Merge pull request #9 from ewels/master

Added samtools, restructured directory structures

.github/workflows/fastqc.yml

@@ -0,0 +1,23 @@
+name: FastQC
+on:
+  push: {}
+  pull_request:
+    paths: tools/fastqc/*
+
+jobs:
+  run_ci_test:
+    runs-on: ubuntu-latest
+
+    steps:
+
+    # Check out the repository
+    - uses: actions/checkout@v1
+      submodules: true
+
+    - name: Install Nextflow
+      run: |
+        wget -qO- get.nextflow.io | bash
+        sudo mv nextflow /usr/local/bin/
+
+    # Test the module
+    - run: nextflow run ./tools/fastqc/test/ -ansi-log false

.github/workflows/samtools_index.yml

@@ -0,0 +1,23 @@
+name: samtools index
+on:
+  push: {}
+  pull_request:
+    paths: tools/samtools/index*
+
+jobs:
+  run_ci_test:
+    runs-on: ubuntu-latest
+
+    steps:
+
+    # Check out the repository
+    - uses: actions/checkout@v1
+      submodules: true
+
+    - name: Install Nextflow
+      run: |
+        wget -qO- get.nextflow.io | bash
+        sudo mv nextflow /usr/local/bin/
+
+    # Test the module
+    - run: nextflow run ./tools/samtools/index/test/ -ansi-log false

.github/workflows/samtools_sort.yml

@@ -0,0 +1,23 @@
+name: samtools sort
+on:
+  push: {}
+  pull_request:
+    paths: tools/samtools/sort*
+
+jobs:
+  run_ci_test:
+    runs-on: ubuntu-latest
+
+    steps:
+
+    # Check out the repository
+    - uses: actions/checkout@v1
+      submodules: true
+
+    - name: Install Nextflow
+      run: |
+        wget -qO- get.nextflow.io | bash
+        sudo mv nextflow /usr/local/bin/
+
+    # Test the module
+    - run: nextflow run ./tools/samtools/sort/test/ -ansi-log false

.github/workflows/trim_galore.yml

@@ -0,0 +1,23 @@
+name: Trim Galore!
+on:
+  push: {}
+  pull_request:
+    paths: tools/trim_galore/*
+
+jobs:
+  run_ci_test:
+    runs-on: ubuntu-latest
+
+    steps:
+
+    # Check out the repository
+    - uses: actions/checkout@v1
+      submodules: true
+
+    - name: Install Nextflow
+      run: |
+        wget -qO- get.nextflow.io | bash
+        sudo mv nextflow /usr/local/bin/
+
+    # Test the module
+    - run: nextflow run ./tools/trim_galore/test/ -ansi-log false

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "test-datasets"]
+	path = test-datasets
+	url = https://github.com/nf-core/test-datasets.git

nf-core/module_testing/check_process_outputs.nf

@@ -0,0 +1,14 @@
+#!/usr/bin/env nextflow
+nextflow.preview.dsl = 2
+
+cheers = Channel.from 'Bonjour', 'Ciao', 'Hello', 'Hola'
+
+process check_output {
+    input:
+    val x from cheers
+
+    script:
+    """
+    echo '$x world!'
+    """
+}

nf/fastqc.nf

@@ -1,34 +0,0 @@
-/*
-* Description:
-*     Run FastQC on sequenced reads
-* Keywords:
-*     read qc
-*     adapter
-* Tools:
-*     FastQC:
-*         homepage: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/
-*         documentation: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/
-*         description: FastQC gives general quality metrics about your reads.
-*                      It provides information about the quality score distribution
-*                      across your reads, the per base sequence content (%A/C/G/T).
-*                      You get information about adapter contamination and other
-*                      overrepresented sequences.
-*/
-process fastqc {
-    tag "$sample_id"
-    publishDir "${params.outdir}/fastqc", mode: 'copy',
-        saveAs: {filename -> filename.indexOf(".zip") > 0 ? "zips/$filename" : "$filename"}
-
-    input:
-    set val(sample_id), file(reads)
-
-    output:
-    file "*_fastqc.{zip,html}"
-
-    script:
-    """
-    fastqc -q $reads
-
-    fastqc --version &> fastqc.version.txt
-    """
-}

test-datasets

@@ -0,0 +1 @@
+Subproject commit e5fef88994b8d34c7bf4b07116e5f7a330d2ee3b

tools/fastqc/main.nf

@@ -0,0 +1,20 @@
+process fastqc {
+    tag "FastQC - $sample_id"
+    publishDir "${params.outdir}/fastqc", mode: 'copy',
+        saveAs: {filename -> filename.indexOf(".zip") > 0 ? "zips/$filename" : "$filename"}
+
+    container 'quay.io/biocontainers/fastqc:0.11.8--2'
+
+    input:
+    tuple sample_id, path(reads)
+
+    output:
+    path "*_fastqc.{zip,html}"
+
+    script:
+    """
+    fastqc -q $reads
+
+    fastqc --version &> fastqc.version.txt
+    """
+}

