def __init__(self, filename, pat_name) :
self.pat_name = pat_name
self.fin = open(filename)
self.allow_absent = False
self.group_repeats = False
self.iterator = splitIterator( self.fin, \
skipLine = skipper )
def iterate(self) :
prev_rsid = -1
#[rsid, {allele:(count,freq),allele2:(count,freq)]
rsid_info = []
for splt in globes.splitIterator( self.freq_file ) :
#print splt
rsid,alleleid,count,freq = int(splt[0]), int(splt[1]), \
int(float(splt[2])), float(splt[3])
if len(self.dallele[alleleid]) > 1 \
or alleleid == 5 \
or alleleid == 8 :
continue
if rsid != prev_rsid :
if prev_rsid > 0 :
freq = 0
for k in rsid_info[1] :
freq += rsid_info[1][k][1]
if freq < .999 :
print "the way we skip indels isnt getting it right"
assert False
yield rsid_info
prev_rsid = rsid_info[0]
rsid_info = []
rsid_info.append(rsid)
rsid_info.append( self.dallele[alleleid] )
rsid_info.append( count )
#rsid_info.append( {self.dallele[alleleid] : (count,freq)} )
prev_rsid = rsid
else :
rsid_info.append( self.dallele[alleleid] )
rsid_info.append( count )
def iterate(self, fast_forward = 0) :
count = 0
for row in globes.splitIterator( self.fin, burn=0 ) :
if count < fast_forward :
count += 1
continue
else : yield row
def iterate(self) :
prev_rsid = -1
#[rsid, allele, count, allele2, count]
rsid_info = []
for splt in globes.splitIterator( self.freq_file ) :
#print splt
try :
rsid,alleleid,count = int(splt[0]), int(splt[1]), \
int(float(splt[2]))
except ValueError :
print splt
assert "Value" == "Error"
if alleleid > 13 or alleleid == 5 or alleleid == 8 :
# where the indels start
# + (used for generic indels?)
# - (used for generic indels?)
continue
if rsid != prev_rsid :
if prev_rsid > 0 :
yield rsid_info
prev_rsid = rsid_info[0]
rsid_info = []
rsid_info.append(rsid)
rsid_info.append( self.dallele[alleleid] )
rsid_info.append( count )
#rsid_info.append( {self.dallele[alleleid] : (count,freq)} )
prev_rsid = rsid
else :
rsid_info.append( self.dallele[alleleid] )
rsid_info.append( count )
def sortFile( filename ) :
fin = open(filename)
fout = open("%s.sorted" % filename,'w')
sorted_splts = sorted( splitIterator( fin ), key = sortHelper )
fout.write( "\n".join( ['\t'.join(splt) for splt in sorted_splts] ) )
fin.close()
fout.close()
def iterate(self, fast_forward = 0) :
count = 0
for row in globes.splitIterator( self.file, \
burn=1, \
stopper=self.stopper ) :
if count < fast_forward :
count += 1
continue
else : yield row
def __init__(self, vcf_file, fast_forward=0) :
self.indexOf = COLUMN_MAP
globes.printColumnWarning( vcf_file, self.indexOf )
self.fin = open( vcf_file, "rb" )
self.patients = getPatients( self.fin )
print "after getPatients"
self.allow_absent = False
self.group_repeats = False
self.iterator = globes.splitIterator( self.fin, burn=fast_forward )
def sortFile( filename ) :
fin = open(filename)
header = fin.readline()
fout = open( "%s.sorted" % filename, 'w' )
fout.write(header)
sorted_splts = sorted( globes.splitIterator( fin, \
stopIter=stopper ), \
key = sortHelper )
fout.write( "\n".join( ['\t'.join(splt) for splt in sorted_splts] ) )
fout.close()
fin.close()
def iterate( self, fast_forward = 0 ) :
count = 0
for row in globes.splitIterator( \
self.file, \
burn = ?, \
header_line_num = ?, \
skipLine = self.skipper, \
headerSanityCheck = self.headerCheck, \
stopIter = self.stopper ) :
if count < fast_forward :
count += 1
continue
else : yield row
def __init__(self, file, switch, fast_forward=1) :
self.file = file
self.switch = switch
self.indexOf = indexOf
self.iterator = globes.splitIterator( self.file, \
burn=1, \
header_line_num=0, \
headerSanityCheck=headerCheck, \
stopIter=stopper, \
skipLine=skipper)
self.allow_absent = False
self.group_repeats = True
#the columns concerning a Variant - want cDNAPosition?
self.cols = ["accession", "functionGVS", "polyPhen", \
"granthamScore", "scorePhastCons", "consScoreGERP", \
"distanceToSplice", "AfricanHapMapFreq", \
"EuropeanHapMapFreq", "AsianHapMapFreq", \
"clinicalAssociation"]
def register( self, dargs ) :
prediction_num = dargs["prediction"]
predictions_file = "%s/%d/%d_predictions.tsv" \
% (globes.SIFT_OUTPUT, \
prediction_num, \
prediction_num)
predictions_file = sort( predictions_file )
self.iterator = globes.splitIterator( predictions_file, stopper=globes.tritonStop )
#the default interaction will be with a varList
self.comp = self.varListComparator
self.eqfunc = self.varListIntegrator
self.ltfunc = doNothing
self.gtfunc = doNothing
#If merging into a SQL iterator (iSQL), then will need to be passed a db
#connection in the arg list
k = "dbconn"
if k in dargs :
self.conn = dargs[k]
self.comp = self.sqlComparator
self.eqfunc = self.sqlIntegrator
def register( self, dargs ) :
switch = dargs['switch'].lower()
if switch == 'snp' :
skipper = globes.dontStop
elif switch == 'indel' :
skipper = self.skipSNPS
self.allow_unmatched = True
else : assert False
self.iterator = globes.splitIterator(dargs['file'], \
burn=3, \
skipper=skipper, \
stopper=globes.tritonStop)
self.comp = self.varListINDELComparator
self.eqfunc = self.varListIntegrator
self.ltfunc = doNothing
self.gtfunc = doNothing
self.conn = dargs['dbconn']
k = 'target'
if k in dargs and dargs[k] == "sql" :
self.comp = self.sqlComparator
self.eqfunc = self.sqlIntegrator