def callRiger(rigerTableFile, scoring='KSbyScore', output='', callRiger=True):
'''
calls riger using the KS scoring metric (default)
'''
rigerDirectory = '/raider/temp/riger/'
rigerTableAbsFile = os.path.abspath(rigerTableFile)
outputFolder = utils.getParentFolder(rigerTableAbsFile)
if len(output) == 0:
output = string.replace(rigerTableAbsFile, '_friger.txt',
'_friger_%s_out.txt' % (scoring))
rigerBashFileName = string.replace(rigerTableAbsFile, '_friger.txt',
'_callRiger.sh')
rigerBashFile = open(rigerBashFileName, 'w')
rigerBashFile.write('#!/usr/bin/bash\n')
rigerBashFile.write('cd %s\n\n' % (rigerDirectory))
rigerCmd = 'java -cp commons-cli-1.2.jar:rigerj-1.6.2.jar org.broadinstitute.rnai.rigerj.RigerJMain -scoringMethod %s -inputFile %s -outputFile %s' % (
scoring, rigerTableAbsFile, output)
rigerBashFile.write(rigerCmd)
rigerBashFile.write('\n')
rigerBashFile.close()
print("WROTE RIGER CMD TO %s" % (rigerBashFileName))
if callRiger == True:
print("Calling RIGER with %s scoring method" % (scoring))
print("RIGER CMD: %s" % (rigerCmd))
os.system(rigerBashFileName)
return rigerBashFileName
def callRiger(rigerTableFile,scoring='KSbyScore',output='',callRiger = True):
'''
calls riger using the KS scoring metric (default)
'''
rigerDirectory = '/raider/temp/riger/'
rigerTableAbsFile = os.path.abspath(rigerTableFile)
outputFolder = utils.getParentFolder(rigerTableAbsFile)
if len(output) == 0:
output = string.replace(rigerTableAbsFile,'_friger.txt','_friger_%s_out.txt' % (scoring))
rigerBashFileName = string.replace(rigerTableAbsFile,'_friger.txt','_callRiger.sh')
rigerBashFile = open(rigerBashFileName,'w')
rigerBashFile.write('#!/usr/bin/bash\n')
rigerBashFile.write('cd %s\n\n' % (rigerDirectory))
rigerCmd = 'java -cp commons-cli-1.2.jar:rigerj-1.6.2.jar org.broadinstitute.rnai.rigerj.RigerJMain -scoringMethod %s -inputFile %s -outputFile %s' % (scoring,rigerTableAbsFile,output)
rigerBashFile.write(rigerCmd)
rigerBashFile.write('\n')
rigerBashFile.close()
print("WROTE RIGER CMD TO %s" % (rigerBashFileName))
if callRiger == True:
print("Calling RIGER with %s scoring method" % (scoring))
print("RIGER CMD: %s" % (rigerCmd))
os.system(rigerBashFileName)
return rigerBashFileName
def makeNameDict(dataFile,roseFolder,namesList=[]):
'''
for each name, check for the presence of an enriched file or allEnhancer table
these are the files required for enhancer clustering
'''
dataDict = pipeline_dfci.loadDataTable(dataFile)
#draw the parent folder from the dataFile
parentFolder = utils.getParentFolder(dataFile)
#check to see if a rose folder exists already
if utils.formatFolder(roseFolder,False):
roseExists = True
roseFolder = utils.formatFolder(roseFolder,False)
else:
roseExists = False
roseFolder = utils.formatFolder(roseFolder,True)
#check namesList to see if datasets exist
if len(namesList) == 0:
namesList = [name for name in dataDict.keys() if dataDict[name]['background'] != 'NONE']
#this filters out control WCE datatsets
#now check that all of the datasets at a minimum have a rose output OR enriched region file
nameDict = {}
for name in namesList:
nameDict[name] = {}
#assumes standard folder structure for enriched file
enrichedFile = "%smacsEnriched/%s" % (parentFolder,dataDict[name]['enrichedMacs'])
print enrichedFile
try:
foo = open(enrichedFile,'r')
foo.close()
nameDict[name]['enrichedFile'] = enrichedFile
except IOError:
nameDict[name]['enrichedFile'] = ''
#roseOutput looks for standard format rose output
#need an allEnhancers table and a region table to proceed
#if the rose folder doesn't exist, don't bother
if roseExists:
roseOutputFiles = os.listdir("%s%s_ROSE" % (roseFolder,name))
allEnhancerFileList = [x for x in roseOutputFiles if x.count("AllEnhancers.table.txt") == 1 and x[0] != '.' ] #no weird hidden or temp files
if len(allEnhancerFileList) > 0:
nameDict[name]['enhancerFile'] = "%s%s_ROSE/%s" % (roseFolder,name,allEnhancerFileList[0])
else:
nameDict[name]['enhancerFile'] = ''
if nameDict[name]['enhancerFile'] == '' and nameDict[name]['enrichedFile'] =='':
print "INSUFFICIENT DATA TO RUN ENAHNCER ANALYSIS ON %s. PLEASE MAKE SURE ROSE OUTPUT OR MACS ENRICHED REGION PEAKS FILE EXISTS" % (name)
sys.exit()
return nameDict
def launchDynamicRose(analysis_name,group1_name,group2_name,group1_list,group2_list,meta_rose_folder,dynamic_rose_folder,genome,data_file,activity_path,inputGFF):
'''
launches meta rose
'''
project_folder = utils.formatFolder(os.path.abspath(utils.getParentFolder(data_file)),False)
dataDict = pipeline_dfci.loadDataTable(data_file)
genome_build = genome.name()
meta_rose_output_1 = utils.formatFolder(meta_rose_folder + group1_name,True)
meta_rose_output_2 = utils.formatFolder(meta_rose_folder + group2_name,True)
meta_rose_string = ','.join([meta_rose_output_1,meta_rose_output_2])
#setting the output
dynamic_rose_folder = utils.formatFolder(dynamic_rose_folder,True)
group1_string = ','.join(group1_list)
group2_string = ','.join(group2_list)
dynamic_cmd = 'python %sdynamicEnhancer_meta.py -g %s -d %s -r %s -o %s --group1 %s --group2 %s --name1 %s --name2 %s -p -m' % (pipeline_dir,genome_build,data_file,meta_rose_string,dynamic_rose_folder,group1_string,group2_string,group1_name,group2_name)
if len(inputGFF) > 0:
dynamic_cmd += ' --input %s' % (inputGFF)
bash_path ='%s%s_dynamic_meta.sh' % (dynamic_rose_folder,analysis_name)
bash_file = open(bash_path,'w')
bash_file.write('#!/usr/bin/bash\n\n')
bash_file.write('cd %s\n\n' % (pipeline_dir))
bash_file.write(dynamic_cmd)
bash_file.write('\n\n')
bash_file.close()
print('Wrote DYNAMIC_META command for %s to %s' % (analysis_name,bash_path))
print('Launching DYNAMIC_META_ROSE')
os.system('bash %s' % (bash_path))
