Merge branch '27-CheckStyle' into 'develop'

fixed style Closes #27 See merge request !48

Merge branch '27-CheckStyle' into 'develop'
fixed style Closes #27 See merge request !48
026b2a52 · Gervaise Henry · 302083f1 · 1fe100af · 026b2a52 · 026b2a52
Commit 026b2a52 authored 5 years ago by Gervaise Henry
--- a/README.md
+++ b/README.md
@@ -103,3 +103,10 @@ To Run:
 | sample2 | pbmc_1k_v2_S2_L002_R1_001.fastq.gz | pbmc_1k_v2_S2_L002_R2_001.fastq.gz |

 [**CHANGELOG**](https://git.biohpc.swmed.edu/BICF/Astrocyte/cellranger_count/blob/develop/CHANGELOG.md)
+
+Credits
+-------
+This worklow is was developed jointly with the [Bioinformatic Core Facility (BICF), Department of Bioinformatics](http://www.utsouthwestern.edu/labs/bioinformatics/)
+
+
+Please cite in publications: Pipeline was developed by BICF from funding provided by **Cancer Prevention and Research Institute of Texas (RP150596)**.
--- a/astrocyte_pkg.yml
+++ b/astrocyte_pkg.yml
@@ -98,15 +98,15 @@ workflow_parameters:
  - id: genome
    type: select
    choices:
-      - [ 'GRCh38-3.0.0', 'Human GRCh38 release 93']
-      - [ 'GRCh38-1.2.0', 'Human GRCh38 release 84']
-      - [ 'hg19-3.0.0', 'Human GRCh37 (hg19) release 87']
-      - [ 'hg19-1.2.0', 'Human GRCh37 (hg19) release 84']
-      - [ 'mm10-3.0.0', 'Mouse GRCm38 (mm10) release 93']
-      - [ 'mm10-1.2.0', 'Mouse GRCm38 (mm10) release 84']
-      - [ 'hg19_and_mm10-3.0.0', 'Human GRCh37 (hg19) + Mouse GRCm38 (mm19) release 93']
-      - [ 'hg19_and_mm10-1.2.0', 'Human GRCh37 (hg19) + Mouse GRCm38 (mm19) release 84']
-      - [ 'ercc92-1.2.0', 'ERCC.92 Spike-In']
+      - ['GRCh38-3.0.0', 'Human GRCh38 release 93']
+      - ['GRCh38-1.2.0', 'Human GRCh38 release 84']
+      - ['hg19-3.0.0', 'Human GRCh37 (hg19) release 87']
+      - ['hg19-1.2.0', 'Human GRCh37 (hg19) release 84']
+      - ['mm10-3.0.0', 'Mouse GRCm38 (mm10) release 93']
+      - ['mm10-1.2.0', 'Mouse GRCm38 (mm10) release 84']
+      - ['hg19_and_mm10-3.0.0', 'Human GRCh37 (hg19) + Mouse GRCm38 (mm19) release 93']
+      - ['hg19_and_mm10-1.2.0', 'Human GRCh37 (hg19) + Mouse GRCm38 (mm19) release 84']
+      - ['ercc92-1.2.0', 'ERCC.92 Spike-In']
    required: true
    description: |
      Reference species and genome used for alignment and subsequent analysis.
@@ -133,9 +133,9 @@ workflow_parameters:
    type: select
    default: 'auto'
    choices:
-      - [ 'auto', 'Auto Detect']
-      - [ 'three', '3']
-      - [ 'two', '2']
+      - ['auto', 'Auto Detect']
+      - ['three', '3']
+      - ['two', '2']
    required: true
    description: |
      10x single cell gene expression chemistry version (only used in cellranger version 3.x).
@@ -144,9 +144,9 @@ workflow_parameters:
    type: select
    default: '3.0.2'
    choices:
-      - [ '3.0.2', '3.0.2']
-      - [ '3.0.1', '3.0.1']
-      - [ '2.1.1', '2.1.1']
+      - ['3.0.2', '3.0.2']
+      - ['3.0.1', '3.0.1']
+      - ['2.1.1', '2.1.1']
    required: true
    description: |
      10x cellranger version.

--- a/docs/index.md
+++ b/docs/index.md
@@ -8,6 +8,10 @@ This pipeline is a wrapper for the cellranger count tool from 10x Genomics. It t

 The pipeline uses Nextflow, a bioinformatics workflow tool.

