def main():
'''main method.'''
seqs = {}
seq_id = ''
seq = ''
rand_len = 300
max_repeat_nucl = 3
invalid_patterns = ['AGATCT', 'CACCTGC', 'CTCGAG', 'GAATTC',
'GAGTC([AGCT]{5})', 'GGATCC', 'GGTCTC']
with open('promoters.txt') as fle:
for line in fle.read().split('\r'):
if len(line) > 0 and line[0] == '>':
if len(seq) > 0:
seqs[seq_id] = seq
seq_id = line[1:].strip()
seq = ''
else:
seq = seq + line.strip().upper()
seqs[seq_id] = seq
for seq_id, seq in seqs.iteritems():
rand_range = range(seq.find('*'), seq.find('*') + rand_len)
update_seq = string.replace(
seq, '*', sequence_utils.get_random_dna(rand_len, max_repeat_nucl,
invalid_patterns))
while _unacceptable(update_seq, rand_range):
update_seq = string.replace(
seq, '*', sequence_utils.get_random_dna(rand_len,
max_repeat_nucl,
invalid_patterns))
seqs[seq_id] = update_seq
with open('promoters_update.txt', 'w') as fle:
for seq_id, seq in seqs.iteritems():
fle.write('>' + seq_id + '\n')
fle.write(seq + '\n')
def get_melt_temp(length=35, max_repeat_nuc=5, num=100):
'''Gets melting temps.'''
melt_tmps = []
seqs = [sequence_utils.get_random_dna(length, max_repeat_nuc)
for _ in range(num)]
for idx, seq in enumerate(seqs):
try:
melt_tmps.extend([sequence_utils.get_melting_temp(seq, dna2,
strict=False)
for dna2 in seqs[idx + 1:]])
except ZeroDivisionError, err:
# Take no action
print err