Merge branch 'develop'

workflow/main.nf

@@ -3,8 +3,7 @@
    params.bams = "$baseDir/../test_data/*.bam"
    params.bais = "$baseDir/../test_data/*.bai"
    params.peaks = "$baseDir/../test_data/*.broadPeak"
-   params.genomepath="/project/shared/bicf_workflow_ref/hg19/"
-   species = "hg19"
+   params.genomepath="/project/shared/bicf_workflow_ref/GRCh37"
    toppeakcount = 200
    design_file = file(params.design)
    deeptools_design = Channel.fromPath(params.design)
@@ -88,7 +87,7 @@ process run_chipseeker_diffpeak {
      """
      module load python/2.7.x-anaconda
      module load R/3.3.2-gccmkl
-     Rscript $baseDir/scripts/runChipseeker.R $diffpeak_design_file hg19
+     Rscript $baseDir/scripts/runChipseeker.R $diffpeak_design_file ${params.genomepath}
 """
 }
 

workflow/scripts/runChipseeker.R

@@ -7,17 +7,20 @@ args = commandArgs(trailingOnly=TRUE)
 #}
 
 library(ChIPseeker)
-if(args[2]=="hg19")
+#Parse the genome path and get genome version
+genome = unlist(strsplit(args[2],"[/]"))[-1]
+
+if(genome=="GRCh37")
 { 
 library(TxDb.Hsapiens.UCSC.hg19.knownGene)
 txdb <- TxDb.Hsapiens.UCSC.hg19.knownGene
 }
-if(args[2]=="mm10")
+if(genome=="GRCm38")
 { 
 library(TxDb.Hsapiens.UCSC.mm10.knownGene)
 txdb <- TxDb.Hsapiens.UCSC.mm10.knownGene
 }
-if(args[2]=="hg38")
+if(genome=="GRCh38")
 { 
 library(TxDb.Hsapiens.UCSC.hg38.knownGene)
 txdb <- TxDb.Hsapiens.UCSC.hg38.knownGene

workflow/scripts/runDeepTools.py

@@ -47,7 +47,7 @@ def bam2bw_wrapper(command):
 
 def run_signal(files, labels, genome):
   #compute matrix and draw profile and heatmap
-  gene_bed = genome+"gene.bed"#"/project/BICF/BICF_Core/bchen4/chipseq_analysis/test/genome/"+genome+"/gene.bed"
+  gene_bed = genome+"/gene.bed"#"/project/BICF/BICF_Core/bchen4/chipseq_analysis/test/genome/"+genome+"/gene.bed"
   bw_commands = []
   for f in files:
     bw_commands.append("bamCoverage -bs 10 -b "+f+" -o "+f.replace("bam","bw"))

workflow/scripts/runMemechip.py

@@ -40,7 +40,7 @@ def main():
   #run(args.infile, args.genome, args.limit, args.output)
   #get Pool ready
   dfile = pd.read_csv(args.infile)
-  meme_arglist =  zip(dfile['Peaks'].tolist(),[args.genome+"genome.2bit"]*dfile.shape[0],[str(args.limit)]*dfile.shape[0],dfile['SampleID'].tolist())  
+  meme_arglist =  zip(dfile['Peaks'].tolist(),[args.genome+"/genome.2bit"]*dfile.shape[0],[str(args.limit)]*dfile.shape[0],dfile['SampleID'].tolist())  
   work_pool = Pool(min(12,dfile.shape[0]))
   resultList =  work_pool.map(run_wrapper, meme_arglist)
   work_pool.close()