+This pipeline is primarily used with a SLURM cluster on the BioHPC Cluster. However, the pipeline should be able to run on any system that Nextflow supports.
+
+Additionally, the pipeline is designed to work with Astrocyte Workflow System using a simple web interface.
+
 To Run:
 -------


--- a/docs/references.md
+++ b/docs/references.md
@@ -8,3 +8,6 @@

 3. **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)
+
+4. **Nextflow**:
+  * Di Tommaso P., Chatzou M., Floden E. W., Barja P. P., Palumbo E., and Notredame C. 2017. Nextflow enables reproducible computational workflows. Nature biotechnology 35(4): 316. doi:[10.1038/nbt.3820](https://doi.org/10.1038/nbt.3820)
--- a/workflow/main.nf
+++ b/workflow/main.nf
@@ -5,17 +5,17 @@

 // Define Input variables
 params.name = "run"
-params.fastq = "$baseDir/../test_data/*.fastq.gz"
-params.designFile = "$baseDir/../test_data/design.csv"
+params.fastq = "${baseDir}/../test_data/*.fastq.gz"
+params.designFile = "${baseDir}/../test_data/design.csv"
 params.genome = 'GRCh38-3.0.0'
 params.expectCells = 10000
 params.forceCells = 0
 params.kitVersion = 'three'
 params.version = '3.0.2'
 params.astrocyte = false
-params.outDir = "$baseDir/output"
-params.multiqcConf = "$baseDir/conf/multiqc_config.yaml"
-params.references = "$baseDir/../docs/references.md"
+params.outDir = "${baseDir}/output"
+params.multiqcConf = "${baseDir}/conf/multiqc_config.yaml"
+params.references = "${baseDir}/../docs/references.md"

 // Assign variables if astrocyte
 if (params.astrocyte) {
@@ -61,23 +61,25 @@ references = params.references


 process checkDesignFile {
-  tag "$name"
-  publishDir "$outDir/misc/${task.process}/$name", mode: 'copy'
+
+  tag "${name}"
+  publishDir "${outDir}/misc/${task.process}/${name}", mode: 'copy'
  module 'python/3.6.1-2-anaconda'

  input:
-  file designLocation
-  file fastqList
+    file designLocation
+    file fastqList

  output:
-  file("design.checked.csv") into designPaths
+    file("design.checked.csv") into designPaths

  script:
-  """
-  hostname
-  ulimit -a
-  python3 $baseDir/scripts/check_design.py -d $designLocation -f $fastqList
-  """
+    """
+    hostname
+    ulimit -a
+    python3 ${baseDir}/scripts/check_design.py -d ${designLocation} -f ${fastqList}
+    """
+
 }


@@ -88,6 +90,7 @@ samples = designPaths
  .groupTuple()
  //.subscribe { println it }

+
 // Duplicate variables
 samples.into {
  samples211
@@ -110,171 +113,186 @@ chemistryParam302 = chemistryParam


 process count211 {
+
  queue '128GB,256GB,256GBv1,384GB'
-  tag "$sample"
-  publishDir "$outDir/${task.process}", mode: 'copy'
+  tag "${sample}"
+  publishDir "${outDir}/${task.process}", mode: 'copy'
  module 'cellranger/2.1.1'

  input:
-  set sample, file("${sample}_S1_L00?_R1_001.fastq.gz"), file("${sample}_S1_L00?_R2_001.fastq.gz") from samples211
-  file ref from refLocation211.first()
-  expectCells211
-  forceCells211
+    set sample, file("${sample}_S1_L00?_R1_001.fastq.gz"), file("${sample}_S1_L00?_R2_001.fastq.gz") from samples211
+    file ref from refLocation211.first()
+    expectCells211
+    forceCells211

  output:
-  file("**/outs/**") into outPaths211
-  file("*_metrics_summary.tsv") into metricsSummary211
+    file("**/outs/**") into outPaths211
+    file("*_metrics_summary.tsv") into metricsSummary211

  when:
  version == '2.1.1'