tools/fastqc/meta.yml

@@ -0,0 +1,32 @@
+name: FastQC
+description: Run FastQC on sequenced reads
+keywords:
+    - Quality Control
+    - QC
+    - Adapters
+tools:
+    - fastqc:
+        description: |
+            FastQC gives general quality metrics about your reads.
+            It provides information about the quality score distribution
+            across your reads, the per base sequence content (%A/C/G/T).
+            You get information about adapter contamination and other
+            overrepresented sequences.
+        homepage: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/
+        documentation: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/
+input:
+    -
+        - sample_id:
+            type: string
+            description: Sample identifier
+        - reads:
+            type: file
+            description: Input FastQ file, or pair of files
+output:
+    -
+        - report:
+            type: file
+            description: FastQC report
+            pattern: *_fastqc.{zip,html}
+authors:
+    - @ewels

tools/fastqc/test/main.nf

@@ -0,0 +1,22 @@
+#!/usr/bin/env nextflow
+nextflow.preview.dsl = 2
+include '../../../nf-core/module_testing/check_process_outputs.nf' params(params)
+include '../main.nf' params(params)
+
+// Define input channels
+readPaths = [
+  ['SRR4238351', ['../../../test-datasets/tools/fastqc/input/SRR4238351_subsamp.fastq.gz']],
+  ['SRR4238355', ['../../../test-datasets/tools/fastqc/input/SRR4238355_subsamp.fastq.gz']],
+  ['SRR4238359', ['../../../test-datasets/tools/fastqc/input/SRR4238359_subsamp.fastq.gz']],
+  ['SRR4238379', ['../../../test-datasets/tools/fastqc/input/SRR4238379_subsamp.fastq.gz']]
+]
+Channel
+  .from(readPaths)
+  .map { row -> [ row[0], [ file(row[1][0]) ] ] }
+  .set { ch_read_files }
+
+// Run the workflow
+workflow {
+    fastqc(ch_read_files)
+    // .check_output()
+}

tools/fastqc/test/nextflow.config

@@ -0,0 +1,2 @@
+docker.enabled = true
+params.outdir = './results'

tools/samtools/index/main.nf

@@ -0,0 +1,22 @@
+process samtools_index {
+    tag "${bam.baseName}"
+
+    container 'quay.io/biocontainers/samtools:1.9--h10a08f8_12'
+
+    input:
+    path(bam)
+
+    output:
+    path "*.sorted.bam"
+
+    script:
+    def suff_mem = ("${(task.memory.toBytes() - 6000000000) / task.cpus}" > 2000000000) ? 'true' : 'false'
+    def avail_mem = (task.memory && suff_mem) ? "-m" + "${(task.memory.toBytes() - 6000000000) / task.cpus}" : ''
+    """
+    samtools sort $bam \\
+        -@ ${task.cpus} ${avail_mem} \\
+        -o ${bam.baseName}.sorted.bam
+
+    samtools --version &> v_samtools.txt
+    """
+}

tools/samtools/index/meta.yml

@@ -0,0 +1,27 @@
+name: samtools sort
+description: Sort a BAM or CRAM file
+keywords:
+    - sort
+tools:
+    - samtools:
+        description: |
+            SAMtools is a set of utilities for interacting with and post-processing
+            short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li.
+            These files are generated as output by short read aligners like BWA.
+        homepage: http://www.htslib.org/
+        documentation: hhttp://www.htslib.org/doc/samtools.html
+        doi: 10.1093/bioinformatics/btp352
+input:
+    -
+        - input:
+            type: file
+            description: Input BAM or CRAM file
+            pattern: *.{bam,cram}
+output:
+    -
+        - index:
+            type: file
+            description: BAM or CRAM index file
+            pattern: *.{bai}
+authors:
+    - @ewels

tools/samtools/index/test/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+echo true
+
+cheers = Channel.from 'Bonjour', 'Ciao', 'Hello', 'Hola'
+
+process sayHello {
+  input:
+    val x from cheers
+  script:
+    """
+    echo '$x world!'
+    """
+}

tools/samtools/index/test/nextflow.config

@@ -0,0 +1,2 @@
+docker.enabled = true
+params.outdir = './results'