def launchMetaRose(group_name,group_list,meta_rose_folder,genome,data_file,stitch,tss):
'''
launches meta rose
'''
project_folder = utils.formatFolder(os.path.abspath(utils.getParentFolder(data_file)),False)
macs_folder = '%smacsEnriched/' % (project_folder) #quick hack to make sure input beds are in the right place
dataDict = pipeline_dfci.loadDataTable(data_file)
meta_rose_output = utils.formatFolder(meta_rose_folder + group_name,True)
genome_build = genome.name()
input_string = ','.join(['%s%s' % (macs_folder,dataDict[name]['enrichedMacs']) for name in group_list])
bam_string = ','.join([dataDict[name]['bam'] for name in group_list])
meta_cmd = 'python %sROSE2_META.py -g %s -i %s -r %s -o %s -n %s -t %s' % (pipeline_dir,genome_build,input_string,bam_string,meta_rose_output,group_name,tss)
if stitch != None:
meta_cmd += ' -s %s' % (stitch)
#adding a mask if necessary
if genome.hasFeature('mask'):
meta_cmd += ' --mask %s' % (genome.returnFeature('mask'))
bash_path ='%s%s_meta_rose.sh' % (meta_rose_output,group_name)
bash_file = open(bash_path,'w')
bash_file.write('#!/usr/bin/bash\n\n')
bash_file.write('cd %s\n\n' % (pipeline_dir))
bash_file.write(meta_cmd)
bash_file.write('\n\n')
bash_file.close()
print('Wrote META_ROSE command for %s to %s' % (group_name,bash_path))
print('Launching META_ROSE')
os.system('bash %s' % (bash_path))
def main():
"""
main run function
"""
#usage = "usage: %prog [options] -g [GENOME] -b [SORTED BAMFILE(S)] -i [INPUTFILE] -o [OUTPUTFOLDER]"
parser = argparse.ArgumentParser(
usage='%(prog)s -i SAMFILE -g REF_GENOME -s SPIKE_GENOME')
# required flags
parser.add_argument("-i",
"--input",
dest="inputSam",
type=str,
help="Enter a sam file",
required=False)
parser.add_argument("-g",
"--genome",
dest="genome",
type=str,
help="specify the main reference genome",
required=False)
parser.add_argument("-s",
"--spike",
dest="spike",
type=str,
help="specify the spike in genome",
required=False)
parser.add_argument(
"-d",
"--dest",
dest="dest",
type=str,
help="specify an optional destination for the final bams to move to",
required=False)
args = parser.parse_args()
print(args)
if args.inputSam and args.genome and args.spike:
print(
'FORMATTING %s FOR CHIP_RX USING REFERENCE GENOME %s and SPIKE_IN GENOME %s'
% (args.inputSam, args.genome, args.spike))
samPath = args.inputSam
if string.upper(samPath).count('.SAM') == 0:
print('ERROR, file must end in .sam or .SAM')
sys.exit()
#get the headers
genome_string = string.upper('%s_%s' % (args.genome, args.spike))
genomeDict = {
'RN6_DM6': [
'/grail/genomes/Rattus_norvegicus/UCSC/rn6/Sequence/Bowtie2Index_dm6/rn6_header.SAM',
'/grail/genomes/Rattus_norvegicus/UCSC/rn6/Sequence/Bowtie2Index_dm6/dm6_header.SAM'
],
}
if genomeDict.has_key(genome_string) == False:
print('ERROR: UNSUPPORTED GENOME COMBINATION %s' % (genome_string))
sys.exit()
else:
print('IDENTIFIED HEADERS FOR GENOME COMBINATION %s' %
(genome_string))
header1 = genomeDict[genome_string][0]
header2 = genomeDict[genome_string][1]
suffix = string.lower('_%s' % (args.spike))
outfile1 = string.replace(samPath, samPath[-4:],
'.%s%s' % (args.genome, samPath[-4:]))
outfile2 = string.replace(samPath, samPath[-4:],
'.%s%s' % (args.spike, samPath[-4:]))
split_sam(suffix, samPath, header1, header2, outfile1, outfile2)
#move stuff to destination folder
if args.dest:
bamFolder = utils.formatFolder(args.dest, False)
samFolder = utils.getParentFolder(samPath)
mv_cmd = 'mv %s*bam* %s' % (samFolder, bamFolder)
print('MOVING BAMS FROM %s TO %s' % (samFolder, bamFolder))
os.system(mv_cmd)
else:
parser.print_help()
sys.exit()
def makeNameDict(dataFile, roseFolder, namesList=[], enhancerType='super'):
'''
for each name, check for the presence of an enriched file or allEnhancer table
these are the files required for enhancer clustering
'''
dataDict = pipeline_dfci.loadDataTable(dataFile)
#draw the parent folder from the dataFile
parentFolder = utils.getParentFolder(dataFile)
print "Using %s as the parent folder" % (parentFolder)
#check to see if a rose folder exists already
if utils.formatFolder(roseFolder, False):
roseExists = True
roseFolder = utils.formatFolder(roseFolder, False)
else:
roseExists = False
roseFolder = utils.formatFolder(roseFolder, True)
#check namesList to see if datasets exist
if len(namesList) == 0:
namesList = [
name for name in dataDict.keys()
if string.upper(name).count('WCE') == 0
and string.upper(name).count('INPUT') == 0
]
#if no namesList is given, this filters out WCE
#now check that all of the datasets at a minimum have a rose output OR enriched region file
nameDict = {}
for name in namesList:
nameDict[name] = {}
#check if each dataset has a background
backgroundName = dataDict[name]['background']
if dataDict.has_key(backgroundName):
nameDict[name]['background'] = True
else:
nameDict[name]['background'] = False
#assumes standard folder structure for enriched file
enrichedFile = "%smacsEnriched/%s" % (parentFolder,
dataDict[name]['enrichedMacs'])
print "Looking for macs output at %s" % (enrichedFile)
try:
foo = open(enrichedFile, 'r')
foo.close()
nameDict[name]['enrichedFile'] = enrichedFile
except IOError:
nameDict[name]['enrichedFile'] = ''
#roseOutput looks for standard format rose output
#need an allEnhancers table and a region table to proceed
#if the rose folder doesn't exist, don't bother
if roseExists:
try:
roseOutputFiles = os.listdir("%s%s_ROSE" % (roseFolder, name))
if enhancerType == 'super':
enhancerString = 'AllEnhancers.table.txt'
if enhancerType == 'stretch':
enhancerString = 'AllEnhancers_Length.table.txt'
if enhancerType == 'superstretch':
enhancerString = 'AllEnhancers_SuperStretch.table.txt'
allEnhancerFileList = [
x for x in roseOutputFiles
if x.count(enhancerString) == 1 and x[0] != '.'
