def main():
usage = "\n%prog [options]"
parser = OptionParser(usage,version="%prog " + __version__)
parser.add_option("-c","--cod",action="store",dest="coding_file",help="Coding sequence (must be CDS without UTR, i.e. from start coden to stop coden) in fasta format")
parser.add_option("-n","--noncod",action="store",dest="noncoding_file",help="Noncoding sequences in fasta format")
(options,args)=parser.parse_args()
if not options.coding_file and not options.noncoding_file:
parser.print_help()
sys.exit(0)
cod = kmer_freq_file(fastafile = options.coding_file, word_size = 6, step_size = 3, frame = 0)
noncod = kmer_freq_file(fastafile = options.noncoding_file, word_size = 6, step_size = 1, frame = 0)
#for i,j in cod.items():
# print str(i) + '\t' + str(j)
cod_sum = 0.0
cod_sum += sum(cod.values())
noncod_sum = 0.0
noncod_sum += sum(noncod.values())
print('hexamer' + '\t' + 'coding' + '\t' + 'noncoding')
for kmer in cod:
if 'N' in kmer:
continue
print(kmer + '\t' + str(float(cod[kmer]/cod_sum)) + '\t' + str(float(noncod[kmer]/noncod_sum)))
def main():
usage = "\n%prog [options]"
parser = OptionParser(usage, version="%prog " + __version__)
parser.add_option("-f",
"--cod",
action="store",
dest="coding_file",
help="sequence in fasta format")
(options, args) = parser.parse_args()
if not options.coding_file:
parser.print_help()
sys.exit(0)
cod = kmer_freq_file(fastafile=options.coding_file,
word_size=6,
step_size=1,
frame=0)
cod_sum = 0.0
cod_sum += sum(cod.values())
cod_sorted = sorted(cod, key=cod.get, reverse=True)
with open("nue_hexamer.txt", "a") as f:
f.write('hexamer' + '\t' + 'coding' + '\n')
for kmer in cod_sorted:
if 'N' in kmer:
continue
with open("nue_hexamer.txt", "a") as f1:
f1.write(kmer + '\t' + str(float(cod[kmer] / cod_sum)) + '\n')