def runApp(mask="",m="",vcf="",v="",out="",o=""):
print "loading features",
params = featureLoadingParameters(build=genomeUtils.hg19,
passFunction=None,
rejectFunction=None,
callbackArgs={},
tickFunction=tick,
tickInterval=10,
mask=None,
attributesToInclude={},
returnFileObject=True)
features = featureFile.parseBedFile(mask, params)
print ""
params = variantLoadingParameters(build=genomeUtils.hg19,
passFunction=None,
rejectFunction=None,
callbackArgs={},
tickFunction=tick,
tickInterval=10,
individualsToInclude=None,
individualAppendString="",
lociToInclude=None,
mask=features.regions,
invertMask=True,
attributesToInclude=None,
attributeAppendString="",
skipGenotypeAttributes=True, # TODO: there's actually a bug here (you should turn this back off
returnFileObject=True,
alleleMatching=allele.STRICT,
attemptRepairsWhenComparing=True)
print "parsing variants",
newFile = variantFile.parseVcfFile(vcf, params)
print ""
# TODO: throw this bit out
print "swapping attributes"
for v in newFile.variants:
newName = v.attributes.get('RSID',v.name)
if isinstance(newName,list):
newName = newName[1]
#if newName.startswith('dbsnp'):
# newName = newName.split(':')[1]
if newName == '.':
newName = v.basicName
v.name = newName
print "writing file..."
newFile.writeVcfFile(out, sortMethod="NUMXYM", includeScriptLine=True)
print ""
print "done"
def notifyRun(vcfPath, vcfAttributes, xAttribute, yAttribute, softFilters, forcedCategoricals, featurePaths):
global canceled, splash, window
splash = QProgressDialog("Loading %s" % os.path.split(vcfPath)[1], "Cancel", 0, 1000, parent=None)
splash.setWindowModality(Qt.WindowModal)
splash.setAutoReset(False)
splash.setAutoClose(False)
splash.show()
canceled = False
vData = variantData(vcfPath, vcfAttributes, forcedCategoricals)
vParams = variantLoadingParameters(passFunction=vData.addVariant,
rejectFunction=None,
callbackArgs={},
tickFunction=tick,
tickInterval=0.1,
individualsToInclude=[],
individualAppendString="",
lociToInclude=None,
mask=None,
invertMask=False,
attributesToInclude=None,
attributeAppendString="",
skipGenotypeAttributes=True,
returnFileObject=False,
alleleMatching=allele.STRICT,
attemptRepairsWhenComparing=True)
try:
variantFile.parseVcfFile(vcfPath, vParams)
except cancelButtonException:
splash.close()
window.window.show()
return
if softFilters == None:
softFilters = {}
for k in vData.axisLookups.iterkeys():
if k == xAttribute or k == yAttribute:
if vData.axisLookups[k].hasNumeric:
fivePercent = 0.05*(vData.axisLookups[k].maximum-vData.axisLookups[k].minimum)
ranges = [(vData.axisLookups[k].maximum-fivePercent,vData.axisLookups[k].maximum)]
else:
ranges = None
values = []
else:
ranges = None
values = None
softFilters[k] = valueFilter(values=values,
ranges=ranges,
includeNone=True,
includeBlank=True,
includeInf=True,
includeNaN=True,
includeMissing=True,
includeAlleleMasked=True,
listMode=valueFilter.LIST_INCLUSIVE)
intMan = interactionManager(vData,softFilters)
# TODO
fData = featureData(featurePaths)
if canceled:
splash.close()
window.window.show()
return
splash.close()
appWindow = appWidget(vData,fData,intMan,xAttribute,yAttribute)
intMan.setApp(appWindow)
def loadDataObjects(self, callback=None):
# Try to parse files in order by format (some files are more informative than others,
# and we want to start off with the best information) ... this may get shaken up
# when we support masking/specific loci
gff3Files = []
bedFiles = []
vcfFiles = []
csvFiles = []
axisLabels = set()
forcedCategoricals = set()
individualsToInclude = self.getAllSamples()
for fileID,f in self.files.iteritems():
if f.format == '.vcf':
vcfFiles.append(fileID)
axisLabels.update(f.hardFilters.iterkeys())
forcedCategoricals.update(f.forcedCategoricals)
