Merge branch '75-rename_plotprofile' into 'dev'

Resolve "Rename Plot profile to be consistent with naming"

Closes #75

See merge request !67

.gitlab-ci.yml

@@ -17,6 +17,13 @@ user_configuration:
   script:
   - pytest -m unit --cov=./workflow/scripts
 
+bash_tests:
+  stage: unit
+  script:
+    - module load singularity/3.0.2
+    - module load deeptools/2.5.0.1
+    - singularity run docker://bats/bats:v1.1.0 --tap workflow/tests/plot_profile.bats
+
 astrocyte:
   stage: astrocyte
   script:

README.md

@@ -75,6 +75,7 @@ $ git clone git@git.biohpc.swmed.edu:BICF/Astrocyte/chipseq_analysis.git
     9. Annotate all peaks using ChipSeeker
     10. Calculate Differential Binding Activity with DiffBind (If more than 1 rep in more than 1 experiment)
     11. Use MEME-ChIP to find motifs in original peaks
+    12. Plot enrichment of signal around TSS
 
 See [FLOWCHART](docs/flowchart.pdf)
 

docs/index.md

@@ -20,6 +20,7 @@ Report issues to the Bioinformatic Core Facility [BICF](mailto:BICF@UTSouthweste
     9. Annotate all peaks using ChipSeeker
     10. Calculate Differential Binding Activity with DiffBind (If more than 1 rep in more than 1 experiment)
     11. Use MEME-ChIP to find motifs in original peaks
+    12. Plot enrichment of signal around TSS
 
 
 ## Workflow Parameters

workflow/main.nf

@@ -98,9 +98,8 @@ skipMotif = params.skipMotif
 skipPlotProfile = params.skipPlotProfile
 references = params.references
 multiqc = params.multiqc
-gtfFile_plotProfile = Channel.fromPath(params.gtf)
-gtfFile_annotPeaks = Channel.fromPath(params.gtf)
-geneNames = Channel.fromPath(params.geneNames)
+gtfFile = params.gtf
+geneNames = params.geneNames
 
 // Check design file for errors
 process checkDesignFile {
@@ -484,8 +483,7 @@ process plotProfile {
 
   input:
 
-  file ("*.pooled.fc_signal.bw") from bigwigs.collect()
-  file gtf from gtfFile_plotProfile
+  file bigWigList from bigwigs.collect()
 
   output:
 
@@ -498,7 +496,7 @@ process plotProfile {
   script:
   """
   module load deeptools/2.5.0.1
-  bash $baseDir/scripts/plotProfile.sh
+  bash $baseDir/scripts/plot_profile.sh -g $gtfFile
   """
 }
 
@@ -540,8 +538,6 @@ process peakAnnotation {
   input:
 
   file designAnnotatePeaks
-  file gtf from gtfFile_annotPeaks
-  file geneNames
 
   output:
 
@@ -552,7 +548,7 @@ process peakAnnotation {
 
   """
   module load R/3.3.2-gccmkl
-  Rscript $baseDir/scripts/annotate_peaks.R $designAnnotatePeaks $gtf $geneNames
+  Rscript $baseDir/scripts/annotate_peaks.R $designAnnotatePeaks $gtfFile $geneNames
   """
 
 }

workflow/scripts/plotProfile.sh

-#!/bin/bash
-#plotProfile.sh
-
-bws=$(ls *.bw)
-gtf=$(ls *.gtf *.bed)
-
-computeMatrix reference-point \
-	--referencePoint TSS \
-	-S $bws \
-	-R $gtf \
-	--skipZeros \
-	-o computeMatrix.gz
-	-p max/2
-
-plotProfile -m computeMatrix.gz \
-	-out plotProfile.png \

workflow/scripts/plot_profile.sh

+#!/bin/bash
+#plot_profile.sh
+
+script_name="plot_profile.sh"
+
+#Help function
+usage() {
+  echo "-h  --Help documentation for $script_name"
+  echo "-g  --File path to gtf/bed files"
+  echo "Example: $script_name -g 'genome.gtf'"
+  exit 1
+}
+
+
+raise()
+{
+  echo "${1}" >&2
+}
+
+check_tools() {
+  raise "
+   Checking for required libraries and components on this system
+   "
+   deeptools --version &> version_deeptools.txt
+   if [ $? -gt 0 ]
+     then
+      raise "Missing deeptools"
+      return 1
+    fi
+}
+
+compute_matrix() {
+  raise "
+  Computing matrix on ${1} using ${2}
+  "
+
+  computeMatrix reference-point \
+    --referencePoint TSS \
+    -S ${1} \
+    -R ${2} \
+    --skipZeros \
+    -o computeMatrix.gz \
+    -p max/2
+
+  if [ $? -gt 0 ]
+  then
+    raise "Problem building matrix"
+    return 1
+  fi
+}
+
+plot_profile() {
+  raise "
+  Plotting profile
+  "
+
+  plotProfile -m computeMatrix.gz \
+    -out plotProfile.png
+
+  if [ $? -gt 0 ]
+  then
+    raise "Problem plotting"
+    return 1
+  fi
+}
+
+
+run_main() {
+
+  # Parsing options
+  OPTIND=1 # Reset OPTIND
+  while getopts :g:h opt
+      do
+          case $opt in
+              g) gtf=$OPTARG;;
+              h) usage;;
+          esac
+      done
+
+  shift $(($OPTIND -1))
+
+  # Check for mandatory options
+  if [[ -z $gtf ]]; then
+      usage
+  fi
+
+  bws=$(ls *pooled.fc_signal.bw)
+
+  check_tools || exit 1
+
+  compute_matrix "${bws}" "${gtf}" || return 1
+
+  plot_profile || return 1
+
+  raise "ALL COMPLETE"
+}
+
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]
+then
+  run_main "$@"
+  if [ $? -gt 0 ]
+  then
+    exit 1
+  fi
+fi

workflow/tests/plot_profile.bats

+#!/opt/bats/libexec/bats-core/ bats
+
+profile_script="./workflow/scripts/plot_profile.sh"
+
+@test "Test deeptools present" {
+  source ${profile_script}
+  run check_tools
+}
+
+@test "Test deeptools computeMatrix" {
+  source ${profile_script}
+  run compute_matrix test_data/ENCSR238SGC_pooled.fc_signal.bw /project/shared/bicf_workflow_ref/mouse/GRCm38/gencode.vM20.annotation.gtf
+  FILE=computeMatrix.gz
+  if [[ -s "$FILE" ]]; then
+      echo "$FILE exists and not empty"
+  fi
+}
+
+@test "Test deeptools plotProfile" {
+  source ${profile_script}
+  run plot_profile computeMatrix.gz
+  FILE=plotProfile.png
+  if [[ -s "$FILE" ]]; then
+      echo "$FILE exists and not empty"
+  fi
+}

workflow/tests/test_plot_profile.py

@@ -11,8 +11,9 @@ test_output_path = os.path.dirname(os.path.abspath(__file__)) + \
 @pytest.mark.singleend
 def test_plot_singleend():
     assert os.path.exists(os.path.join(test_output_path, 'plotProfile.png'))
-
+    assert os.path.getsize(os.path.join(test_output_path, 'plotProfile.png')) > 0
 
 @pytest.mark.pairedend
 def test_plot_pairedend():
-    assert os.path.exists(os.path.join(test_output_path, 'computeMatrix.gz'))
+    assert os.path.exists(os.path.join(test_output_path, 'plotProfile.png'))
+    assert os.path.getsize(os.path.join(test_output_path, 'plotProfile.png')) > 0