  script:
-  if (forceCells211 == 0){
-    """
-	  hostname
-    ulimit -a
-    bash "$baseDir/scripts/filename_check.sh" -r "$ref"
-    cellranger count --id="$sample" --transcriptome="./$ref" --fastqs=. --sample="$sample" --expect-cells=$expectCells211
-    sed -E 's/("([^"]*)")?,/\\2\t/g' ${sample}/outs/metrics_summary.csv | tr -d "," | sed "s/^/${sample}\t/" > ${sample}_metrics_summary.tsv
-    """
-  } else {
-    """
-	  hostname
-    ulimit -a
-    bash "$baseDir/scripts/filename_check.sh" -r "$ref"
-    cellranger count --id="$sample" --transcriptome="./$ref" --fastqs=. --sample="$sample" --force-cells=$forceCells211
-    sed -E 's/("([^"]*)")?,/\\2\t/g' ${sample}/outs/metrics_summary.csv | tr -d "," | sed "s/^/${sample}\t/" > ${sample}_metrics_summary.tsv
-    """
-  }
+    if (forceCells211 == 0) {
+      """
+      hostname
+      ulimit -a
+      bash ${baseDir}/scripts/filename_check.sh -r ${ref}
+      cellranger count --id=${sample} --transcriptome=./${ref} --fastqs=. --sample=${sample} --expect-cells=${expectCells211}
+      sed -E 's/("([^"]*)")?,/\\2\t/g' ${sample}/outs/metrics_summary.csv | tr -d "," | sed "s/^/${sample}\t/" > ${sample}_metrics_summary.tsv
+      """
+    } 
+    else {
+      """
+      hostname
+      ulimit -a
+      bash ${baseDir}/scripts/filename_check.sh -r ${ref}
+      cellranger count --id=${sample} --transcriptome=./${ref} --fastqs=. --sample=${sample} --force-cells=${forceCells211}
+      sed -E 's/("([^"]*)")?,/\\2\t/g' ${sample}/outs/metrics_summary.csv | tr -d "," | sed "s/^/${sample}\t/" > ${sample}_metrics_summary.tsv
+      """
+    }
+
 }


 process count301 {
+
  queue '128GB,256GB,256GBv1,384GB'
-  tag "$sample"
-  publishDir "$outDir/${task.process}", mode: 'copy'
+  tag "${sample}"
+  publishDir "${outDir}/${task.process}", mode: 'copy'
  module 'cellranger/3.0.1'

  input:
-  set sample, file("${sample}_S1_L00?_R1_001.fastq.gz"), file("${sample}_S1_L00?_R2_001.fastq.gz") from samples301
-  file ref from refLocation301.first()
-  expectCells301
-  forceCells301
-  chemistryParam301
+    set sample, file("${sample}_S1_L00?_R1_001.fastq.gz"), file("${sample}_S1_L00?_R2_001.fastq.gz") from samples301
+    file ref from refLocation301.first()
+    expectCells301
+    forceCells301
+    chemistryParam301

  output:
-  file("**/outs/**") into outPaths301
-  file("*_metrics_summary.tsv") into metricsSummary301
+    file("**/outs/**") into outPaths301
+    file("*_metrics_summary.tsv") into metricsSummary301

  when:
-  version == '3.0.1'
+    version == '3.0.1'

  script:
-  if (forceCells301 == 0){
-    """
-    hostname
-    ulimit -a
-    bash "$baseDir/scripts/filename_check.sh" -r "$ref"
-    cellranger count --id="$sample" --transcriptome="./$ref" --fastqs=. --sample="$sample" --expect-cells=$expectCells301 --chemistry="$chemistryParam301"
-    sed -E 's/("([^"]*)")?,/\\2\t/g' ${sample}/outs/metrics_summary.csv | tr -d "," | sed "s/^/${sample}\t/" > ${sample}_metrics_summary.tsv
-    """
-  } else {
-    """
-    hostname
-    ulimit -a
-    bash "$baseDir/scripts/filename_check.sh" -r "$ref"
-    cellranger count --id="$sample" --transcriptome="./$ref" --fastqs=. --sample="$sample" --force-cells=$forceCells301 --chemistry="$chemistryParam301"
-    sed -E 's/("([^"]*)")?,/\\2\t/g' ${sample}/outs/metrics_summary.csv | tr -d "," | sed "s/^/${sample}\t/" > ${sample}_metrics_summary.tsv
-    """
-  }
+    if (forceCells301 == 0) {
+      """
+      hostname
+      ulimit -a
+      bash ${baseDir}/scripts/filename_check.sh -r ${ref}
+      cellranger count --id=${sample} --transcriptome=./${ref} --fastqs=. --sample=${sample} --expect-cells=${expectCells301} --chemistry=${chemistryParam301}
+      sed -E 's/("([^"]*)")?,/\\2\t/g' ${sample}/outs/metrics_summary.csv | tr -d "," | sed "s/^/${sample}\t/" > ${sample}_metrics_summary.tsv
+      """
+    } 
+    else {
+      """
+      hostname
+      ulimit -a
+      bash ${baseDir}/scripts/filename_check.sh -r ${ref}
+      cellranger count --id=${sample} --transcriptome=./${ref} --fastqs=. --sample=${sample} --force-cells=${forceCells301} --chemistry=${chemistryParam301}
+      sed -E 's/("([^"]*)")?,/\\2\t/g' ${sample}/outs/metrics_summary.csv | tr -d "," | sed "s/^/${sample}\t/" > ${sample}_metrics_summary.tsv
+      """
+    }
+
 }