] #no weird hidden or temp files
if len(allEnhancerFileList) > 0:
nameDict[name]['enhancerFile'] = "%s%s_ROSE/%s" % (
roseFolder, name, allEnhancerFileList[0])
else:
nameDict[name]['enhancerFile'] = ''
except OSError:
nameDict[name]['enhancerFile'] = ''
else:
nameDict[name]['enhancerFile'] = ''
if nameDict[name]['enhancerFile'] == '' and nameDict[name][
'enrichedFile'] == '':
print "INSUFFICIENT DATA TO RUN ENAHNCER ANALYSIS ON %s. PLEASE MAKE SURE ROSE OUTPUT OR MACS ENRICHED REGION PEAKS FILE EXISTS" % (
name)
print nameDict[name]
sys.exit()
return nameDict
def extractGuideFastq(fastqFile,outputFolder='',gzip=False):
'''
takes a fastq and extracts candidate guide RNAs
'''
#get the full absolute path for the fastq File
fastqFile = os.path.abspath(fastqFile)
fastq = utils.open(fastqFile,'r')
#get the fastq name and root
if len(outputFolder) == 0:
outputFolder = utils.getParentFolder(fastqFile)
#makes sure the output folder exists
utils.formatFolder(outputFolder,True)
#grab the name info from the fastq
fastqName = fastqFile.split('/')[-1]
fastqRoot = string.replace(fastqName,'.fastq','')
fastqRoot = string.replace(fastqRoot,'.gz','')
#guideFastqFile output
guideFastqFile = '%s%s.gecko.fastq' % (outputFolder,fastqRoot)
guideFastq = utils.open(guideFastqFile,'w')
print('processing %s' % (fastqName))
print('million reads processed:')
ticker = 0
found = 0
while True:
if ticker%1000000 == 0:
print(ticker/1000000)
fastqLines = []
#now load the fastq lines
try:
for i in range(4):
fastqLines.append(fastq.next())
except StopIteration:
break
#see if you can find a cut site
seq = fastqLines[1].rstrip()
try:
cutPosition = seq.index(cutSeq)
found+=1
except ValueError:
ticker+=1
continue
guideStart = cutPosition + cutOffset
guideStop = guideStart + guideLength
#pulling out the guide seq in the fastqLines
fastqLines[1] = fastqLines[1][guideStart:guideStop] + '\n'
fastqLines[3] = fastqLines[3][guideStart:guideStop] + '\n'
for line in fastqLines:
guideFastq.write(line)
ticker+=1
# if ticker == 100000:
# print(ticker)
# print(found)
# print(float(found)/float(ticker))
# break
print('SUMMARY STATISTICS')
print(ticker)
print(found)
print(float(found)/float(ticker))
#close the fastq
guideFastq.close()
#gzip the fastq
if gzip:
os.system('gzip %s &' % (guideFastqFile))
guideFastqFile += '.gz'
return guideFastqFile
def makeNameDict(dataFile,roseFolder,namesList=[],enhancerType='super'):
'''
for each name, check for the presence of an enriched file or allEnhancer table
these are the files required for enhancer clustering
'''
dataDict = pipeline_dfci.loadDataTable(dataFile)
#draw the parent folder from the dataFile
parentFolder = utils.getParentFolder(dataFile)
print "Using %s as the parent folder" % (parentFolder)
#check to see if a rose folder exists already
if utils.formatFolder(roseFolder,False):
roseExists = True
roseFolder = utils.formatFolder(roseFolder,False)
else:
roseExists = False
roseFolder = utils.formatFolder(roseFolder,True)
#check namesList to see if datasets exist
if len(namesList) == 0:
namesList = [name for name in dataDict.keys() if string.upper(name).count('WCE') ==0 and string.upper(name).count('INPUT') == 0 ]
#if no namesList is given, this filters out WCE
#now check that all of the datasets at a minimum have a rose output OR enriched region file
nameDict = {}
for name in namesList:
nameDict[name] = {}
#check if each dataset has a background
backgroundName = dataDict[name]['background']
if dataDict.has_key(backgroundName):
nameDict[name]['background'] = True
else:
nameDict[name]['background'] = False
#assumes standard folder structure for enriched file
enrichedFile = "%smacsEnriched/%s" % (parentFolder,dataDict[name]['enrichedMacs'])
print "Looking for macs output at %s" % (enrichedFile)
try:
foo = open(enrichedFile,'r')
foo.close()
nameDict[name]['enrichedFile'] = enrichedFile
except IOError:
nameDict[name]['enrichedFile'] = ''
#roseOutput looks for standard format rose output
#need an allEnhancers table and a region table to proceed
#if the rose folder doesn't exist, don't bother
if roseExists:
try:
roseOutputFiles = os.listdir("%s%s_ROSE" % (roseFolder,name))
if enhancerType == 'super':
enhancerString = 'AllEnhancers.table.txt'
if enhancerType == 'stretch':
enhancerString = 'AllEnhancers_Length.table.txt'
if enhancerType == 'superstretch':
enhancerString = 'AllEnhancers_SuperStretch.table.txt'
allEnhancerFileList = [x for x in roseOutputFiles if x.count(enhancerString) == 1 and x[0] != '.' ] #no weird hidden or temp files
if len(allEnhancerFileList) > 0:
nameDict[name]['enhancerFile'] = "%s%s_ROSE/%s" % (roseFolder,name,allEnhancerFileList[0])
else:
nameDict[name]['enhancerFile'] = ''
except OSError:
nameDict[name]['enhancerFile']=''
else:
nameDict[name]['enhancerFile'] = ''
if nameDict[name]['enhancerFile'] == '' and nameDict[name]['enrichedFile'] =='':
print "INSUFFICIENT DATA TO RUN ENAHNCER ANALYSIS ON %s. PLEASE MAKE SURE ROSE OUTPUT OR MACS ENRICHED REGION PEAKS FILE EXISTS" % (name)
print nameDict[name]
sys.exit()
return nameDict
def mapEnhancerToGeneTop(rankByBamFile, controlBamFile, genome, annotFile, enhancerFile, transcribedFile='', uniqueGenes=True, searchWindow=50000, noFormatTable=False):
'''
maps genes to enhancers. if uniqueGenes, reduces to gene name only. Otherwise, gives for each refseq
'''
startDict = utils.makeStartDict(annotFile)
enhancerName = enhancerFile.split('/')[-1].split('.')[0]
