def process(in_filename, out_filename):
in_file = open(in_filename)
out_file = open(out_filename, 'w')
header, sequence = utils.load(in_file)
in_file.close()
out_file.write(header + '\n')
out_file.write('\n'.join(utils.prepare_subsequences(utils.translate(sequence), 80)))
out_file.close()
def process(model_file, sequence_file, window_size):
model = json.loads(model_file.read())
model_file.close()
header, sequence = utils.load(sequence_file)
sequence_file.close()
print(header)
hmm = HMM(**model['model'])
subsequences = utils.prepare_subsequences(sequence, window_size)
decoded = ''
for seq in subsequences:
decoded += ''.join(hmm.decode(seq)[1])
print('{} / {}'.format(len(decoded), 3 * len(sequence)), file=sys.stderr)
lines = utils.prepare_subsequences(decoded, 80)
for l in lines:
print(l)
def prepare_subsequences_test():
# Given
sequence = 'AAAGGGCCCU'
# When
subseq = utils.prepare_subsequences(sequence, 3)
# Then
assert len(subseq) == 4
assert subseq[0] == 'AAA'
assert subseq[1] == 'GGG'
assert subseq[2] == 'CCC'
assert subseq[3] == 'U'