elif f.format == '.csv':
csvFiles.append(fileID)
axisLabels.update(f.hardFilters.iterkeys())
forcedCategoricals.update(f.forcedCategoricals)
elif f.format == '.gff3':
gff3Files.append(fileID)
elif f.format == '.bed':
bedFiles.append(fileID)
vData = tempVariantData(axisLabels,set(self.statistics.iterkeys()),forcedCategoricals,self.startingXaxis,self.startingYaxis)
for fileID in gff3Files:
pass
for fileID in bedFiles:
pass
for fileID in vcfFiles:
if callback != None:
callback(numTicks=0,message='Loading %s' % fileID)
parameters = variantLoadingParameters(build=self.files[fileID].build,
passFunction=vData.addVariant,
rejectFunction=None,
callbackArgs={},
tickFunction=callback,
tickInterval=self.loadingPercentages[fileID],
individualsToInclude=individualsToInclude,
individualAppendString=" (%s)" % fileID,
lociToInclude=None, # TODO: support masking and specfic loci
mask=None,
attributesToInclude=self.files[fileID].hardFilters,
attributeAppendString=" (%s)" % fileID,
skipGenotypeAttributes=True)
if variantFile.parseVcfFile(self.files[fileID].path, parameters) == "ABORTED":
return (None,None)
for fileID in csvFiles:
if callback != None:
callback(numTicks=0,message='Loading %s' % fileID)
parameters = variantLoadingParameters(build=self.files[fileID].build,
passFunction=vData.addVariant,
rejectFunction=None,
callbackArgs={},
tickFunction=callback,
tickInterval=self.loadingPercentages[fileID],
individualsToInclude=[], # .csv files don't have genotypes
individualAppendString="",
lociToInclude=None, # TODO: support masking and specfic loci
mask=None,
attributesToInclude=self.files[fileID].hardFilters,
attributeAppendString=" (%s)" % fileID,
skipGenotypeAttributes=True)
if variantFile.parseCsvFile(self.files[fileID].path, parameters) == "ABORTED":
return (None,None)
# Now that we've loaded the files, do our group calculations
callback(numTicks=0,message='Calculating group statistics')
vData.performGroupCalculations(self.groups, self.statistics, callback, self.loadingPercentages[None])
return vData
def runApp(loci="", l="", vcf="", v="", individuals="", i="", out="", o="", remove="", r=""):
if individuals != None:
print "Parsing individual list..."
individualList = []
infile = open(individuals, "r")
for line in infile:
individualList.append(line.strip())
infile.close()
else:
individualList = None
if loci != None:
print "Parsing loci list..."
firstLine = True
infile = open(loci, "r")
for line in infile:
if firstLine:
firstLine = False
continue
columns = line.split()
lociToKeep.add(
variant(
chromosome=columns[0],
position=columns[1],
matchMode=allele.FLEXIBLE,
attemptRepairsWhenComparing=True,
ref=".*",
alt=".*",
name=columns[2],
build=genomeUtils.hg19,
attributeFilters=None,
)
)
infile.close()
print "Parsing .vcf file..."
# we only care about genotypes; we throw out all other details.
parseParameters = variantLoadingParameters(
passFunction=add,
tickFunction=tick,
tickInterval=5,
individualsToInclude=individualList,
lociToInclude=lociToKeep,
attributesToInclude={},
skipGenotypeAttributes=True,
)
variantFile.parseVcfFile(vcf, parseParameters)
print ""
print "Writing results..."
outfile = open(out, "w")
outfile.write("Chromosome\tPosition\tRs#")
for i in individualList:
outfile.write("\t%s" % i)
outfile.write("\n")
if remove != None:
removeFile = open(remove, "w")
removeFile.write("Chromosome\tPosition\tRs#\tReason\n")
for v in sorted(lociToKeep, key=lambda x: x.position):
if remove != None and len(v.genotypes) == 0:
removeFile.write("%s\t%i\t%s\tNo Genotypes\n" % (v.chromosome, v.position, v.name))
else:
outfile.write("%s\t%i\t%s" % (v.chromosome, v.position, v.name))
for i in individualList:
outfile.write("\t%s" % str(v.genotypes.get(i, "./.")))
