Merge pull request #25 from piotr-faba-ardigen/add_cutadapt_tool

Add cutadapt tool

.github/workflows/cutadapt.yml

@@ -0,0 +1,34 @@
+name: cutadapt
+on:
+  push: {}
+  pull_request:
+    paths: tools/cutadapt/*
+
+jobs:
+  run_ci_test:
+    runs-on: ubuntu-latest
+
+    steps:
+      # Check out the repository
+      - uses: actions/checkout@v2
+      - name: Checkout submodules
+        shell: bash
+        run: |
+          auth_header="$(git config --local --get http.https://github.com/.extraheader)"
+          git submodule sync --recursive
+          git -c "http.extraheader=$auth_header" -c protocol.version=2 submodule update --init --force --recursive --depth=1
+
+      - name: Install Nextflow
+        run: |
+          wget -qO- get.nextflow.io | bash
+          sudo mv nextflow /usr/local/bin/
+
+      - name: Test module with paired-end data
+        run: |
+          cd tools/cutadapt/test_paired/
+          nextflow run . -ansi-log false
+
+      - name: Test module with single-end data
+        run: |
+          cd tools/cutadapt/test_single/
+          nextflow run . -ansi-log false

test-datasets

@@ -1 +1 @@
-Subproject commit e5fef88994b8d34c7bf4b07116e5f7a330d2ee3b
+Subproject commit aae85a5c9c72238959108212481ce83bae569709

tools/cutadapt/main.nf

@@ -0,0 +1,45 @@
+process cutadapt {
+    tag "${sample_id}"
+
+    container 'quay.io/biocontainers/cutadapt:1.16--py27_1'
+
+    input:
+    tuple val(sample_id), file(reads)
+
+    output:
+    tuple sample_id, file("trimmed_*.fastq")
+
+    script:
+    forward_fq = "trimmed_1.fastq"
+    reverse_fq = "trimmed_2.fastq"
+
+    
+    if (params.singleEnd) {
+        processing = """
+                    cutadapt \
+		            	-j ${task.cpus} \
+		            	-q $params.cutadapt_min_quality \
+		            	--minimum-length $params.cutadapt_min_length \
+		            	--output ${forward_fq} \
+		            	${reads}
+                    """
+    } else {
+        processing = """
+                    cutadapt \
+		            	-j ${task.cpus} \
+		            	-q $params.cutadapt_min_quality \
+		            	--minimum-length $params.cutadapt_min_length \
+		            	--pair-filter=any \
+		            	--output ${forward_fq} \
+		            	--paired-output ${reverse_fq} ${reads}
+            
+                    
+                    """
+    }
+
+    version = """
+    cutadapt --version &> v_cutadapt.txt
+    """
+
+    return processing + version
+}

tools/cutadapt/meta.yml

@@ -0,0 +1,36 @@
+name: Cutadapt
+description: cutadapt removes adapter sequences from high-throughput sequencing reads
+keywords:
+    - Quality Control
+    - QC
+    - Adapters
+tools:
+    - fastqc:
+        description: |
+            Cutadapt finds and removes adapter sequences, primers, poly-A tails and other types of unwanted sequence
+            from your high-throughput sequencing reads.
+            
+            Cleaning your data in this way is often required: Reads from small-RNA sequencing contain the 3’
+            sequencing adapter because the read is longer than the molecule that is sequenced. Amplicon reads 
+            start with a primer sequence. Poly-A tails are useful for pulling out RNA from your sample, but 
+            often you don’t want them to be in your reads.
+        homepage: https://cutadapt.readthedocs.io/en/stable/
+        documentation: https://cutadapt.readthedocs.io/en/stable/
+input:
+    -
+        - sample_id:
+            type: string
+            description: Sample identifier
+        - reads:
+            type: file
+            description: Input FastQ file, or pair of files
+output:
+    -
+        - sample_id:
+            type: string
+            description: Sample identifier
+        - reads:
+            type: file
+            description: trimmed FastQ file, or pair of files
+authors:
+    - @piotr-faba-ardigen

tools/cutadapt/test_paired/main.nf

@@ -0,0 +1,14 @@
+#!/usr/bin/env nextflow
+nextflow.preview.dsl = 2
+include '../main.nf' params(params)
+
+// Define input channels
+
+Channel
+  .fromFilePairs('../../../test-datasets/tools/cutadapt/input/*_{1,2}.fastq' )
+  .set { ch_read_files }
+
+// Run the workflow
+workflow {
+    cutadapt(ch_read_files)
+}

tools/cutadapt/test_paired/nextflow.config

@@ -0,0 +1,9 @@
+docker.enabled = true
+params.outdir = './results'
+
+params{    
+    //preprocessing options
+    cutadapt_min_length = 40
+    cutadapt_min_quality = 25
+    singleEnd = false
+}

tools/cutadapt/test_single/main.nf

@@ -0,0 +1,21 @@
+#!/usr/bin/env nextflow
+nextflow.preview.dsl = 2
+include '../main.nf' params(params)
+
+// Define input channels
+
+readPaths = [
+  ['SRR4238351', '../../../test-datasets/tools/cutadapt/input/SRR4238351_subsamp.fastq.gz'],
+  ['SRR4238355', '../../../test-datasets/tools/cutadapt/input/SRR4238355_subsamp.fastq.gz'],
+  ['SRR4238359', '../../../test-datasets/tools/cutadapt/input/SRR4238359_subsamp.fastq.gz'],
+  ['SRR4238379', '../../../test-datasets/tools/cutadapt/input/SRR4238379_subsamp.fastq.gz']
+]
+Channel
+  .from(readPaths)
+  .map { row -> [ row[0], [ file(row[1]) ] ] }
+  .set { ch_read_files }
+
+// Run the workflow
+workflow {
+    cutadapt(ch_read_files)
+}

tools/cutadapt/test_single/nextflow.config

@@ -0,0 +1,9 @@
+docker.enabled = true
+params.outdir = './results'
+
+params{    
+    //preprocessing options
+    cutadapt_min_length = 40
+    cutadapt_min_quality = 25
+    singleEnd = true
+}