enhancerTable = utils.parseTable(enhancerFile, '\t')
# internal parameter for debugging
byRefseq = False
if len(transcribedFile) > 0:
transcribedTable = utils.parseTable(transcribedFile, '\t')
transcribedGenes = [line[1] for line in transcribedTable]
else:
transcribedGenes = startDict.keys()
print('MAKING TRANSCRIPT COLLECTION')
transcribedCollection = utils.makeTranscriptCollection(
annotFile, 0, 0, 500, transcribedGenes)
print('MAKING TSS COLLECTION')
tssLoci = []
for geneID in transcribedGenes:
tssLoci.append(utils.makeTSSLocus(geneID, startDict, 0, 0))
# this turns the tssLoci list into a LocusCollection
# 50 is the internal parameter for LocusCollection and doesn't really
# matter
tssCollection = utils.LocusCollection(tssLoci, 50)
geneDict = {'overlapping': defaultdict(
list), 'proximal': defaultdict(list)}
# dictionaries to hold ranks and superstatus of gene nearby enhancers
rankDict = defaultdict(list)
superDict = defaultdict(list)
# list of all genes that appear in this analysis
overallGeneList = []
# find the damn header
for line in enhancerTable:
if line[0][0] == '#':
continue
else:
header = line
break
if noFormatTable:
# set up the output tables
# first by enhancer
enhancerToGeneTable = [
header + ['OVERLAP_GENES', 'PROXIMAL_GENES', 'CLOSEST_GENE']]
else:
# set up the output tables
# first by enhancer
enhancerToGeneTable = [
header[0:9] + ['OVERLAP_GENES', 'PROXIMAL_GENES', 'CLOSEST_GENE'] + header[-2:]]
# next by gene
geneToEnhancerTable = [
['GENE_NAME', 'REFSEQ_ID', 'PROXIMAL_ENHANCERS']]
# next make the gene to enhancer table
geneToEnhancerTable = [
['GENE_NAME', 'REFSEQ_ID', 'PROXIMAL_ENHANCERS', 'ENHANCER_RANKS', 'IS_SUPER', 'ENHANCER_SIGNAL']]
for line in enhancerTable:
if line[0][0] == '#' or line[0][0] == 'R':
continue
enhancerString = '%s:%s-%s' % (line[1], line[2], line[3])
enhancerLocus = utils.Locus(line[1], line[2], line[3], '.', line[0])
# overlapping genes are transcribed genes whose transcript is directly
# in the stitchedLocus
overlappingLoci = transcribedCollection.getOverlap(
enhancerLocus, 'both')
overlappingGenes = []
for overlapLocus in overlappingLoci:
overlappingGenes.append(overlapLocus.ID())
# proximalGenes are transcribed genes where the tss is within 50kb of
# the boundary of the stitched loci
proximalLoci = tssCollection.getOverlap(
utils.makeSearchLocus(enhancerLocus, searchWindow, searchWindow), 'both')
proximalGenes = []
for proxLocus in proximalLoci:
proximalGenes.append(proxLocus.ID())
distalLoci = tssCollection.getOverlap(
utils.makeSearchLocus(enhancerLocus, 1000000, 1000000), 'both')
distalGenes = []
for proxLocus in distalLoci:
distalGenes.append(proxLocus.ID())
overlappingGenes = utils.uniquify(overlappingGenes)
proximalGenes = utils.uniquify(proximalGenes)
distalGenes = utils.uniquify(distalGenes)
allEnhancerGenes = overlappingGenes + proximalGenes + distalGenes
# these checks make sure each gene list is unique.
# technically it is possible for a gene to be overlapping, but not proximal since the
# gene could be longer than the 50kb window, but we'll let that slide
# here
for refID in overlappingGenes:
if proximalGenes.count(refID) == 1:
proximalGenes.remove(refID)
for refID in proximalGenes:
if distalGenes.count(refID) == 1:
distalGenes.remove(refID)
# Now find the closest gene
if len(allEnhancerGenes) == 0:
closestGene = ''
else:
# get enhancerCenter
enhancerCenter = (int(line[2]) + int(line[3])) / 2
# get absolute distance to enhancer center
distList = [abs(enhancerCenter - startDict[geneID]['start'][0])
for geneID in allEnhancerGenes]
# get the ID and convert to name
closestGene = startDict[
allEnhancerGenes[distList.index(min(distList))]]['name']
# NOW WRITE THE ROW FOR THE ENHANCER TABLE
if noFormatTable:
newEnhancerLine = list(line)
newEnhancerLine.append(
join(utils.uniquify([startDict[x]['name'] for x in overlappingGenes]), ','))
newEnhancerLine.append(
join(utils.uniquify([startDict[x]['name'] for x in proximalGenes]), ','))
newEnhancerLine.append(closestGene)
else:
newEnhancerLine = line[0:9]
newEnhancerLine.append(
join(utils.uniquify([startDict[x]['name'] for x in overlappingGenes]), ','))
newEnhancerLine.append(
join(utils.uniquify([startDict[x]['name'] for x in proximalGenes]), ','))
newEnhancerLine.append(closestGene)
newEnhancerLine += line[-2:]
enhancerToGeneTable.append(newEnhancerLine)
# Now grab all overlapping and proximal genes for the gene ordered
# table
overallGeneList += overlappingGenes
for refID in overlappingGenes:
geneDict['overlapping'][refID].append(enhancerString)
rankDict[refID].append(int(line[-2]))
superDict[refID].append(int(line[-1]))
overallGeneList += proximalGenes
for refID in proximalGenes:
geneDict['proximal'][refID].append(enhancerString)
rankDict[refID].append(int(line[-2]))
superDict[refID].append(int(line[-1]))
# End loop through
# Make table by gene
print('MAKING ENHANCER ASSOCIATED GENE TSS COLLECTION')
overallGeneList = utils.uniquify(overallGeneList)
enhancerGeneCollection = utils.makeTranscriptCollection(
annotFile, 5000, 5000, 500, overallGeneList)
enhancerGeneGFF = utils.locusCollectionToGFF(enhancerGeneCollection)
# dump the gff to file
enhancerFolder = utils.getParentFolder(enhancerFile)
gffRootName = "%s_TSS_ENHANCER_GENES_-5000_+5000" % (genome)
enhancerGeneGFFFile = "%s%s_%s.gff" % (enhancerFolder, enhancerName,gffRootName)
utils.unParseTable(enhancerGeneGFF, enhancerGeneGFFFile, '\t')
