def postProcessOutput(self):
super(BlastOutput6ParserAnalysis,self).postProcessOutput()
data = {}
file = self.input_files[0]
with open(file) as fp:
for line in fp:
line = line.rstrip('\n')
ff = line.split('\t')
qid = ff[0]
hid = ff[1]
pid = float(ff[2])
alnlen = ff[3]
mm = int(ff[4])
gaps = int(ff[5])
qstart = int(ff[6])
qend = int(ff[7])
hstart = int(ff[8])
hend = int(ff[9])
exval = float(ff[10])
score = float(ff[11])
feat = Feature()
feat.qid = qid
feat.qstart = qstart
feat.qend = qend
feat.hid = hid
feat.hstart = hstart
feat.hend = hend
feat.pid = pid
feat.score = score
feat.mm = mm
feat.gaps = gaps
feat.exval = exval
if len(ff) > 12:
feat.qlen = int(ff[12])
feat.hlen = int(ff[13])
feat.qseq = ff[14]
feat.hseq = ff[15]
if not qid in data:
data[qid] = []
tmp = data[qid]
tmp.append(feat)
self.data = data
def parseLine(self,line):
line = line.rstrip('\n')
ff = line.split('\t')
#psLayout version 3
#match mis- rep. N's Q gap Q gap T gap T gap strand Q Q Q Q T T T T block blockSizes qStart tStarts
#match match count bases count bases name size start end name size start end count
#---------------------------------------------------------------------------------------------------------------------------------------------------------------
#236 0 0 0 0 0 0 0 + TRINITY_DN4669_c0_g1_i1 237 0 236 Gm16144_ENSMUST00000131093 1843 1272 1508 1 236, 0, 1272,
#179 0 0 0 0 0 0 0 - TRINITY_DN4615_c0_g1_i1 317 0 179 Hdhd3_ENSMUST00000037820 2977 0 179 1 179, 138, 0,
#183 0 0 0 0 0 0 0 + TRINITY_DN4601_c0_g1_i1 219 36 219 Atp6v1a_ENSMUST00000130036 40052 2211 2394 1
f = Feature()
match = int(ff[0])
mismatch = int(ff[1])
strand = ff[8]
qid = ff[9]
qlen = int(ff[10])
qstart = int(ff[11])
qend = int(ff[12])
hid = ff[13]
hlen = int(ff[14])
hstart = int(ff[15])
hend = int(ff[16])
f.qid = qid
f.type1 = 'blat'
f.type2 = 'blat'
f.qstart = qstart
f.qend = qend
f.hid = hid
f.hstart = hstart
f.hend = hend
f.score = int(100*match/qlen)
f.qlen = qlen
f.hlen = hlen
f.hitattr['match'] = match
f.hitattr['mismatch'] = mismatch
if strand != ".":
if strand == "+":
f.strand = 1
elif strand == 1:
f.strand = 1
elif strand == "-":
f.strand = -1
elif strand == -1:
f.strand = -1
return f
def parseBlastOutput6(file):
hits = {}
prev = None
with open(file) as fp:
for line in fp:
line = line.rstrip('\n')
ff = line.split('\t')
qid = ff[0]
hid = ff[1]
pid = float(ff[2])
alnlen = ff[3]
mm = int(ff[4])
gaps = int(ff[5])
qstart = int(ff[6])
qend = int(ff[7])
hstart = int(ff[8])
hend = int(ff[9])
exval = float(ff[10])
score = float(ff[11])
feat = Feature()
feat.qid = qid
feat.qstart = qstart
feat.qend = qend
feat.hid = hid
feat.hstart = hstart
feat.hend = hend
feat.pid = pid
feat.score = score
feat.mm = mm
feat.gaps = gaps
feat.exval = exval
if len(ff) > 15:
feat.qlen = int(ff[12])
feat.hlen = int(ff[13])
feat.qseq = ff[14]
feat.hseq = ff[15]
if not qid in hits:
hits[qid] = []
tmp = hits[qid]
tmp.append(feat)
return hits
def parseLine(self, line):
line = line.rstrip('\n')
ff = line.split('\t')
##score name1 strand1 size1 zstart1 end1 name2 strand2 size2 zstart2 end2 identity idPct coverage covPct
#12413 98004798 + 1579 278 1520 F27C8.1 - 1482 200 1455 709/1185 59.8% 1255/1482 84.7%
#15213 98029119 + 1752 526 1572 F27C8.1 - 1482 365 1415 615/1014 60.7% 1050/1482 70.9%
f = Feature()
qstrand = ff[2]
hstrand = ff[7]
qid = ff[1]
qlen = int(ff[3])
qstart = int(ff[4])
qend = int(ff[5])
hid = ff[6]
hlen = int(ff[8])
hstart = int(ff[9])
hend = int(ff[10])
f.qid = qid
f.type1 = 'lastz'
f.type2 = 'lastz'
f.qstart = qstart
f.qend = qend
f.hid = hid
f.hstart = hstart
f.hend = hend
f.score = int(ff[0])
f.qlen = qlen
f.hlen = hlen
pid = ff[12].replace('%', '')
cov = ff[14].replace('%', '')
f.hitattr['pid'] = float(pid)
f.hitattr['cov'] = float(cov)
if qstrand == "+" and hstrand == "+":
strand = 1
elif qstrand == "+" and hstrand == "-":
strand = -1
elif qstrand == "-" and hstrand == "+":
strand = -1
elif qstrand == "-" and hstrand == "-":
strand = 1
return f