tools/samtools/sort/main.nf

@@ -0,0 +1,18 @@
+process samtools_index {
+    tag "${bam.baseName}"
+
+    container 'quay.io/biocontainers/samtools:1.9--h10a08f8_12'
+
+    input:
+    path(bam)
+
+    output:
+    path "*.bam.bai"
+
+    script:
+    """
+    samtools index $bam
+
+    samtools --version &> v_samtools.txt
+    """
+}

tools/samtools/sort/meta.yml

@@ -0,0 +1,27 @@
+name: samtools sort
+description: Sort a BAM or CRAM file
+keywords:
+    - sort
+tools:
+    - samtools:
+        description: |
+            SAMtools is a set of utilities for interacting with and post-processing
+            short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li.
+            These files are generated as output by short read aligners like BWA.
+        homepage: http://www.htslib.org/
+        documentation: hhttp://www.htslib.org/doc/samtools.html
+        doi: 10.1093/bioinformatics/btp352
+input:
+    -
+        - input:
+            type: file
+            description: Input BAM or CRAM file
+            pattern: *.{bam,cram}
+output:
+    -
+        - sorted_file:
+            type: file
+            description: Sorted BAM or CRAM file
+            pattern: *.{bam,cram}
+authors:
+    - @ewels

tools/samtools/sort/test/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+echo true
+
+cheers = Channel.from 'Bonjour', 'Ciao', 'Hello', 'Hola'
+
+process sayHello {
+  input:
+    val x from cheers
+  script:
+    """
+    echo '$x world!'
+    """
+}

tools/samtools/sort/test/nextflow.config

@@ -0,0 +1,2 @@
+docker.enabled = true
+params.outdir = './results'

tools/trim_galore/main.nf

@@ -0,0 +1,35 @@
+process fastqc {
+    tag "$sample_id"
+    publishDir "${params.outdir}/trim_galore", mode: 'copy',
+        saveAs: {filename ->
+            if (filename.indexOf("_fastqc") > 0) "FastQC/$filename"
+            else if (filename.indexOf("trimming_report.txt") > 0) "logs/$filename"
+            else filename
+        }
+
+    container 'quay.io/biocontainers/trim-galore:0.6.5--0'
+
+    input:
+    tuple sample_id, path(reads)
+
+    output:
+    tuple name, path("*fq.gz")
+    path "*trimming_report.txt"
+    path "*_fastqc.{zip,html}"
+
+    script:
+    c_r1 = clip_r1 > 0 ? "--clip_r1 ${clip_r1}" : ''
+    c_r2 = clip_r2 > 0 ? "--clip_r2 ${clip_r2}" : ''
+    tpc_r1 = three_prime_clip_r1 > 0 ? "--three_prime_clip_r1 ${three_prime_clip_r1}" : ''
+    tpc_r2 = three_prime_clip_r2 > 0 ? "--three_prime_clip_r2 ${three_prime_clip_r2}" : ''
+    nextseq = params.trim_nextseq > 0 ? "--nextseq ${params.trim_nextseq}" : ''
+    if (params.singleEnd) {
+        """
+        trim_galore --fastqc --gzip $c_r1 $tpc_r1 $nextseq $reads
+        """
+    } else {
+        """
+        trim_galore --paired --fastqc --gzip $c_r1 $c_r2 $tpc_r1 $tpc_r2 $nextseq $reads
+        """
+    }
+}

tools/trim_galore/meta.yml

@@ -0,0 +1,43 @@
+name: Trim Galore!
+description: Trim FastQ files using Trim Galore!
+keywords:
+    - trimming
+    - adapters
+    - sequencing adapters
+tools:
+    - fastqc:
+        description: |
+            A wrapper tool around Cutadapt and FastQC to consistently apply quality
+            and adapter trimming to FastQ files, with some extra functionality for
+            MspI-digested RRBS-type (Reduced Representation Bisufite-Seq) libraries.
+        homepage: https://www.bioinformatics.babraham.ac.uk/projects/trim_galore/
+        documentation: https://github.com/FelixKrueger/TrimGalore/blob/master/Docs/Trim_Galore_User_Guide.md
+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
+        - trimmed_fastq:
+            type: file
+            description: Trimmed FastQ files
+            pattern: *fq.gz
+    -
+        - report:
+            type: file
+            description: Trim Galore! trimming report
+            pattern: *trimming_report.txt
+    -
+        - fastqc_report:
+            type: file
+            description: FastQC report
+            pattern: *_fastqc.{zip,html}
+authors:
+    - @ewels

tools/trim_galore/test/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+echo true
+
+cheers = Channel.from 'Bonjour', 'Ciao', 'Hello', 'Hola'
+
+process sayHello {
+  input:
+    val x from cheers
+  script:
+    """
+    echo '$x world!'
+    """
+}