# now we need to run bamToGFF
# Try to use the bamliquidatior_path.py script on cluster, otherwise, failover to local (in path), otherwise fail.
bamliquidator_path = '/ark/home/jdm/pipeline/bamliquidator_batch.py'
if not os.path.isfile(bamliquidator_path):
bamliquidator_path = 'bamliquidator_batch.py'
if not os.path.isfile(bamliquidator_path):
raise ValueError('bamliquidator_batch.py not found in path')
print('MAPPING SIGNAL AT ENHANCER ASSOCIATED GENE TSS')
# map density at genes in the +/- 5kb tss region
# first on the rankBy bam
bamName = rankByBamFile.split('/')[-1]
mappedRankByFolder = "%s%s_%s_%s/" % (enhancerFolder, enhancerName,gffRootName, bamName)
mappedRankByFile = "%s%s_%s_%s/matrix.gff" % (enhancerFolder,enhancerName, gffRootName, bamName)
cmd = 'python ' + bamliquidator_path + ' --sense . -e 200 --match_bamToGFF -r %s -o %s %s' % (enhancerGeneGFFFile, mappedRankByFolder,rankByBamFile)
print("Mapping rankby bam %s" % (rankByBamFile))
print(cmd)
outputRank = subprocess.Popen(cmd, stdout=subprocess.PIPE, shell=True)
outputRank = outputRank.communicate()
if len(outputRank[0]) > 0: # test if mapping worked correctly
print("SUCCESSFULLY MAPPED TO %s FROM BAM: %s" % (enhancerGeneGFFFile, rankByBamFile))
else:
print("ERROR: FAILED TO MAP %s FROM BAM: %s" % (enhancerGeneGFFFile, rankByBamFile))
sys.exit()
# next on the control bam if it exists
if len(controlBamFile) > 0:
controlName = controlBamFile.split('/')[-1]
mappedControlFolder = "%s%s_%s_%s/" % (
enhancerFolder, enhancerName,gffRootName, controlName)
mappedControlFile = "%s%s_%s_%s/matrix.gff" % (
enhancerFolder, enhancerName,gffRootName, controlName)
cmd = 'python ' + bamliquidator_path + ' --sense . -e 200 --match_bamToGFF -r %s -o %s %s' % (enhancerGeneGFFFile, mappedControlFolder,controlBamFile)
print("Mapping control bam %s" % (controlBamFile))
print(cmd)
outputControl = subprocess.Popen(cmd, stdout=subprocess.PIPE, shell=True)
outputControl = outputControl.communicate()
if len(outputControl[0]) > 0: # test if mapping worked correctly
print("SUCCESSFULLY MAPPED TO %s FROM BAM: %s" % (enhancerGeneGFFFile, controlBamFile))
else:
print("ERROR: FAILED TO MAP %s FROM BAM: %s" % (enhancerGeneGFFFile, controlBamFile))
sys.exit()
# now get the appropriate output files
if len(controlBamFile) > 0:
print("CHECKING FOR MAPPED OUTPUT AT %s AND %s" %
(mappedRankByFile, mappedControlFile))
if utils.checkOutput(mappedRankByFile, 1, 1) and utils.checkOutput(mappedControlFile, 1, 1):
print('MAKING ENHANCER ASSOCIATED GENE TSS SIGNAL DICTIONARIES')
signalDict = makeSignalDict(mappedRankByFile, mappedControlFile)
else:
print("NO MAPPING OUTPUT DETECTED")
sys.exit()
else:
print("CHECKING FOR MAPPED OUTPUT AT %s" % (mappedRankByFile))
if utils.checkOutput(mappedRankByFile, 1, 30):
print('MAKING ENHANCER ASSOCIATED GENE TSS SIGNAL DICTIONARIES')
signalDict = makeSignalDict(mappedRankByFile)
else:
print("NO MAPPING OUTPUT DETECTED")
sys.exit()
# use enhancer rank to order
rankOrder = utils.order([min(rankDict[x]) for x in overallGeneList])
usedNames = []
# make a new dict to hold TSS signal by max per geneName
geneNameSigDict = defaultdict(list)
print('MAKING GENE TABLE')
for i in rankOrder:
refID = overallGeneList[i]
geneName = startDict[refID]['name']
if usedNames.count(geneName) > 0 and uniqueGenes == True:
continue
else:
usedNames.append(geneName)
proxEnhancers = geneDict['overlapping'][
refID] + geneDict['proximal'][refID]
superStatus = max(superDict[refID])
enhancerRanks = join([str(x) for x in rankDict[refID]], ',')
enhancerSignal = signalDict[refID]
geneNameSigDict[geneName].append(enhancerSignal)
newLine = [geneName, refID, join(
proxEnhancers, ','), enhancerRanks, superStatus, enhancerSignal]
geneToEnhancerTable.append(newLine)
#utils.unParseTable(geneToEnhancerTable,'/grail/projects/newRose/geneMapper/foo.txt','\t')
print('MAKING ENHANCER TO TOP GENE TABLE')
if noFormatTable:
enhancerToTopGeneTable = [
enhancerToGeneTable[0] + ['TOP_GENE', 'TSS_SIGNAL']]
else:
enhancerToTopGeneTable = [enhancerToGeneTable[0][0:12] + [
'TOP_GENE', 'TSS_SIGNAL'] + enhancerToGeneTable[0][-2:]]
for line in enhancerToGeneTable[1:]:
geneList = []
if noFormatTable:
geneList += line[-3].split(',')
geneList += line[-2].split(',')
else:
geneList += line[10].split(',')
geneList += line[11].split(',')
geneList = utils.uniquify([x for x in geneList if len(x) > 0])
if len(geneList) > 0:
try:
sigVector = [max(geneNameSigDict[x]) for x in geneList]
maxIndex = sigVector.index(max(sigVector))
maxGene = geneList[maxIndex]
maxSig = sigVector[maxIndex]
if maxSig == 0.0:
maxGene = 'NONE'
maxSig = 'NONE'
except ValueError:
if len(geneList) == 1:
maxGene = geneList[0]
maxSig = 'NONE'
else:
maxGene = 'NONE'
maxSig = 'NONE'
else:
maxGene = 'NONE'
maxSig = 'NONE'
if noFormatTable:
newLine = line + [maxGene, maxSig]
else:
newLine = line[0:12] + [maxGene, maxSig] + line[-2:]
enhancerToTopGeneTable.append(newLine)
# resort enhancerToGeneTable
if noFormatTable:
return enhancerToGeneTable, enhancerToTopGeneTable, geneToEnhancerTable
else:
enhancerOrder = utils.order([int(line[-2])
for line in enhancerToGeneTable[1:]])
sortedTable = [enhancerToGeneTable[0]]
sortedTopGeneTable = [enhancerToTopGeneTable[0]]
for i in enhancerOrder:
sortedTable.append(enhancerToGeneTable[(i + 1)])
sortedTopGeneTable.append(enhancerToTopGeneTable[(i + 1)])
return sortedTable, sortedTopGeneTable, geneToEnhancerTable