 process count302 {
+
  queue '128GB,256GB,256GBv1,384GB'
-  tag "$sample"
-  publishDir "$outDir/${task.process}", mode: 'copy'
+  tag "${sample}"
+  publishDir "${outDir}/${task.process}", mode: 'copy'
  module 'cellranger/3.0.2'

  input:
-  set sample, file("${sample}_S?_L001_R1_001.fastq.gz"), file("${sample}_S?_L001_R2_001.fastq.gz") from samples302
-  file ref from refLocation302.first()
-  expectCells302
-  forceCells302
-  chemistryParam302
+    set sample, file("${sample}_S?_L001_R1_001.fastq.gz"), file("${sample}_S?_L001_R2_001.fastq.gz") from samples302
+    file ref from refLocation302.first()
+    expectCells302
+    forceCells302
+    chemistryParam302

  output:
-  file("**/outs/**") into outPaths302
-  file("*_metrics_summary.tsv") into metricsSummary302
+    file("**/outs/**") into outPaths302
+    file("*_metrics_summary.tsv") into metricsSummary302

  when:
-  version == '3.0.2'
+    version == '3.0.2'

  script:
-  if (forceCells302 == 0){
-    """
-	  hostname
-    ulimit -a
-    bash "$baseDir/scripts/filename_check.sh" -r "$ref"
-    cellranger count --id="$sample" --transcriptome="./$ref" --fastqs=. --sample="$sample" --expect-cells=$expectCells302 --chemistry="$chemistryParam302"
-    sed -E 's/("([^"]*)")?,/\\2\t/g' ${sample}/outs/metrics_summary.csv | tr -d "," | sed "s/^/${sample}\t/" > ${sample}_metrics_summary.tsv
-    """
-  } else {
-    """
-	  hostname
-    ulimit -a
-    bash "$baseDir/scripts/filename_check.sh" -r "$ref"
-    cellranger count --id="$sample" --transcriptome="./$ref" --fastqs=. --sample="$sample" --force-cells=$forceCells302 --chemistry="$chemistryParam302"
-    sed -E 's/("([^"]*)")?,/\\2\t/g' ${sample}/outs/metrics_summary.csv | tr -d "," | sed "s/^/${sample}\t/" > ${sample}_metrics_summary.tsv
-    """
-  }
+    if (forceCells302 == 0) {
+      """
+      hostname
+      ulimit -a
+      bash ${baseDir}/scripts/filename_check.sh -r ${ref}
+      cellranger count --id=${sample} --transcriptome=./${ref} --fastqs=. --sample=${sample} --expect-cells=${expectCells302} --chemistry=${chemistryParam302}
+      sed -E 's/("([^"]*)")?,/\\2\t/g' ${sample}/outs/metrics_summary.csv | tr -d "," | sed "s/^/${sample}\t/" > ${sample}_metrics_summary.tsv
+      """
+    } 
+    else {
+      """
+      hostname
+      ulimit -a
+      bash ${baseDir}/scripts/filename_check.sh -r ${ref}
+      cellranger count --id=${sample} --transcriptome=./${ref} --fastqs=. --sample=${sample} --force-cells=${forceCells302} --chemistry=${chemistryParam302}
+      sed -E 's/("([^"]*)")?,/\\2\t/g' ${sample}/outs/metrics_summary.csv | tr -d "," | sed "s/^/${sample}\t/" > ${sample}_metrics_summary.tsv
+      """
+    }
+
 }


 process versions {
-  tag "$name"
-  publishDir "$outDir/misc/${task.process}/$name", mode: 'copy'
+
+  tag "${name}"
+  publishDir "${outDir}/misc/${task.process}/${name}", mode: 'copy'
  module 'python/3.6.1-2-anaconda:pandoc/2.7:multiqc/1.7'

  input:

  output:
-  file("*.yaml") into yamlPaths
+    file("*.yaml") into yamlPaths

  script:
-  """
-  hostname
-  ulimit -a
-  echo $workflow.nextflow.version > version_nextflow.txt
-  echo $version > version_cellranger.txt
-  multiqc --version | tr -d 'multiqc, version ' > version_multiqc.txt
-  python3 "$baseDir/scripts/generate_versions.py" -f version_*.txt -o versions
-  python3 "$baseDir/scripts/generate_references.py" -r "$references" -o references
-  """
+    """
+    hostname
+    ulimit -a
+    echo ${workflow.nextflow.version} > version_nextflow.txt
+    echo ${version} > version_cellranger.txt
+    multiqc --version | tr -d 'multiqc, version ' > version_multiqc.txt
+    python3 "${baseDir}/scripts/generate_versions.py" -f version_*.txt -o versions
+    python3 "${baseDir}/scripts/generate_references.py" -r "${references}" -o references
+    """
+
 }