outfile.write("\n")
outfile.close()
if remove != None:
removeFile.close()
print "Done."
def runApp(mask="",m="",vcf="",v="",out="",o="",csv="",c=""):
print "loading features",
params = featureLoadingParameters(build=genomeUtils.hg19,
passFunction=None,
rejectFunction=None,
callbackArgs={},
tickFunction=tick,
tickInterval=10,
mask=None,
attributesToInclude={},
returnFileObject=True)
features = featureFile.parseBedFile(mask, params)
print ""
variants = {}
fileAttributes = variantFile.extractVcfFileInfo(vcf)
def addVariant(v):
variants[v.genomePosition] = v
params = variantLoadingParameters(build=genomeUtils.hg19,
passFunction=addVariant,
rejectFunction=None,
callbackArgs={},
tickFunction=tick,
tickInterval=10,
individualsToInclude=None,
individualAppendString="",
lociToInclude=None,
mask=None, #features.regions,
invertMask=False, #True
attributesToInclude=None,
attributeAppendString="",
skipGenotypeAttributes=True, # TODO: there's actually a bug here (you should turn this back off
returnFileObject=False,
alleleMatching=allele.UNENFORCED,
attemptRepairsWhenComparing=True)
print "parsing vcf file",
variantFile.parseVcfFile(vcf, params)
print ""
# TODO: throw this bit out
print "swapping attributes"
for v in variants.itervalues():
newName = v.attributes.get('RSID',v.name)
if v.attributes.has_key('RSID'):
newName = v.attributes['RSID']
del v.attributes['RSID']
else:
newName = v.name
if isinstance(newName,list):
newName = newName[1]
#if newName.startswith('dbsnp'):
# newName = newName.split(':')[1]
if newName == '.':
newName = v.basicName
v.name = newName
print "calculating frequencies",
tickInterval = len(variants) / 10
i = 0
nextTick = tickInterval
groupDict = { "CASES3":set(["T2DG0300147", "T2DG0300160", "T2DG0300135", "T2DG0300133", "T2DG0300143"]),
"CASES6":set(["T2DG0600449", "T2DG0600426", "T2DG0600428", "T2DG0600470", "T2DG0600442", "T2DG0600431"]),
"CASES20":set(["T2DG2000900", "T2DG2000901", "T2DG2000904", "T2DG2000928"]),
"CASES21":set(["T2DG2100946", "T2DG2100955", "T2DG2100967", "T2DG2100966"]),
"CONTROLS_IND_EXTREME":set(["T2DG0200013", "T2DG0200027", "T2DG0500309", "T2DG0701163", "T2DG0701156", "T2DG0800488", "T2DG0901234", "T2DG1000568", "T2DG1000570", "T2DG1101324", "T2DG1600768", "T2DG2701070", "T2DG4701118", "T2DG0200068", "T2DG0200071", "T2DG0400250", "T2DG0500349", "T2DG0500339", "T2DG0701179", "T2DG0800504", "T2DG0800564", "T2DG0901289", "T2DG0901275", "T2DG1000595", "T2DG1101348", "T2DG1600785", "T2DG1700875", "T2DG2701094", "T2DG4701124"]),
