Bump woodstox-core from 5.0.3 to 5.4.0 in /share/script/jar/META-INF/maven/org.apache.logging.log4j/log4j-core

Readme.md

@@ -1,3 +1,6 @@
+[![DOI](https://zenodo.org/badge/179099583.svg)](https://zenodo.org/badge/latestdoi/179099583)
+
+
 # HemTools: a collection of NGS pipelines and bioinformatic analyses
 
 The code here is tailored specifically for HPCF at Stjude. It may not work directly outside Stjude.

bin/0101_clean.py

@@ -0,0 +1,76 @@
+#!/usr/bin/env python
+
+import pandas as pd
+import sys
+import os
+import argparse
+
+
+def my_args():
+	mainParser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+	mainParser.add_argument('-o',"--output", help="output file", default="my_table.json")
+
+	# group.add_argument('--outward',  help="get outward reads", action='store_true')
+	# group.add_argument('--inward',  help="get inward reads", action='store_true')
+	group = mainParser.add_mutually_exclusive_group(required=True)
+	group.add_argument('-p','--pipeline_name',  help="which pipeline to run, e.g., atac_seq")
+	group.add_argument("--list_pipelines",  help="list all available pipelines",action='store_true')		
+	group.add_argument("--guess_input",  help="Let the program generate the input files for you.",action='store_true')
+	group.add_argument("--user_lsf",  help="user defined lsf file")
+
+
+	mainParser.add_argument('-f',"--input",  help="tab delimited any number of columns (tsv file), the last column is output prefix. For example, a paired-end fastq input could be: Read 1 fastq, Read 2 fastq, sample ID")
+	mainParser.add_argument('-q',"--queue",  help="submit queue",default="standard")
+
+
+	mainParser.add_argument('-f2',"--input2",  help="for jobs with dependencies. tab delimited any number of columns (tsv file), the last column is output prefix. For example, a paired-end fastq input could be: Read 1 fastq, Read 2 fastq, sample ID")
+
+
+	# mainParser.add_argument("--single",  help="default is paired-end data, specify this parameter if you have single-end data",action='store_true')		
+	mainParser.add_argument("--csv",  help="convert tsv to csv when doing guess_input",action='store_true')		
+	mainParser.add_argument("--email",  help="send user the fastq.tsv file",action='store_true')		
+
+	genome=mainParser.add_argument_group(title='Genome Info')
+	genome.add_argument('-g','--genome',  help="genome version: hg19, hg38, mm9, mm10. By default, specifying a genome version will automatically update index file, black list, chrom size and effectiveGenomeSize, unless a user explicitly sets those options.", default='hg19',type=str)
+	genome.add_argument('-i','--index_file',  help="BWA index file", default=myData['hg19_BWA_index'])
+	genome.add_argument('-b','--black_list',  help="Blacklist file", default=myData['hg19_black_list'])
+	genome.add_argument('-s','--chrom_size',  help="chrome size", default=myData['hg19_chrom_size'])
+	genome.add_argument('-e','--effectiveGenomeSize',  help="effectiveGenomeSize for bamCoverage", default=myPars['hg19_effectiveGenomeSize'])
+	mainParser.add_argument('--interactive',  help="run pipeline interatively", action='store_true')
+
+	mainParser.add_argument('-s',"--sample_list",  help="table rows, a list of samples, these are supposed to be folder names, one column",required=True)
+	mainParser.add_argument('-f','--feature_list',  help="table columns, map file name to specific feature name",required=True)
+	# mainParser.add_argument('--softlinks',  help=argparse.SUPPRESS,default="")
+	# mainParser.add_argument('--treatment_bam',  help=argparse.SUPPRESS)
+	# mainParser.add_argument('--port',  help=argparse.SUPPRESS)
+
+	##------- add parameters above ---------------------
+	args = mainParser.parse_args()	
+	return args
+
+def main():
+
+	args = my_args()
+
+
+
+if __name__ == "__main__":
+	main()
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