+
 metricsSummary = metricsSummary211.mix(metricsSummary301, metricsSummary302)

+
 // Generate MultiQC Report
 process multiqc {
-  tag "$name"
+
+  tag "${name}"
  queue 'super'
-  publishDir "$outDir/${task.process}/$name", mode: 'copy'
+  publishDir "${outDir}/${task.process}/${name}", mode: 'copy'
  module 'multiqc/1.7'

  input:
-  file ('*') from metricsSummary.collect()
-  file yamlPaths
+    file ('*') from metricsSummary.collect()
+    file yamlPaths

  output:
-  file "multiqc_report.html" into mqcPaths
+    file "multiqc_report.html" into mqcPaths

  script:
-  """
-  hostname
-  ulimit -a
-  awk 'FNR==1 && NR!=1{next;}{print}' *.tsv > metrics_summary_mqc.tsv
-  sed -i '1s/^.*\tE/Sample\tE/' metrics_summary_mqc.tsv
-  multiqc -c $multiqcConf .
-  """
+    """
+    hostname
+    ulimit -a
+    awk 'FNR==1 && NR!=1{next;}{print}' *.tsv > metrics_summary_mqc.tsv
+    sed -i '1s/^.*\tE/Sample\tE/' metrics_summary_mqc.tsv
+    multiqc -c ${multiqcConf} .
+    """
+
 }
--- a/workflow/scripts/check_design.py
+++ b/workflow/scripts/check_design.py
@@ -39,13 +39,14 @@ def get_args():


 def check_design_headers(design):
-    '''Check if design file conforms to sequencing type.'''
+    '''Check if design file contains correct headers.'''

    # Default headers
    design_template = [
        'Sample',
-	    'fastq_R1',
-	    'fastq_R2']
+	'fastq_R1',
+	'fastq_R2',
+        ]

    design_headers = list(design.columns.values)


--- a/workflow/scripts/filename_check.sh
+++ b/workflow/scripts/filename_check.sh
@@ -5,28 +5,27 @@ usage() {
  echo "-r  --ref file"
  exit 1
 }
+
 OPTIND=1
 while getopts :r: opt
 do
-   case $opt in
-        r) ref=$OPTARG;;
-   esac
+  case ${opt} in
+    r) ref=${OPTARG};;
+  esac
 done

-shift $(($OPTIND -1));
+shift $((${OPTIND} -1))

-name=`readlink -e $ref`
+name=$(readlink -e ${ref})

-if [ `find $name -name "* *" | wc -l` -gt 0 ];
-then
-   echo "Error: Spaces found in Reference Files";
-   echo `find $name -name "* *"`;
-   exit 21;
-fi;
+if [ $(find $name -name "* *" | wc -l) -gt 0 ]; then
+  echo "Error: Spaces found in Reference Files"
+  echo $(find $name -name "* *")
+  exit 21
+fi

-if [ $(echo "$ref" | tr -d ' ') != "$ref" ];
-then
-   echo "Error: Spaces found in Reference Files";
-   echo "$ref";
-   exit 21;
-fi;
+if [ $(echo "${ref}" | tr -d ' ') != "${ref}" ]; then
+  echo "Error: Spaces found in Reference Files"
+  echo ${ref}
+  exit 21
+fi
--- a/workflow/scripts/generate_references.py
+++ b/workflow/scripts/generate_references.py
-#
-# * --------------------------------------------------------------------------
-# * Licensed under MIT (https://git.biohpc.swmed.edu/BICF/Astrocyte/cellranger_count/LICENSE.md)
-# * --------------------------------------------------------------------------
-#
+#!/usr/bin/env python3

 '''Make header for HTML of references.'''


--- a/workflow/scripts/generate_versions.py
+++ b/workflow/scripts/generate_versions.py
@@ -16,7 +16,6 @@ For more details:
 '''

 # SETTINGS
-
 logger = logging.getLogger(__name__)
 logger.addHandler(logging.NullHandler())
 logger.propagate = False