"CONTROL_Normal_nonind":set(["T2DG0200098", "T2DG0200076", "T2DG0200104", "T2DG0200065", "T2DG0400287", "T2DG0400260", "T2DG0400280", "T2DG0400288", "T2DG0400267", "T2DG0400269", "T2DG0400279", "T2DG0400256", "T2DG0400273", "T2DG0500370", "T2DG0500367", "T2DG0500353", "T2DG0500383", "T2DG0500362", "T2DG0500364", "T2DG0500379", "T2DG0500351", "T2DG0500381", "T2DG0500385", "T2DG0500357", "T2DG0701225", "T2DG0701227", "T2DG0701194", "T2DG0701196", "T2DG0701195", "T2DG0701211", "T2DG0701222", "T2DG0701220", "T2DG0701204", "T2DG0701208", "T2DG0701192", "T2DG0701191", "T2DG0701198", "T2DG0701181", "T2DG0701174", "T2DG0800561", "T2DG0800542", "T2DG0800563", "T2DG0800547", "T2DG0800559", "T2DG0901306", "T2DG0901296", "T2DG0901285", "T2DG0901284", "T2DG0901269", "T2DG0901295", "T2DG0901299", "T2DG0901279", "T2DG0901307", "T2DG1000637", "T2DG1000629", "T2DG1000630", "T2DG1000614", "T2DG1000612", "T2DG1000613", "T2DG1000631", "T2DG1000591", "T2DG1000620", "T2DG1000640", "T2DG1000606", "T2DG1000636", "T2DG1000638", "T2DG1000627", "T2DG1101369", "T2DG1101381", "T2DG1101383", "T2DG1101377", "T2DG1101354", "T2DG1101356", "T2DG1600793", "T2DG1600811", "T2DG1600816", "T2DG1600810", "T2DG1700872", "T2DG1700869", "T2DG1700876", "T2DG1700867", "T2DG2701096", "T2DG2701093", "T2DG4701139", "T2DG4701129"]),
"CONTROLS_PreHypertension_ind":set(["T2DG0200073", "T2DG0200031", "T2DG0200040", "T2DG0200032", "T2DG0200042", "T2DG0200047", "T2DG0200070", "T2DG0200078", "T2DG0200096", "T2DG0200063", "T2DG0200077", "T2DG0200057", "T2DG0200086", "T2DG0200041", "T2DG0400234", "T2DG0400243", "T2DG0400257", "T2DG0400261", "T2DG0400264", "T2DG0400241", "T2DG0400237", "T2DG0400238", "T2DG0400258", "T2DG0400295", "T2DG0400254", "T2DG0400262", "T2DG0500334", "T2DG0500346", "T2DG0500358", "T2DG0500371", "T2DG0500389", "T2DG0500332", "T2DG0500352", "T2DG0500375", "T2DG0500347", "T2DG0500388", "T2DG0500373", "T2DG0701188", "T2DG0701219", "T2DG0701203", "T2DG0701199", "T2DG0701216", "T2DG0701217", "T2DG0701214", "T2DG0800541", "T2DG0800520", "T2DG0800552", "T2DG0800529", "T2DG0800514", "T2DG0800502", "T2DG0800505", "T2DG0800509", "T2DG0901305", "T2DG0901287", "T2DG0901267", "T2DG0901271", "T2DG0901270", "T2DG0901308", "T2DG0901288", "T2DG0901298", "T2DG0901278", "T2DG0901272", "T2DG0901263", "T2DG1000599", "T2DG1000618", "T2DG1000597", "T2DG1000611", "T2DG1000616", "T2DG1000592", "T2DG1000598", "T2DG1000604", "T2DG1000642", "T2DG1000639", "T2DG1000607", "T2DG1101365", "T2DG1101366", "T2DG1101382", "T2DG1101388", "T2DG1101389", "T2DG1101372", "T2DG1101384", "T2DG1101385", "T2DG1101338", "T2DG1101341", "T2DG1101343", "T2DG1101387", "T2DG1101390", "T2DG1101344", "T2DG1101342", "T2DG1600812", "T2DG1600819", "T2DG1600805", "T2DG1600804", "T2DG1600807", "T2DG1600799", "T2DG1700861", "T2DG1700846", "T2DG1700854", "T2DG1700853", "T2DG1700868", "T2DG1700870", "T2DG2701110", "T2DG2701085", "T2DG2701088", "T2DG2701111", "T2DG2701107", "T2DG2701091", "T2DG4701130", "T2DG4701122", "T2DG4701133", "T2DG4701127", "T2DG4701128", "T2DG0200006", "T2DG0200008", "T2DG0200012", "T2DG0200009", "T2DG0200018", "T2DG0200023", "T2DG0200007", "T2DG0400219", "T2DG0500318", "T2DG0500327", "T2DG0500310", "T2DG0500312", "T2DG0500313", "T2DG0701164", "T2DG0701143", "T2DG0800490", "T2DG0800498", "T2DG0901251", "T2DG1000567", "T2DG1000582", "T2DG1000586", "T2DG1000565", "T2DG1000566", "T2DG1000569", "T2DG1101320", "T2DG1101330", "T2DG1600767", "T2DG1600773", "T2DG1600778", "T2DG1600771", "T2DG1700824", "T2DG1700836", "T2DG2701073", "T2DG2701079"]),
