Merge branch '10-addReferenceMultiQC' into 'develop'

Resolve "Add references to multiqc report" and Update README

Closes #10

See merge request !37

README.md

@@ -30,7 +30,7 @@ To Run:
   * **--bcl**
         * Base call files (tarballed [*.tar] +/- gunzipping [*.tar.gz] from a sequencing of 10x single-cell expereiment, supports pigr parallelization).
         * There can be multiple basecall files, but they all will be demultiplexed by the same design file.
-        * eg: **--bcl '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/simple/cellranger-tiny-bcl-simple-1_2_0.tar.gz'**
+        * eg: **--bcl '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/simple1/cellranger-tiny-bcl-1_2_0.tar.gz'**
   * **--designFile**
         * path to design file (csv format) location
         * column 1 = "Lane" (number of lanes to demultiplex, */** for all lanes)
@@ -44,7 +44,7 @@ To Run:
         * eg: **--outDir 'test'**
     * FULL EXAMPLE:
 
-**nextflow run workflow/main.nf --name 'test' --bcl '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/simple/cellranger-tiny-bcl-simple-1_2_0.tar.gz' --designFile '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/simple/cellranger-tiny-bcl-simple-1_2_0.csv' --outDir 'test'**
+**nextflow run workflow/main.nf --name 'test' --bcl '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/simple1/cellranger-tiny-bcl-1_2_0.tar.gz' --designFile '/project/shared/bicf_workflow_ref/workflow_testdata/cellranger/cellranger_mkfastq/simple1/cellranger-tiny-bcl-simple-1_2_0.csv' --outDir 'test'**
 
 * Design example:
 
@@ -53,4 +53,4 @@ To Run:
 | *    | test_sample | SI-P03-C9 |
 
 
-[**CHANGELOG**](https://git.biohpc.swmed.edu/BICF/Astrocyte/cellranger_mkfastq/blob/develop/CHANGELOG.md)
\ No newline at end of file
+[**CHANGELOG**](https://git.biohpc.swmed.edu/BICF/Astrocyte/cellranger_mkfastq/blob/develop/CHANGELOG.md)

docs/references.md

+### References
+
+1. **python**:
+  * Anaconda (Anaconda Software Distribution, [https://anaconda.com](https://anaconda.com))
+
+2. **pigz**
+  * pigz [https://zlib.net/pigz/](https://zlib.net/pigz/)
+
+3. **cellranger**
+  * Cellranger mkfastq [https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/using/mkfastq](https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/using/mkfastq)
+
+4. **fastqc**
+  * fastqc [https://www.bioinformatics.babraham.ac.uk/projects/fastqc/](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
+
+5. **MultiQc**:
+  * Ewels P., Magnusson M., Lundin S. and Käller M. 2016. MultiQC: Summarize analysis results for multiple tools and samples in a single report. Bioinformatics 32(19): 3047–3048. doi:[10.1093/bioinformatics/btw354](https://dx.doi.org/10.1093/bioinformatics/btw354)

workflow/conf/multiqc_config.yaml

@@ -19,3 +19,9 @@ module_order:
         path_filters:
             - '*_R2_*fastqc.zip'
     - custom_content
+
+report_section_order:
+    Software_Versions:
+      order: -1100
+    Software_References:
+      order: -1200

workflow/main.nf

@@ -8,6 +8,7 @@ params.name = "run"
 params.bcl = "$baseDir/../test_data/*.tar.gz"
 params.designFile = "$baseDir/../test_data/design.csv"
 params.outDir = "$baseDir/output"
+params.references = "$baseDir/../docs/references.md"
 
 // Define List of Files
 tarList = Channel.fromPath( params.bcl )
@@ -18,6 +19,7 @@ designLocation = Channel
   .fromPath(params.designFile)
   .ifEmpty { exit 1, "design file not found: ${params.designFile}" }
 outDir = params.outDir
+references = params.references
 
 process checkDesignFile {
   tag "$name"
@@ -119,7 +121,7 @@ process fastqc {
 process versions {
   tag "$name"
   publishDir "$outDir/misc/${task.process}/$name", mode: 'copy'
-  module 'python/3.6.1-2-anaconda:cellranger/3.0.2:bcl2fastq/2.19.1:fastqc/0.11.5'
+  module 'python/3.6.1-2-anaconda:cellranger/3.0.2:bcl2fastq/2.19.1:fastqc/0.11.5:pandoc/2.7'
 
   input:
 
@@ -136,6 +138,7 @@ process versions {
   bash "$baseDir/scripts/versions_mkfastq.sh"
   bash "$baseDir/scripts/versions_fastqc.sh"
   python3 "$baseDir/scripts/generate_versions.py" -f version_*.txt -o versions
+  python3 "$baseDir/scripts/generate_references.py" -r "$references" -o references
   """
 }
 

workflow/scripts/generate_references.py

+#!/usr/bin/env python
+
+#
+# * --------------------------------------------------------------------------
+# * Licensed under MIT (https://git.biohpc.swmed.edu/BICF/Astrocyte/cellranger_count/LICENSE.md)
+# * --------------------------------------------------------------------------
+#
+
+'''Make header for HTML of references.'''
+
+import argparse
+import subprocess
+import shlex
+import logging
+
+EPILOG = '''
+For more details:
+	%(prog)s --help
+'''
+
+# SETTINGS
+
+logger = logging.getLogger(__name__)
+logger.addHandler(logging.NullHandler())
+logger.propagate = False
+logger.setLevel(logging.INFO)
+
+
+def get_args():
+    '''Define arguments.'''
+
+    parser = argparse.ArgumentParser(
+        description=__doc__, epilog=EPILOG,
+        formatter_class=argparse.RawDescriptionHelpFormatter)
+
+    parser.add_argument('-r', '--reference',
+                        help="The reference file (markdown format).",
+                        required=True)
+
+    parser.add_argument('-o', '--output',
+                        help="The out file name.",
+                        default='references')
+
+    args = parser.parse_args()
+    return args
+
+
+def main():
+    args = get_args()
+    reference = args.reference
+    output = args.output
+
+    out_filename = output + '_mqc.yaml'
+
+    # Header for HTML
+    print('''
+        id: 'Software References'
+        section_name: 'Software References'
+        description: 'This section describes references for the tools used.'
+        plot_type: 'html'
+        data: |
+        '''
+    , file = open(out_filename, "w")
+    )
+
+    # Turn Markdown into HTML
+    references_html = 'bash -c "pandoc -p {} | sed \'s/^/                /\' >> {}"'
+    references_html = references_html.format(reference, out_filename)
+    subprocess.check_call(shlex.split(references_html))
+
+
+if __name__ == '__main__':
+    main()