def loadSeqAndChain(seq_file,
k,
suppress_save=False,
mc_file=None,
retain_n=False):
"""Load the sequence and the Markov Chain List.
Load the MC list from a file if it exists. If not, create the chain
and save it to the file for the next use (skip the save if suppressed)."""
template_seq = str(SeqIO.read(seq_file, 'fasta').seq)
# Cut out all the maximul prefix and suffix of ambiguity codes -- which will have no effect on the Markov chain construction.
if not retain_n:
start = 0
while template_seq[start] not in bases:
start += 1
finish = len(template_seq)
while template_seq[finish - 1] not in bases:
finish -= 1
coord_adjust = start
template_seq = template_seq[start:finish]
else:
coord_adjust = 0
mc_file = re.sub("\.(fa|fasta)$", ".pmc%d" %
(k), seq_file) if mc_file is None else mc_file
if os.path.exists(mc_file):
markov_list = markov_gen.read_pmck(mc_file)
else:
markov_list = markov_gen.MarkovArray(k, template_seq)
if not suppress_save:
markov_gen.pickle_markov_list(markov_list, mc_file)
return template_seq, markov_list, coord_adjust
def loadSeqAndChain(seq_file, k, suppress_save = False, mc_file = None, retain_n = False):
"""Load the sequence and the Markov Chain List.
Load the MC list from a file if it exists. If not, create the chain
and save it to the file for the next use (skip the save if suppressed).
Parameters:
* seq_file: The sequence file.
* k: The order of the markov chain.
* suppress_save: Boolean. If true, don't save the generated MC file. (Can't imagine why we would want this.)
* mc_file: The name of the mc_file to use. (Derive from seq_file if not provided.)
* retrain_n: If false, we will be cutting of the largest possible N* prefix and suffix.
Return: A tuple:
1. The chromosome sequence.
2. The markov chain
3. Where we will start in the template sequence (in case a prefix has been removed).
4. Where we will end in the templace sequence (in case a suffix has been removed).
"""
template_seq = str(SeqIO.read(seq_file, 'fasta').seq)
# Cut out all the maximul prefix and suffix of ambiguity codes -- which will have no effect on the Markov chain construction.
start, finish = 0, len(template_seq)
if not retain_n: # Cut down the chromsome to the first real base at each end -- eliminate trailing Ns.
while template_seq[start] not in bases: start += 1
while template_seq[finish-1] not in bases: finish -= 1
mc_file = re.sub("\.(fa|fasta)$", ".pmc%d" % (k), seq_file) if mc_file is None else mc_file
if os.path.exists(mc_file):
markov_list = markov_gen.read_pmck(mc_file)
else:
markov_list = markov_gen.MarkovArray(k, template_seq)
if not suppress_save:
markov_gen.pickle_markov_list(markov_list, mc_file)
return template_seq, markov_list, start, finish
def loadSeqAndChain(seq_file, k, suppress_save = False, mc_file = None, retain_n = False):
"""Load the sequence and the Markov Chain List.
Load the MC list from a file if it exists. If not, create the chain
and save it to the file for the next use (skip the save if suppressed)."""
template_seq = str(SeqIO.read(seq_file, 'fasta').seq)
# Cut out all the maximul prefix and suffix of ambiguity codes -- which will have no effect on the Markov chain construction.
if not retain_n:
start = 0
while template_seq[start] not in bases: start += 1
finish = len(template_seq)
while template_seq[finish-1] not in bases: finish -= 1
coord_adjust = start
template_seq = template_seq[start:finish]
else:
coord_adjust = 0
mc_file = re.sub("\.(fa|fasta)$", ".pmc%d" % (k), seq_file) if mc_file is None else mc_file
if os.path.exists(mc_file):
markov_list = markov_gen.read_pmck(mc_file)
else:
markov_list = markov_gen.MarkovArray(k, template_seq)
if not suppress_save:
markov_gen.pickle_markov_list(markov_list, mc_file)
return template_seq, markov_list, coord_adjust
def loadSeqAndChain(seq_file,
k,
suppress_save=False,
mc_file=None,
retain_n=False):
"""Load the sequence and the Markov Chain List.
Load the MC list from a file if it exists. If not, create the chain
and save it to the file for the next use (skip the save if suppressed).
Parameters:
* seq_file: The sequence file.
* k: The order of the markov chain.
* suppress_save: Boolean. If true, don't save the generated MC file. (Can't imagine why we would want this.)
* mc_file: The name of the mc_file to use. (Derive from seq_file if not provided.)
* retrain_n: If false, we will be cutting of the largest possible N* prefix and suffix.
Return: A tuple:
1. The chromosome sequence.
2. The markov chain
3. Where we will start in the template sequence (in case a prefix has been removed).
4. Where we will end in the templace sequence (in case a suffix has been removed).
"""
template_seq = str(SeqIO.read(seq_file, 'fasta').seq)
# Cut out all the maximul prefix and suffix of ambiguity codes -- which will have no effect on the Markov chain construction.
start, finish = 0, len(template_seq)
if not retain_n: # Cut down the chromsome to the first real base at each end -- eliminate trailing Ns.
while template_seq[start] not in bases:
start += 1
while template_seq[finish - 1] not in bases:
finish -= 1
mc_file = re.sub("\.(fa|fasta)$", ".pmc%d" %
(k), seq_file) if mc_file is None else mc_file
if os.path.exists(mc_file):
markov_list = markov_gen.read_pmck(mc_file)
else:
markov_list = markov_gen.MarkovArray(k, template_seq)
if not suppress_save:
markov_gen.pickle_markov_list(markov_list, mc_file)
return template_seq, markov_list, start, finish