From 3cc1bd730822f8d72306f7493065db96cd158ae9 Mon Sep 17 00:00:00 2001
From: Beibei Chen <beibei.chen@utsouthwestern.edu>
Date: Wed, 26 Apr 2017 10:19:22 -0500
Subject: [PATCH] remove unessessory files
---
workflow/main.nf | 5 +--
workflow/scripts/process.py | 77 -------------------------------------
2 files changed, 1 insertion(+), 81 deletions(-)
delete mode 100644 workflow/scripts/process.py
diff --git a/workflow/main.nf b/workflow/main.nf
index 8425afc..bb90254 100644
--- a/workflow/main.nf
+++ b/workflow/main.nf
@@ -1,10 +1,9 @@
#!/usr/bin/env nextflow
params.design="$baseDir/../test_data/samplesheet.csv"
params.bams = "$baseDir/../test_data/*.bam"
-// params.bais = "$baseDir/../test_data/*.bai"
params.peaks = "$baseDir/../test_data/*.broadPeak"
params.genomepath="/project/shared/bicf_workflow_ref/GRCh37"
- toppeakcount = 200
+ toppeakcount = -1
design_file = file(params.design)
deeptools_design = Channel.fromPath(params.design)
diffbind_design = Channel.fromPath(params.design)
@@ -17,8 +16,6 @@
diffbind_bams = Channel.fromPath(params.bams)
diffbind_peaks = Channel.fromPath(params.peaks)
meme_peaks = Channel.fromPath(params.peaks)
-// deeptools_bamindex = Channel.fromPath(params.bais)
-// diffbind_bamindex = Channel.fromPath(params.bais)
process bamindex {
publishDir "$baseDir/output/", mode: 'copy'
diff --git a/workflow/scripts/process.py b/workflow/scripts/process.py
deleted file mode 100644
index cc5ab14..0000000
--- a/workflow/scripts/process.py
+++ /dev/null
@@ -1,77 +0,0 @@
-#!/usr/bin/python
-# programmer : bbc
-# usage: main function to call all the procedures for chip-seq analysis
-import sys
-import os
-import argparse as ap
-import logging
-import pandas as pd
-import glob
-import subprocess
-from multiprocessing import Pool
-import runDeepTools
-import runMemechip
-logging.basicConfig(level=10)
-
-
-def prepare_argparser():
- description = "Make wig file for given bed using bam"
- epilog = "For command line options of each command, type %(prog)% COMMAND -h"
- argparser = ap.ArgumentParser(description=description, epilog = epilog)
- argparser.add_argument("-i","--input",dest = "infile",type=str,required=True, help="input design file")
- argparser.add_argument("-g","--genome",dest = "genome",type=str,required=True, help="genome", default="hg19")
- argparser.add_argument("--top-peak",dest="toppeak",type=int, default=-1, help = "Only use top peaks for motif call")
- #argparser.add_argument("-s","--strandtype",dest="stranded",type=str,default="none", choices=["none","reverse","yes"])
- #argparser.add_argument("-n","--name",dest="trackName",type=str,default="UserTrack",help = "track name for bedgraph header")
- return(argparser)
-
-def memechip_wrapper(args):
- #print args
- runMemechip.run(*args)
-
-def main():
- argparser = prepare_argparser()
- args = argparser.parse_args()
- #dfile = pd.read_csv(args.infile)
-
- #for testing, add testing path to all input files
- test_path = "/project/BICF/BICF_Core/bchen4/chipseq_analysis/test/"
- designfile = pd.read_csv(args.infile)
- designfile['Peaks'] = designfile['Peaks'].apply(lambda x: test_path+x)
- designfile['bamReads'] = designfile['bamReads'].apply(lambda x: test_path+x)
- designfile['bamControl'] = designfile['bamControl'].apply(lambda x: test_path+x)
- designfile.to_csv(args.infile+"_new",index=False)
- dfile = pd.read_csv(args.infile+"_new")
- #call deeptools
- runDeepTools.run(args.infile+"_new", args.genome)
- #call diffbind
- this_script = os.path.abspath(__file__).split("/")
- folder = "/".join(this_script[0:len(this_script)-1])
-
- diffbind_command = "Rscript "+folder+"/runDiffBind.R "+args.infile+"_new"
- #logging.debug(diffbind_command)
- p = subprocess.Popen(diffbind_command, shell=True)
- p.communicate()
- #call chipseeker on original peaks and overlapping peaks
- chipseeker_command = "Rscript "+folder+"/runChipseeker.R "+",".join(dfile['Peaks'].tolist())+" "+",".join(dfile['SampleID'])
-#BC## logging.debug(chipseeker_command)
- p = subprocess.Popen(chipseeker_command, shell=True)
- p.communicate()
- overlapping_peaks = glob.glob('*diffbind.bed')
- overlapping_peak_names = []
- for pn in overlapping_peaks:
- overlapping_peak_names.append(pn.split("_diffbind")[0].replace("!","non"))
- chipseeker_overlap_command = "Rscript "+folder+"/runChipseeker.R "+",".join(overlapping_peaks)+" "+",".join(overlapping_peak_names)
- p = subprocess.Popen(chipseeker_overlap_command, shell=True)
- p.communicate()
- #MEME-chip on all peaks
- meme_arglist = zip(dfile['Peaks'].tolist(),[test_path+"hg19.2bit"]*dfile.shape[0],[str(args.toppeak)]*dfile.shape[0],dfile['SampleID'].tolist())
-#BC# #print meme_arglist
- work_pool = Pool(min(12,dfile.shape[0]))
- resultList = work_pool.map(memechip_wrapper, meme_arglist)
- work_pool.close()
- work_pool.join()
-
-
-if __name__=="__main__":
- main()
--
GitLab