def main():
p = optparse.OptionParser(__doc__)
p.add_option("-D", "--debug", action="store_true", dest="D", help="debug")
p.add_option("-N", "--novel", action="store_true", dest="novel",\
help="Only check at novel loci")
p.add_option("-i", "--identifier", dest="i",\
help="Identifier to use")
p.add_option("-o", "--outupt", dest="o",\
help="Input database")
options, args = p.parse_args()
if options.o:
conn = sqlite3.connect(options.o)
else:
conn = sqlite3.connect('/gen_local/hsuj/temp/masked.data')
t = (args[0], )
c = conn.cursor()
c.execute('''SELECT * FROM transcripts WHERE tcons=?''', t)
res = c.fetchmany()
fa = FastA(args[1])
for i in res:
starts = map(int, i[3].split(','))
ends = map(int, i[4].split(','))
starts.sort()
ends.sort()
# Make sure this remains sorted
seq = [fa.grabSequence(i[2], x , y) for x, y in zip(starts,ends)]
print("".join(seq))
def main():
p = optparse.OptionParser(__doc__)
p.add_option("-D", "--debug", action="store_true", dest="debug", help="debug")
p.add_option("-r", "--refSeq", action="store_true", dest="r", help="Input GTF is from refSeq Flat File")
p.add_option(
"-o", "--output", action="store", dest="o", help="Output file, if not set will default to INPUT.an.bam"
)
options, args = p.parse_args()
gtf = GTF.GTF(args[0])
gtf.load_gtf()
vcf = VCFfile(args[1])
fa = FastA(args[2])
pfa = Seq(open("HCN4.pfa.txt", "rU").read())
print ("Length of the protein sequence:%i" % len(pfa))
bleh = open("test.txt", "w+")
sequence = ""
first = True
for x in gtf.data:
print (x.start, x.end)
if first:
# Get last codon
gstart = x.start - 3
gend = x.end - 1
else:
gstart = x.start
gend = x.end
temp = Seq(fa.grabSequence("chr15", gstart + 1, gend + 1).rstrip("\n"))
bleh.write(str(temp))
temp = temp.reverse_complement()
bleh.write(str(temp))
bleh.write("\n")
bleh.write("\n")
sequence = temp + sequence
first = False
print ("Our sequence:%i " % len(sequence))
print ("pp: %i " % len(sequence.translate()))
"""
bleh.write(str(sequence).upper())
bleh.write("\n")
bleh.write("\n")
bleh.write(str(sequence.translate()).upper())
bleh.write("\n")
bleh.write(str(pfa))
"""
print (str(sequence.translate().upper()) == str(pfa).upper())
print "\t".join(["rsID", "chrom", "pos", "bp position", "ref", "alt", "AA position", "AA Ref"])
for line in vcf:
try:
chrom = int(line.chr[3:])
pos = int(line.pos)
except TypeError:
chrom = ord(line.chr[3:])
if chrom == 15:
hit = itertools.takewhile(lambda x: x.start < pos and x.end > pos, gtf.data)
for i in hit:
position_within_gene = i.end - pos + i.dist_tss + 2
aa_num = position_within_gene / 3 + 1
out_list = [
line.id,
str(chrom),
str(pos),
str(position_within_gene),
line.ref,
line.alt,
str(aa_num),
pfa[aa_num - 1],
]
print ("\t".join(out_list))
else:
pass