Fix and test use of GTF and Genename params

CHANGELOG.md

@@ -11,6 +11,7 @@ All notable changes to this project will be documented in this file.
 - Add Python version to MultiQC
 - Add and Update tests
 - Use GTF files instead of TxDb and org libraries in Annotate Peaks
+- Make gtf and geneName files as param inputs
 
 ## [publish_1.0.6 ] - 2019-05-31
 ### Added

workflow/conf/biohpc.config

@@ -74,25 +74,28 @@ params {
   // Reference file paths on BioHPC
   genomes {
     'GRCh38' {
-      bwa = '/project/shared/bicf_workflow_ref/GRCh38'
+      bwa = '/project/shared/bicf_workflow_ref/human/GRCh38'
       genomesize = 'hs'
-      chromsizes = '/project/shared/bicf_workflow_ref/GRCh38/genomefile.txt'
-      fasta = '/project/shared/bicf_workflow_ref/GRCh38/genome.fa'
-      gtf = '/project/shared/bicf_workflow_ref/GRCh38/gencode.gtf'
+      chromsizes = '/project/shared/bicf_workflow_ref/human/GRCh38/genomefile.txt'
+      fasta = '/project/shared/bicf_workflow_ref/human/GRCh38/genome.fa'
+      gtf = '/project/shared/bicf_workflow_ref/human/GRCh38/gencode.gtf'
+      geneNames = '/project/shared/bicf_workflow_ref/human/GRCh38/genenames.txt'
     }
     'GRCh37' {
-      bwa = '/project/shared/bicf_workflow_ref/GRCh37'
+      bwa = '/project/shared/bicf_workflow_ref/human/GRCh37'
       genomesize = 'hs'
-      chromsizes = '/project/shared/bicf_workflow_ref/GRCh37/genomefile.txt'
-      fasta = '/project/shared/bicf_workflow_ref/GRCh37/genome.fa'
-      gtf = '/project/shared/bicf_workflow_ref/GRCh37/gencode.gtf'
+      chromsizes = '/project/shared/bicf_workflow_ref/human/GRCh37/genomefile.txt'
+      fasta = '/project/shared/bicf_workflow_ref/human/GRCh37/genome.fa'
+      gtf = '/project/shared/bicf_workflow_ref/human/GRCh37/gencode.gtf'
+      geneNames = '/project/shared/bicf_workflow_ref/human/GRCh37/genenames.txt'
     }
     'GRCm38' {
-      bwa = '/project/shared/bicf_workflow_ref/GRCm38'
+      bwa = '/project/shared/bicf_workflow_ref/mouse/GRCm38'
       genomesize = 'mm'
-      chromsizes = '/project/shared/bicf_workflow_ref/GRCm38/genomefile.txt'
-      fasta = '/project/shared/bicf_workflow_ref/GRCm38/genome.fa'
-      gtf = '/project/shared/bicf_workflow_ref/GRCm38/gencode.gtf'
+      chromsizes = '/project/shared/bicf_workflow_ref/mouse/GRCm38/genomefile.txt'
+      fasta = '/project/shared/bicf_workflow_ref/mouse/GRCm38/genome.fa'
+      gtf = '/project/shared/bicf_workflow_ref/mouse/GRCm38/gencode.gtf'
+      geneNames = '/project/shared/bicf_workflow_ref/mouse/GRCm38/genenames.txt'
     }
   }
 }