def main():
"""
main run function
"""
#usage = "usage: %prog [options] -g [GENOME] -b [SORTED BAMFILE(S)] -i [INPUTFILE] -o [OUTPUTFOLDER]"
parser = argparse.ArgumentParser(usage='%(prog)s -i SAMFILE -g REF_GENOME -s SPIKE_GENOME')
# required flags
parser.add_argument("-i", "--input", dest="inputSam", type=str,
help="Enter a sam file", required=False)
parser.add_argument("-g", "--genome", dest="genome", type=str,
help="specify the main reference genome", required=False)
parser.add_argument("-s", "--spike", dest="spike", type=str,
help="specify the spike in genome", required=False)
parser.add_argument("-d", "--dest", dest="dest", type=str,
help="specify an optional destination for the final bams to move to", required=False)
args = parser.parse_args()
print(args)
if args.inputSam and args.genome and args.spike:
print('FORMATTING %s FOR CHIP_RX USING REFERENCE GENOME %s and SPIKE_IN GENOME %s' % (args.inputSam,args.genome,args.spike))
samPath = args.inputSam
if string.upper(samPath).count('.SAM') == 0:
print('ERROR, file must end in .sam or .SAM')
sys.exit()
#get the headers
genome_string = string.upper('%s_%s' % (args.genome,args.spike))
genomeDict = {'RN6_DM6':['/grail/genomes/Rattus_norvegicus/UCSC/rn6/Sequence/Bowtie2Index_dm6/rn6_header.SAM','/grail/genomes/Rattus_norvegicus/UCSC/rn6/Sequence/Bowtie2Index_dm6/dm6_header.SAM'],
}
if genomeDict.has_key(genome_string) == False:
print('ERROR: UNSUPPORTED GENOME COMBINATION %s' % (genome_string))
sys.exit()
else:
print('IDENTIFIED HEADERS FOR GENOME COMBINATION %s' %(genome_string))
header1 = genomeDict[genome_string][0]
header2 = genomeDict[genome_string][1]
suffix = string.lower('_%s' % (args.spike))
outfile1 = string.replace(samPath,samPath[-4:],'.%s%s' % (args.genome,samPath[-4:]))
outfile2 = string.replace(samPath,samPath[-4:],'.%s%s' % (args.spike,samPath[-4:]))
split_sam(suffix,samPath,header1,header2,outfile1,outfile2)
#move stuff to destination folder
if args.dest:
bamFolder = utils.formatFolder(args.dest,False)
samFolder = utils.getParentFolder(samPath)
mv_cmd = 'mv %s*bam* %s' % (samFolder,bamFolder)
print('MOVING BAMS FROM %s TO %s' % (samFolder,bamFolder))
os.system(mv_cmd)
else:
parser.print_help()
sys.exit()
def mapEnhancerToGeneTop(rankByBamFile, controlBamFile, genome, annotFile, enhancerFile, transcribedFile='', uniqueGenes=True, searchWindow=50000, noFormatTable=False):
'''
maps genes to enhancers. if uniqueGenes, reduces to gene name only. Otherwise, gives for each refseq
'''
startDict = utils.makeStartDict(annotFile)
enhancerName = enhancerFile.split('/')[-1].split('.')[0]
enhancerTable = utils.parseTable(enhancerFile, '\t')
# internal parameter for debugging
byRefseq = False
if len(transcribedFile) > 0:
transcribedTable = utils.parseTable(transcribedFile, '\t')
transcribedGenes = [line[1] for line in transcribedTable]
else:
transcribedGenes = startDict.keys()
print('MAKING TRANSCRIPT COLLECTION')
transcribedCollection = utils.makeTranscriptCollection(
annotFile, 0, 0, 500, transcribedGenes)
print('MAKING TSS COLLECTION')
tssLoci = []
for geneID in transcribedGenes:
tssLoci.append(utils.makeTSSLocus(geneID, startDict, 0, 0))
# this turns the tssLoci list into a LocusCollection
# 50 is the internal parameter for LocusCollection and doesn't really
# matter
tssCollection = utils.LocusCollection(tssLoci, 50)
geneDict = {'overlapping': defaultdict(
list), 'proximal': defaultdict(list)}
# dictionaries to hold ranks and superstatus of gene nearby enhancers
rankDict = defaultdict(list)
superDict = defaultdict(list)
# list of all genes that appear in this analysis
overallGeneList = []
# find the damn header
for line in enhancerTable:
if line[0][0] == '#':
continue
else:
header = line
break
if noFormatTable:
# set up the output tables
# first by enhancer
enhancerToGeneTable = [
header + ['OVERLAP_GENES', 'PROXIMAL_GENES', 'CLOSEST_GENE']]
else:
# set up the output tables
# first by enhancer
enhancerToGeneTable = [
header[0:9] + ['OVERLAP_GENES', 'PROXIMAL_GENES', 'CLOSEST_GENE'] + header[-2:]]
# next by gene
geneToEnhancerTable = [
['GENE_NAME', 'REFSEQ_ID', 'PROXIMAL_ENHANCERS']]
# next make the gene to enhancer table
geneToEnhancerTable = [
['GENE_NAME', 'REFSEQ_ID', 'PROXIMAL_ENHANCERS', 'ENHANCER_RANKS', 'IS_SUPER', 'ENHANCER_SIGNAL']]
for line in enhancerTable:
if line[0][0] == '#' or line[0][0] == 'R':
continue
enhancerString = '%s:%s-%s' % (line[1], line[2], line[3])
enhancerLocus = utils.Locus(line[1], line[2], line[3], '.', line[0])
# overlapping genes are transcribed genes whose transcript is directly
# in the stitchedLocus
overlappingLoci = transcribedCollection.getOverlap(
enhancerLocus, 'both')
overlappingGenes = []
for overlapLocus in overlappingLoci:
overlappingGenes.append(overlapLocus.ID())
# proximalGenes are transcribed genes where the tss is within 50kb of
# the boundary of the stitched loci
proximalLoci = tssCollection.getOverlap(
utils.makeSearchLocus(enhancerLocus, searchWindow, searchWindow), 'both')
proximalGenes = []
for proxLocus in proximalLoci:
proximalGenes.append(proxLocus.ID())
distalLoci = tssCollection.getOverlap(
utils.makeSearchLocus(enhancerLocus, 1000000, 1000000), 'both')
distalGenes = []
for proxLocus in distalLoci:
distalGenes.append(proxLocus.ID())
overlappingGenes = utils.uniquify(overlappingGenes)
proximalGenes = utils.uniquify(proximalGenes)
distalGenes = utils.uniquify(distalGenes)