"CONTROLS_ALL":set(["T2DG0200013", "T2DG0200027", "T2DG0500309", "T2DG0701163", "T2DG0701156", "T2DG0800488", "T2DG0901234", "T2DG1000568", "T2DG1000570", "T2DG1101324", "T2DG1600768", "T2DG2701070", "T2DG4701118", "T2DG0200068", "T2DG0200071", "T2DG0400250", "T2DG0500349", "T2DG0500339", "T2DG0701179", "T2DG0800504", "T2DG0800564", "T2DG0901289", "T2DG0901275", "T2DG1000595", "T2DG1101348", "T2DG1600785", "T2DG1700875", "T2DG2701094", "T2DG4701124", "T2DG0200098", "T2DG0200076", "T2DG0200104", "T2DG0200065", "T2DG0400287", "T2DG0400260", "T2DG0400280", "T2DG0400288", "T2DG0400267", "T2DG0400269", "T2DG0400279", "T2DG0400256", "T2DG0400273", "T2DG0500370", "T2DG0500367", "T2DG0500353", "T2DG0500383", "T2DG0500362", "T2DG0500364", "T2DG0500379", "T2DG0500351", "T2DG0500381", "T2DG0500385", "T2DG0500357", "T2DG0701225", "T2DG0701227", "T2DG0701194", "T2DG0701196", "T2DG0701195", "T2DG0701211", "T2DG0701222", "T2DG0701220", "T2DG0701204", "T2DG0701208", "T2DG0701192", "T2DG0701191", "T2DG0701198", "T2DG0701181", "T2DG0701174", "T2DG0800561", "T2DG0800542", "T2DG0800563", "T2DG0800547", "T2DG0800559", "T2DG0901306", "T2DG0901296", "T2DG0901285", "T2DG0901284", "T2DG0901269", "T2DG0901295", "T2DG0901299", "T2DG0901279", "T2DG0901307", "T2DG1000637", "T2DG1000629", "T2DG1000630", "T2DG1000614", "T2DG1000612", "T2DG1000613", "T2DG1000631", "T2DG1000591", "T2DG1000620", "T2DG1000640", "T2DG1000606", "T2DG1000636", "T2DG1000638", "T2DG1000627", "T2DG1101369", "T2DG1101381", "T2DG1101383", "T2DG1101377", "T2DG1101354", "T2DG1101356", "T2DG1600793", "T2DG1600811", "T2DG1600816", "T2DG1600810", "T2DG1700872", "T2DG1700869", "T2DG1700876", "T2DG1700867", "T2DG2701096", "T2DG2701093", "T2DG4701139", "T2DG4701129", "T2DG0200073", "T2DG0200031", "T2DG0200040", "T2DG0200032", "T2DG0200042", "T2DG0200047", "T2DG0200070", "T2DG0200078", "T2DG0200096", "T2DG0200063", "T2DG0200077", "T2DG0200057", "T2DG0200086", "T2DG0200041", "T2DG0400234", "T2DG0400243", "T2DG0400257", "T2DG0400261", "T2DG0400264", "T2DG0400241", "T2DG0400237", "T2DG0400238", "T2DG0400258", "T2DG0400295", "T2DG0400254", "T2DG0400262", "T2DG0500334", "T2DG0500346", "T2DG0500358", "T2DG0500371", "T2DG0500389", "T2DG0500332", "T2DG0500352", "T2DG0500375", "T2DG0500347", "T2DG0500388", "T2DG0500373", "T2DG0701188", "T2DG0701219", "T2DG0701203", "T2DG0701199", "T2DG0701216", "T2DG0701217", "T2DG0701214", "T2DG0800541", "T2DG0800520", "T2DG0800552", "T2DG0800529", "T2DG0800514", "T2DG0800502", "T2DG0800505", "T2DG0800509", "T2DG0901305", "T2DG0901287", "T2DG0901267", "T2DG0901271", "T2DG0901270", "T2DG0901308", "T2DG0901288", "T2DG0901298", "T2DG0901278", "T2DG0901272", "T2DG0901263", "T2DG1000599", "T2DG1000618", "T2DG1000597", "T2DG1000611", "T2DG1000616", "T2DG1000592", "T2DG1000598", "T2DG1000604", "T2DG1000642", "T2DG1000639", "T2DG1000607", "T2DG1101365", "T2DG1101366", "T2DG1101382", "T2DG1101388", "T2DG1101389", "T2DG1101372", "T2DG1101384", "T2DG1101385", "T2DG1101338", "T2DG1101341", "T2DG1101343", "T2DG1101387", "T2DG1101390", "T2DG1101344", "T2DG1101342", "T2DG1600812", "T2DG1600819", "T2DG1600805", "T2DG1600804", "T2DG1600807", "T2DG1600799", "T2DG1700861", "T2DG1700846", "T2DG1700854", "T2DG1700853", "T2DG1700868", "T2DG1700870", "T2DG2701110", "T2DG2701085", "T2DG2701088", "T2DG2701111", "T2DG2701107", "T2DG2701091", "T2DG4701130", "T2DG4701122", "T2DG4701133", "T2DG4701127", "T2DG4701128", "T2DG0200006", "T2DG0200008", "T2DG0200012", "T2DG0200009", "T2DG0200018", "T2DG0200023", "T2DG0200007", "T2DG0400219", "T2DG0500318", "T2DG0500327", "T2DG0500310", "T2DG0500312", "T2DG0500313", "T2DG0701164", "T2DG0701143", "T2DG0800490", "T2DG0800498", "T2DG0901251", "T2DG1000567", "T2DG1000582", "T2DG1000586", "T2DG1000565", "T2DG1000566", "T2DG1000569", "T2DG1101320", "T2DG1101330", "T2DG1600767", "T2DG1600773", "T2DG1600778", "T2DG1600771", "T2DG1700824", "T2DG1700836", "T2DG2701073", "T2DG2701079"])}
for v in variants.itervalues():
performGroupCalculations(v,groupDict,"CONTROLS_IND_EXTREME",mode=-1)
i += 1
if i > nextTick:
nextTick += tickInterval
print ".",
print ""
del fileAttributes['INDIVIDUALS']
del fileAttributes['INFO']['RSID']
for k in groupDict.iterkeys():
fileAttributes['INFO'][k] = {"ID":k,"Number":1,"Type":"Float","Description":"%s Allele frequency"%k}
print "loading .csv file",
acceptAllFilter = valueFilter()
csvDict = {"SIFT_score":acceptAllFilter,
"LRT_score":acceptAllFilter,
"MutationTaster_pred":acceptAllFilter,
"phyloP":acceptAllFilter,
"SLR_test_statistic":acceptAllFilter,
"LRT_pred":acceptAllFilter,
"MutationTaster_score":acceptAllFilter,
"MutationTaster_pred":acceptAllFilter,
"GERP++_NR":acceptAllFilter,
"GERP++_RS":acceptAllFilter,
"phyloP":acceptAllFilter,
"29way_logOdds":acceptAllFilter,
"LRT_Omega":acceptAllFilter,
"1000Gp1_AF":acceptAllFilter}
for k in csvDict.iterkeys():
fileAttributes['INFO'][k] = {"ID":k,"Number":1,"Type":"Float","Description":k}
def tryRepair(v):
if variants.has_key(v.genomePosition):
for key,value in v.attributes.iteritems():
variants[v.genomePosition].setAttribute(key,value)
params = variantLoadingParameters(build=genomeUtils.hg19,
passFunction=tryRepair,
rejectFunction=None,
callbackArgs={},
tickFunction=tick,
tickInterval=10,
individualsToInclude=None,
individualAppendString="",
lociToInclude=None,
mask=None, #features.regions,
invertMask=False, #True,
attributesToInclude=csvDict,
attributeAppendString="",
skipGenotypeAttributes=True,
returnFileObject=False,
alleleMatching=allele.UNENFORCED,
attemptRepairsWhenComparing=True)
variantFile.parseCsvFile(csv,params)
print ""
print "writing file..."