workflow/main.nf

@@ -33,14 +33,27 @@ params.multiqc =  "$baseDir/conf/multiqc_config.yaml"
 if (params.astrocyte) {
   print("Running under astrocyte")
   referenceLocation = "/project/shared/bicf_workflow_ref"
-  params.bwaIndex = "$referenceLocation/$params.genome"
-  params.chromSizes = "$referenceLocation/$params.genome/genomefile.txt"
-  params.fasta = "$referenceLocation/$params.genome/genome.fa"
-  params.gtf = "$referenceLocation/$params.genome/gencode.gtf"
-  if (params.genome == 'GRCh37' || params.genome == 'GRCh38') {
+  if (params.genome == 'GRCh37') {
+    params.bwaIndex = "$referenceLocation/human/$params.genome"
+    params.chromSizes = "$referenceLocation/human/$params.genome/genomefile.txt"
+    params.fasta = "$referenceLocation/human/$params.genome/genome.fa"
+    params.gtf = "$referenceLocation/human/$params.genome/gencode.v19.chr_patch_hapl_scaff.annotation.gtf"
+    params.geneNames = "$referenceLocation/human/$params.genome/genenames.txt"
     params.genomeSize = 'hs'
   } else if (params.genome == 'GRCm38') {
+    params.bwaIndex = "$referenceLocation/mouse/$params.genome"
+    params.chromSizes = "$referenceLocation/mouse/$params.genome/genomefile.txt"
+    params.fasta = "$referenceLocation/mouse/$params.genome/genome.fa"
+    params.gtf = "$referenceLocation/mouse/$params.genome/gencode.vM20.annotation.gtf"
+    params.geneNames = "$referenceLocation/mouse/$params.genome/genenames.txt"
     params.genomeSize = 'mm'
+  } else if (params.genome == 'GRCh38') {
+    params.bwaIndex = "$referenceLocation/human/$params.genome"
+    params.chromSizes = "$referenceLocation/human/$params.genome/genomefile.txt"
+    params.fasta = "$referenceLocation/human/$params.genome/genome.fa"
+    params.gtf = "$referenceLocation/human/$params.genome/gencode.v25.chr_patch_hapl_scaff.annotation.gtf"
+    params.geneNames = "$referenceLocation/human/$params.genome/genenames.txt"
+    params.genomeSize = 'hs'
   }
 } else {
     params.bwaIndex = params.genome ? params.genomes[ params.genome ].bwa ?: false : false
@@ -48,6 +61,7 @@ if (params.astrocyte) {
     params.chromSizes = params.genome ? params.genomes[ params.genome ].chromsizes ?: false : false
     params.fasta = params.genome ? params.genomes[ params.genome ].fasta ?: false : false
     params.gtf = params.genome ? params.genomes[ params.genome ].gtf ?: false : false
+    params.geneNames = params.genome ? params.genomes[ params.genome ].geneNames ?: false : false
 }
 
 
@@ -84,7 +98,9 @@ skipMotif = params.skipMotif
 skipPlotProfile = params.skipPlotProfile
 references = params.references
 multiqc = params.multiqc
-gtfFile = Channel.fromPath(params.gtf)
+gtfFile_plotProfile = Channel.fromPath(params.gtf)
+gtfFile_annotPeaks = Channel.fromPath(params.gtf)
+geneNames = Channel.fromPath(params.geneNames)
 
 // Check design file for errors
 process checkDesignFile {
@@ -469,7 +485,7 @@ process plotProfile {
   input:
 
   file ("*.pooled.fc_signal.bw") from bigwigs.collect()
-  file gtf from gtfFile
+  file gtf from gtfFile_plotProfile
 
   output:
 
@@ -524,6 +540,8 @@ process peakAnnotation {
   input:
 
   file designAnnotatePeaks
+  file gtf from gtfFile_annotPeaks
+  file geneNames
 
   output:
 
@@ -534,7 +552,7 @@ process peakAnnotation {
 
   """
   module load R/3.3.2-gccmkl
-  Rscript $baseDir/scripts/annotate_peaks.R $designAnnotatePeaks $genome
+  Rscript $baseDir/scripts/annotate_peaks.R $designAnnotatePeaks $genome $gtf $geneNames
   """
 
 }

workflow/scripts/annotate_peaks.R

@@ -16,24 +16,18 @@ library(GenomicFeatures)
 args <- commandArgs(trailingOnly=TRUE)
 
 # Check input args
-if (length(args) != 2) {
-  stop("Usage: annotate_peaks.R annotate_design.tsv genome_assembly", call.=FALSE)
+if (length(args) != 4) {
+  stop("Usage: annotate_peaks.R annotate_design.tsv genome_assembly gtf geneNames", call.=FALSE)
 }
 
 design_file <- args[1]
 genome_assembly <- args[2]
+gtf <- args[3]
+geneNames <- args[4]
 
 # Load UCSC Known Genes
-if(genome_assembly=='GRCh37') {
-    txdb <- makeTxDbFromGFF("/project/shared/bicf_workflow_ref/human/GRCh37/gencode.v19.chr_patch_hapl_scaff.annotation.gtf")
-    sym <- read.table("/project/shared/bicf_workflow_ref/human/GRCh37/genenames.txt", header=T, sep='\t') [,4:5]
-} else if(genome_assembly=='GRCm38')  {
-    txdb <- makeTxDbFromGFF("/project/shared/bicf_workflow_ref/mouse/GRCm38/gencode.vM20.annotation.gtf")
-    sym <- read.table("/project/shared/bicf_workflow_ref/mouse/GRCm38/genenames.txt", header=T, sep='\t') [,4:5]
-} else if(genome_assembly=='GRCh38')  {
-    txdb <- makeTxDbFromGFF("/project/shared/bicf_workflow_ref/human/GRCh38/gencode.v25.chr_patch_hapl_scaff.annotation.gtf")
-    sym <- read.table("/project/shared/bicf_workflow_ref/human/GRCh38/genenames.txt", header=T, sep='\t') [,4:5]
-}
+txdb <- makeTxDbFromGFF(gtf)
+sym <- read.table(geneNames, header=T, sep='\t') [,4:5]
 
 # Output version of ChIPseeker
 chipseeker_version = packageVersion('ChIPseeker')