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
def parseLine(self,line):
line = line.rstrip('\n')
ff = line.split('\t')
#chr1 unknown CDS 3054734 3054733 . + -1 gene_id "ENSMUSG00000090025"; gene_name "ENSMUSG00000090025"; transcript_id "ENSMUST00000160944";
f = Feature()
f.qid = ff[0]
f.type1 = ff[1]
f.type2 = ff[2]
f.qstart = int(ff[3])
f.qend = int(ff[4])
if ff[5] != ".":
f.score = double(ff[5])
if ff[6] != ".":
if ff[6] == "+":
f.strand = 1
elif ff[6] == 1:
f.strand = 1
elif ff[6] == "-":
f.strand = -1
elif ff[6] == -1:
f.strand = -1
if ff[7] != ".":
f.phase = int(ff[7])
featf = ff[8].split(';')
for feat in featf:
feat = feat.strip()
tmp = feat.split(' ')
if len(tmp) == 2:
key = tmp[0].strip()
val = tmp[1].strip()
val = val.strip('"')
f.hitattr[key] = val
if key == "transcript_id":
f.hid = val
return f
def nextGFF(self):
for line in self.fh:
if line is None:
return
if re.search('^##FASTA', line):
return None
if re.search('^#', line):
continue
line = line.rstrip('\n')
ff = line.split('\t')
##gff-version 3
#!gff-spec-version 1.20
#!processor NCBI annotwriter
#!genome-build ASM72083v1
#!genome-build-accession NCBI_Assembly:GCF_000720835.1
##sequence-region NZ_JODT01000001.1 1 388890
##species http://www.ncbi.nlm.nih.gov/Taxonomy/Browser/wwwtax.cgi?id=67256
#NZ_JODT01000001.1 RefSeq region 1 388890 . + . ID=id0;Dbxref=taxon:67256;collection-date=2010;country=Japan: Suginami%2C Tokyo;culture-collection=NRRL:B-2120;gbkey=Src;isolation-source=garden soil;mol_type=genomic DNA;strain=NRRL B-2120;sub-species=achromogenes
#NZ_JODT01000001.1 RefSeq gene 283 1188 . - . ID=gene0;Name=IH25_RS0100010;gbkey=Gene;locus_tag=IH25_RS0100010
#NZ_JODT01000001.1 Protein Homology CDS 283 1188 . - 0 ID=cds0;Parent=gene0;Dbxref=Genbank:WP_030600633.1;Name=WP_030600633.1;gbkey=CDS;product=DeoR faimly transcriptional regulator;protein_id=WP_030600633.1;transl_table=11
#NZ_JODT01000001.1 RefSeq gene 1391 2839 . - . ID=gene1;Name=IH25_RS0100015;gbkey=Gene;locus_tag=IH25_RS0100015
#NZ_JODT01000001.1 Protein Homology CDS 1391 2839 . - 0 ID=cds1;Parent=gene1;Dbxref=Genbank:WP_030600636.1;Name=WP_030600636.1;Note=catalyzes the reduction of nonspecific electron acceptors such as 2%2C6-dimethyl-1%2C4-benzoquinone and 5-hydroxy-1%2C4-naphthaquinone%3B does not have lipoamide dehydrogenase activity;gbkey=CDS;product=flavoprotein disulfide reductase;protein_id=WP_030600636.1;transl_table=11
#NZ_JODT01000001.1 RefSeq gene 2936 3373 . + . ID=gene2;Name=IH25_RS0100020;gbkey=Gene;locus_tag=IH25_RS0100020
#NZ_JODT01000001.1 Protein Homology CDS 2936 3373 . + 0 ID=cds2;Parent=gene2;Dbxref=Genbank:WP_030600640.1;Name=WP_030600640.1;gbkey=CDS;product=gamma-glutamyl cyclotransferase;protein_id=WP_030600640.1;transl_table=11
#NZ_JODT01000001.1 RefSeq gene 3499 4323 . + . ID=gene3;Name=IH25_RS0100025;gbkey=Gene;locus_tag=IH25_RS0100025
#NZ_JODT01000001.1 Protein Homology CDS 3499 4323 . + 0 ID=cds3;Parent=gene3;Dbxref=Genbank:WP_03060
if len(ff) < 8:
raise Exception(
"GFF line needs 8 or more fields to parse [%s]" % line)
f = Feature()
f.qid = ff[0]
f.type1 = ff[1]
f.type2 = ff[2]
f.qstart = int(ff[3])
f.qend = int(ff[4])
f.score = ff[5]
f.strand = ff[6]
f.phase = ff[7]
if f.score == ".":
f.score = 0
else:
f.score = int(f.score)
if f.strand == "+":
f.strand = 1
if f.strand == "-":
f.strand = -1
if f.strand == ".":
f.strand = 0
if len(ff) > 8:
hidstr = ff[8]
hitattr = {}
hffarr = hidstr.split(';')
for hff in hffarr:
tmparr = hff.split('=')
hitattr[tmparr[0]] = tmparr[1]
f.hitattr = hitattr
return f