allEnhancerGenes = overlappingGenes + proximalGenes + distalGenes
# these checks make sure each gene list is unique.
# technically it is possible for a gene to be overlapping, but not proximal since the
# gene could be longer than the 50kb window, but we'll let that slide
# here
for refID in overlappingGenes:
if proximalGenes.count(refID) == 1:
proximalGenes.remove(refID)
for refID in proximalGenes:
if distalGenes.count(refID) == 1:
distalGenes.remove(refID)
# Now find the closest gene
if len(allEnhancerGenes) == 0:
closestGene = ''
else:
# get enhancerCenter
enhancerCenter = (int(line[2]) + int(line[3])) / 2
# get absolute distance to enhancer center
distList = [abs(enhancerCenter - startDict[geneID]['start'][0])
for geneID in allEnhancerGenes]
# get the ID and convert to name
closestGene = startDict[
allEnhancerGenes[distList.index(min(distList))]]['name']
# NOW WRITE THE ROW FOR THE ENHANCER TABLE
if noFormatTable:
newEnhancerLine = list(line)
newEnhancerLine.append(
join(utils.uniquify([startDict[x]['name'] for x in overlappingGenes]), ','))
newEnhancerLine.append(
join(utils.uniquify([startDict[x]['name'] for x in proximalGenes]), ','))
newEnhancerLine.append(closestGene)
else:
newEnhancerLine = line[0:9]
newEnhancerLine.append(
join(utils.uniquify([startDict[x]['name'] for x in overlappingGenes]), ','))
newEnhancerLine.append(
join(utils.uniquify([startDict[x]['name'] for x in proximalGenes]), ','))
newEnhancerLine.append(closestGene)
newEnhancerLine += line[-2:]
enhancerToGeneTable.append(newEnhancerLine)
# Now grab all overlapping and proximal genes for the gene ordered
# table
overallGeneList += overlappingGenes
for refID in overlappingGenes:
geneDict['overlapping'][refID].append(enhancerString)
rankDict[refID].append(int(line[-2]))
superDict[refID].append(int(line[-1]))
overallGeneList += proximalGenes
for refID in proximalGenes:
geneDict['proximal'][refID].append(enhancerString)
rankDict[refID].append(int(line[-2]))
superDict[refID].append(int(line[-1]))
# End loop through
# Make table by gene
print('MAKING ENHANCER ASSOCIATED GENE TSS COLLECTION')
overallGeneList = utils.uniquify(overallGeneList)
#get the chromLists from the various bams here
cmd = 'samtools idxstats %s' % (rankByBamFile)
idxStats = subprocess.Popen(cmd,stdout=subprocess.PIPE,shell=True)
idxStats= idxStats.communicate()
bamChromList = [line.split('\t')[0] for line in idxStats[0].split('\n')[0:-2]]
if len(controlBamFile) > 0:
cmd = 'samtools idxstats %s' % (controlBamFile)
idxStats = subprocess.Popen(cmd,stdout=subprocess.PIPE,shell=True)
idxStats= idxStats.communicate()
bamChromListControl = [line.split('\t')[0] for line in idxStats[0].split('\n')[0:-2]]
bamChromList = [chrom for chrom in bamChromList if bamChromListControl.count(chrom) != 0]
#now make sure no genes have a bad chrom
overallGeneList = [gene for gene in overallGeneList if bamChromList.count(startDict[gene]['chr']) != 0]
#now make an enhancer collection of all transcripts
enhancerGeneCollection = utils.makeTranscriptCollection(
annotFile, 5000, 5000, 500, overallGeneList)
enhancerGeneGFF = utils.locusCollectionToGFF(enhancerGeneCollection)
# dump the gff to file
enhancerFolder = utils.getParentFolder(enhancerFile)
gffRootName = "%s_TSS_ENHANCER_GENES_-5000_+5000" % (genome)
enhancerGeneGFFFile = "%s%s_%s.gff" % (enhancerFolder, enhancerName,gffRootName)
utils.unParseTable(enhancerGeneGFF, enhancerGeneGFFFile, '\t')