temp = variantFile(fileAttributes)
temp.variants = variants.values()
temp.writeVcfFile(out, sortMethod="NUMXYM", includeScriptLine=True)
print ""
print "done"
def runApp(loci="",l="",vcf="",v="",individuals="",i="",out="",o="",remove="",r=""):
lociToKeep = set()
def tick():
print ".",
def add(v):
if lociToKeep != None:
lociToKeep.add(v)
if individuals != None:
print "Parsing individual list..."
individualList = []
infile = open(individuals,'r')
for line in infile:
individualList.append(line.strip())
infile.close()
else:
individualList = variantFile.extractVcfFileInfo(vcf)["INDIVIDUALS"]
individualList.sort()
if loci != None:
print "Parsing loci list..."
firstLine = True
infile = open(loci,'r')
for line in infile:
if firstLine:
firstLine = False
continue
columns = line.split()
lociToKeep.add(variant(chromosome=columns[0], position=columns[1], matchMode=allele.UNENFORCED, attemptRepairsWhenComparing=True, ref=".*", alt=".*", name=columns[2], build=genomeUtils.hg19, attributeFilters=None))
infile.close()
else:
lociToKeep = None
if not isinstance(vcf,list):
vcf = [vcf]
for infile in vcf:
print "Parsing %s" % infile
# we only care about genotypes; we throw out all other details.
parseParameters = variantLoadingParameters( passFunction=add,
tickFunction=tick,
tickInterval=5,
individualsToInclude=individualList,
alleleMatching = allele.UNENFORCED,
lociToInclude=lociToKeep,
attributesToInclude={},
skipGenotypeAttributes=True)
if lociToKeep == None:
parseParameters.returnFileObject = True
resultFile = variantFile.parseVcfFile(infile,parseParameters)
print ""
print "Writing results..."
outfile = open(out,'w')
outfile.write("Chromosome\tPosition\tRs#\tMajor\tMinor")
for i in individualList:
outfile.write("\t%s" % i)
outfile.write("\n")
if remove != None:
removeFile = open(remove,'w')
removeFile.write("Chromosome\tPosition\tRs#\tReason\n")
if lociToKeep != None:
lociToKeep = sorted(lociToKeep, key=lambda v: v.name)
else:
lociToKeep = sorted(resultFile.variants, key=lambda v: v.name)
for v in lociToKeep:
if len(v.genotypes) == 0:
if remove != None:
removeFile.write("%s\t%i\t%s\tNo Genotypes\n" % (v.chromosome,v.position,v.name))
elif len(v.alleles) < 2:
if remove != None:
removeFile.write("%s\t%i\t%s\tNot enough alleles" % (v.chromosome,v.position,v.name))
else:
outfile.write("%s\t%i\t%s\t%s\t%s" % (v.chromosome,v.position,v.name,v.alleles[0],v.alleles[1]))
for i in individualList:
a1 = "_"
a2 = "_"
if v.genotypes.has_key(i):
g = v.genotypes[i]
if g.allele1 != None:
a1 = str(g.allele1)
if g.allele2 != None:
a2 = str(g.allele2)
outfile.write("\t%s%s" % (a1,a2))
outfile.write("\n")
outfile.close()
if remove != None:
removeFile.close()
print "Done."