bin/AB_compartment.py

@@ -0,0 +1,96 @@
+#!/hpcf/apps/python/install/2.7.13/bin/python
+import sys
+import os
+p_dir = os.path.dirname(os.path.realpath(__file__)) + "/"
+sys.path.append(os.path.abspath(p_dir+"../utils/"))
+from utils import *
+import multiprocessing 
+import time 
+
+
+
+"""
+Every python wrapper is supposed to be similar, since they are using the same convention.
+
+The only thing need to be changed is the guess_input function and the argparser function.
+
+look for ## CHANGE THE FUNCTION HERE FOR DIFFERENT WRAPPER
+
+variable inherents from utils:
+myData
+myPars
+myPipelines
+"""
+current_file_base_name = __file__.split("/")[-1].split(".")[0]
+def my_args():
+	mainParser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
+	mainParser.add_argument('-j',"--jid",  help="enter a job ID, which is used to make a new directory. Every output will be moved into this folder.", default=current_file_base_name+'_'+username+"_"+str(datetime.date.today()))	
+
+
+	mainParser.add_argument('-f','--h5_list',  help="two columns tsv") # hicpro input data
+	mainParser.add_argument('--queue',  default="priority")
+	mainParser.add_argument('--interactive',  help="run pipeline interatively", action='store_true')
+
+
+	##------- add parameters above ---------------------
+	args = mainParser.parse_args()	
+	return args
+
+
+def main():
+
+	args = my_args()
+	##------- check if jid exist  ----------------------
+	if isdir(args.jid):
+		addon_string = str(uuid.uuid4()).split("-")[-1]
+		logging.warning ("The input job id is not available!")
+		args.jid = args.jid+"_"+addon_string
+		logging.info ("The new job id is: "+args.jid)
+	else:
+		logging.info ("The job id is: "+args.jid)			
+
+	##------- add functions below ----------------------
+	os.system("mkdir -p %s"%(args.jid))
+	os.system("mkdir -p %s/log_files"%(args.jid))
+
+
+	#-------------- run jobs ----------------------
+
+
+	pipeline_name = current_file_base_name
+
+	if args.interactive:
+		run_interative_jobs(myPipelines[pipeline_name],args)
+		exit()
+
+
+	submit_pipeline_jobs(myPipelines[pipeline_name],args)
+
+
+if __name__ == "__main__":
+	main()
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

bin/BaseSpaceRunDownloader_v2.py

@@ -0,0 +1,106 @@
+#!/usr/bin/env python
+from urllib2 import Request, urlopen, URLError
+import json
+import math
+import sys
+import os
+import socket
+import optparse
+
+"""
+python BaseSpaceRunDownloader_v2.py -r 190257127 -a 4d645052b0be44009f7cd98bb9acf6cf
+
+"""
+
+def arg_parser():
+    cwd_dir = os.getcwd()
+    parser = optparse.OptionParser()
+    parser.add_option( '-r', dest='runid', help='Run ID: required')
+    parser.add_option( '-a', dest='accesstoken', help='Access Token: required')
+    ( options, args ) = parser.parse_args()
+
+    try:
+       if options.runid == None:
+             raise Exception
+       if options.accesstoken == None:
+	     raise Exception
+
+    except Exception:
+	    print("Usage: BaseSpaceRunDownloader_vN.py -r <RunID> -a <AccessToken>")
+	    sys.exit()
+
+    return options
+
+def restrequest(rawrequest):
+	request = Request(rawrequest)
+
+	try:
+        	response = urlopen(request)
+        	json_string = response.read()
+        	json_obj = json.loads(json_string)
+
+	except URLError, e:
+    		print 'Got an error code:', e
+		sys.exit()
+
+	return json_obj
+
+def downloadrestrequest(rawrequest,path):
+	dirname = RunID + os.sep + os.path.dirname(path)
+
+	if dirname != '':
+		if not os.path.isdir(dirname):
+			os.makedirs(dirname)
+
+	request = (rawrequest)
+
+	outfile = open(RunID + os.sep + path,'wb')
+
+        try:
+                response = urlopen(request,timeout=1)
+
+		outfile.write(response.read())
+		outfile.close()
+
+        except URLError, e:
+                print 'Got an error code:', e
+		outfile.close()
+		downloadrestrequest(rawrequest,path)
+
+
+	except socket.error:
+		print 'Got a socket error: retrying'
+		outfile.close()
+		downloadrestrequest(rawrequest,path)
+
+
+options = arg_parser()
+
+RunID = options.runid
+AccessToken = options.accesstoken
+
+request = 'http://api.basespace.illumina.com/v1pre3/runs/%s/files?access_token=%s' %(RunID,AccessToken)
+
+json_obj = restrequest(request)
+totalCount = json_obj['Response']['TotalCount']
+
+noffsets = int(math.ceil(float(totalCount)/1000.0))
+
+hreflist = []
+pathlist = []
+filenamelist = [] 
+for index in range(noffsets):
+	offset = 1000*index
+	request = 'http://api.basespace.illumina.com/v1pre3/runs/%s/files?access_token=%s&limit=1000&Offset=%s' %(RunID,AccessToken,offset) 
+	json_obj = restrequest(request)
+	nfiles = len(json_obj['Response']['Items'])
+	for fileindex in range(nfiles):
+		href = json_obj['Response']['Items'][fileindex]['Href']
+		hreflist.append(href)
+		path = json_obj['Response']['Items'][fileindex]['Path']
+		pathlist.append(path)
+
+for index in range(len(hreflist)):
+	request = 'http://api.basespace.illumina.com/%s/content?access_token=%s'%(hreflist[index],AccessToken)
+	print 'downloading %s' %(pathlist[index]) 
+	downloadrestrequest(request, pathlist[index])