results from zip
+ type: File
+ outputBinding:
+ glob: "*_fastqc.html"
+
diff --git a/workflows/fastqc/workflow.cwl b/workflows/fastqc/workflow.cwl
new file mode 100644
index 0000000..d80a7ea
--- /dev/null
+++ b/workflows/fastqc/workflow.cwl
@@ -0,0 +1,32 @@
+#!/usr/bin/env cwl-runner
+cwlVersion: v1.2
+class: Workflow
+
+requirements:
+ ScatterFeatureRequirement: {}
+ SubworkflowFeatureRequirement: {}
+
+inputs:
+ fastq: File[]
+ finaloutdir: string
+
+steps:
+ fastqc:
+ run: fastqc.cwl
+ scatter: fastq
+ in:
+ fastq: fastq
+ out: [fastqc_zip, fastqc_html]
+ collectFiles:
+ run: ./collectFilesInDir.cwl
+ in:
+ destination: finaloutdir
+ files:
+ source: [fastqc/fastqc_html, fastqc/fastqc_zip]
+ linkMerge: merge_flattened
+ out: [outDir]
+
+outputs:
+ outdir:
+ type: Directory
+ outputSource: collectFiles/outDir
\ No newline at end of file
--
GitLab