# now we need to run bamToGFF
# Try to use the bamliquidatior_path.py script on cluster, otherwise, failover to local (in path), otherwise fail.
bamliquidator_path = 'bamliquidator_batch'
print('MAPPING SIGNAL AT ENHANCER ASSOCIATED GENE TSS')
# map density at genes in the +/- 5kb tss region
# first on the rankBy bam
bamName = rankByBamFile.split('/')[-1]
mappedRankByFolder = "%s%s_%s_%s/" % (enhancerFolder, enhancerName,gffRootName, bamName)
mappedRankByFile = "%s%s_%s_%s/matrix.txt" % (enhancerFolder,enhancerName, gffRootName, bamName)
cmd = bamliquidator_path + ' --sense . -e 200 --match_bamToGFF -r %s -o %s %s' % (enhancerGeneGFFFile, mappedRankByFolder,rankByBamFile)
print("Mapping rankby bam %s" % (rankByBamFile))
print(cmd)
os.system(cmd)
#check for completion
if utils.checkOutput(mappedRankByFile,0.2,5):
print("SUCCESSFULLY MAPPED TO %s FROM BAM: %s" % (enhancerGeneGFFFile, rankByBamFile))
else:
print("ERROR: FAILED TO MAP %s FROM BAM: %s" % (enhancerGeneGFFFile, rankByBamFile))
sys.exit()
# next on the control bam if it exists
if len(controlBamFile) > 0:
controlName = controlBamFile.split('/')[-1]
mappedControlFolder = "%s%s_%s_%s/" % (
enhancerFolder, enhancerName,gffRootName, controlName)
mappedControlFile = "%s%s_%s_%s/matrix.txt" % (
enhancerFolder, enhancerName,gffRootName, controlName)
cmd = bamliquidator_path + ' --sense . -e 200 --match_bamToGFF -r %s -o %s %s' % (enhancerGeneGFFFile, mappedControlFolder,controlBamFile)
print("Mapping control bam %s" % (controlBamFile))
print(cmd)
os.system(cmd)
#check for completion
if utils.checkOutput(mappedControlFile,0.2,5):
print("SUCCESSFULLY MAPPED TO %s FROM BAM: %s" % (enhancerGeneGFFFile, controlBamFile))
else:
print("ERROR: FAILED TO MAP %s FROM BAM: %s" % (enhancerGeneGFFFile, controlBamFile))
sys.exit()
# now get the appropriate output files
if len(controlBamFile) > 0:
print("CHECKING FOR MAPPED OUTPUT AT %s AND %s" %
(mappedRankByFile, mappedControlFile))
if utils.checkOutput(mappedRankByFile, 1, 1) and utils.checkOutput(mappedControlFile, 1, 1):
print('MAKING ENHANCER ASSOCIATED GENE TSS SIGNAL DICTIONARIES')
signalDict = makeSignalDict(mappedRankByFile, mappedControlFile)
else:
print("NO MAPPING OUTPUT DETECTED")
sys.exit()
else:
print("CHECKING FOR MAPPED OUTPUT AT %s" % (mappedRankByFile))
if utils.checkOutput(mappedRankByFile, 1, 30):
print('MAKING ENHANCER ASSOCIATED GENE TSS SIGNAL DICTIONARIES')
signalDict = makeSignalDict(mappedRankByFile)
else:
print("NO MAPPING OUTPUT DETECTED")
sys.exit()
# use enhancer rank to order
rankOrder = utils.order([min(rankDict[x]) for x in overallGeneList])
usedNames = []
# make a new dict to hold TSS signal by max per geneName
geneNameSigDict = defaultdict(list)
print('MAKING GENE TABLE')
for i in rankOrder:
refID = overallGeneList[i]
geneName = startDict[refID]['name']
if usedNames.count(geneName) > 0 and uniqueGenes == True:
continue
else:
usedNames.append(geneName)
proxEnhancers = geneDict['overlapping'][
refID] + geneDict['proximal'][refID]
superStatus = max(superDict[refID])
enhancerRanks = join([str(x) for x in rankDict[refID]], ',')
enhancerSignal = signalDict[refID]
geneNameSigDict[geneName].append(enhancerSignal)
newLine = [geneName, refID, join(
proxEnhancers, ','), enhancerRanks, superStatus, enhancerSignal]
geneToEnhancerTable.append(newLine)
#utils.unParseTable(geneToEnhancerTable,'/grail/projects/newRose/geneMapper/foo.txt','\t')
print('MAKING ENHANCER TO TOP GENE TABLE')
if noFormatTable:
enhancerToTopGeneTable = [
enhancerToGeneTable[0] + ['TOP_GENE', 'TSS_SIGNAL']]
else:
enhancerToTopGeneTable = [enhancerToGeneTable[0][0:12] + [
'TOP_GENE', 'TSS_SIGNAL'] + enhancerToGeneTable[0][-2:]]
for line in enhancerToGeneTable[1:]:
geneList = []
if noFormatTable:
geneList += line[-3].split(',')
geneList += line[-2].split(',')
else:
geneList += line[10].split(',')
geneList += line[11].split(',')
geneList = utils.uniquify([x for x in geneList if len(x) > 0])
if len(geneList) > 0:
try:
sigVector = [max(geneNameSigDict[x]) for x in geneList]
maxIndex = sigVector.index(max(sigVector))
maxGene = geneList[maxIndex]
maxSig = sigVector[maxIndex]
if maxSig == 0.0:
maxGene = 'NONE'
maxSig = 'NONE'
except ValueError:
if len(geneList) == 1:
maxGene = geneList[0]
maxSig = 'NONE'
else:
maxGene = 'NONE'
maxSig = 'NONE'
else:
maxGene = 'NONE'
maxSig = 'NONE'
if noFormatTable:
newLine = line + [maxGene, maxSig]
else:
newLine = line[0:12] + [maxGene, maxSig] + line[-2:]
enhancerToTopGeneTable.append(newLine)
# resort enhancerToGeneTable
if noFormatTable:
return enhancerToGeneTable, enhancerToTopGeneTable, geneToEnhancerTable
else:
enhancerOrder = utils.order([int(line[-2])
for line in enhancerToGeneTable[1:]])
sortedTable = [enhancerToGeneTable[0]]
sortedTopGeneTable = [enhancerToTopGeneTable[0]]
for i in enhancerOrder:
sortedTable.append(enhancerToGeneTable[(i + 1)])
sortedTopGeneTable.append(enhancerToTopGeneTable[(i + 1)])
return sortedTable, sortedTopGeneTable, geneToEnhancerTable
def extractGuideFastq(fastqFile, outputFolder='', gzip=False):
'''
takes a fastq and extracts candidate guide RNAs
'''
#get the full absolute path for the fastq File
fastqFile = os.path.abspath(fastqFile)
fastq = utils.open(fastqFile, 'r')
#get the fastq name and root
if len(outputFolder) == 0:
outputFolder = utils.getParentFolder(fastqFile)
#makes sure the output folder exists
utils.formatFolder(outputFolder, True)
#grab the name info from the fastq
fastqName = fastqFile.split('/')[-1]
fastqRoot = string.replace(fastqName, '.fastq', '')
fastqRoot = string.replace(fastqRoot, '.gz', '')
#guideFastqFile output
guideFastqFile = '%s%s.gecko.fastq' % (outputFolder, fastqRoot)
guideFastq = utils.open(guideFastqFile, 'w')
print('processing %s' % (fastqName))
print('million reads processed:')
ticker = 0
found = 0
while True:
if ticker % 1000000 == 0:
print(ticker / 1000000)
fastqLines = []
#now load the fastq lines
try:
for i in range(4):
fastqLines.append(fastq.next())
except StopIteration:
break
#see if you can find a cut site
seq = fastqLines[1].rstrip()
try:
cutPosition = seq.index(cutSeq)
found += 1
except ValueError:
ticker += 1
continue
guideStart = cutPosition + cutOffset
guideStop = guideStart + guideLength
#pulling out the guide seq in the fastqLines
fastqLines[1] = fastqLines[1][guideStart:guideStop] + '\n'
fastqLines[3] = fastqLines[3][guideStart:guideStop] + '\n'
for line in fastqLines:
guideFastq.write(line)
ticker += 1
# if ticker == 100000:
# print(ticker)
# print(found)
# print(float(found)/float(ticker))
# break
print('SUMMARY STATISTICS')
print(ticker)
print(found)
print(float(found) / float(ticker))
#close the fastq
guideFastq.close()
#gzip the fastq
if gzip:
os.system('gzip %s &' % (guideFastqFile))
guideFastqFile += '.gz'
return guideFastqFile