def main(args):
logging.basicConfig(level=logging.getLevelName(args.logging))
logging.info('User args: %s' % pformat(args))
config = load_config_from_json_file(
args.config,
['gap', 'same', 'diff', 'max_number_of_paths', 'max_sequence_length'])
logging.info('Config is: \n%s' % pformat(config))
seq1 = load_fasta_file(args.input1)
seq2 = load_fasta_file(args.input2)
if config['max_sequence_length'] != 0 and max(
len(seq1), len(seq2)) > config['max_sequence_length']:
raise ValueError('Sequence exceeded max_sequence_length ')
score_matrix, nodes_mapping = solve(seq1, seq2, config['gap'],
config['diff'], config['same'])
logging.debug('Score matrix: \n%s' % pformat(score_matrix))
logging.debug('Nodes mapping: (target_node): [(parent_node),...]\n%s' %
pformat(nodes_mapping))
logging.info('Alignments score: %s' % score_matrix[len(seq1), len(seq2)])
paths = PathResolver(nodes_mapping).resolve_paths(
len(seq1), len(seq2), config['max_number_of_paths'])
allignments = [get_allignments(path, seq1, seq2) for path in paths]
for (allignment_1, allignment_2), i in zip(allignments,
range(len(allignments))):
logging.info('[A%04d] %s' % (i, allignment_1))
logging.info('[A%04d] %s' % (i, allignment_2))
if args.output:
save_output(
args.output, {
'seq1': seq1,
'seq2': seq2,
'config': config,
'allignments': allignments,
'score_matrix': score_matrix.tolist()
})
logging.info('Saved output to %s' % args.output)
def load_train_sequences(fasta_file_path, clusters_file_path):
"""
:param fasta_file_path:{string}, path to fasta input file.
:param clusters_file_path:{string},path to cluster file.
:return:{list}, list of train sequences.
"""
observation = load_fasta_file(fasta_file_path)
train_sequences = []
with open(clusters_file_path,'r') as tsv:
reader = csv.reader(tsv, dialect='excel-tab')
for line in [line for line in reader][1:]:
start, end = map(int, line)
train_sequences.append(observation[start-100:end+100])
return train_sequences
def main():
from hmm import load_hmm_model_from_files
fasta_file_path = r'data/chrom17.fasta'
emission_input_file = r'data/initial_emission.tsv'
transition_input_file = r'data/initial_transition.tsv'
hmm_model = load_hmm_model_from_files(emission_input_file, transition_input_file)
observation = load_fasta_file(fasta_file_path)
v, ptr = viterbi_algorithm(hmm_model, observation)
np.savez_compressed('output/viterbi_algorithm_output.npz', v=v, ptr=ptr)
path = restore_viterbi_path(v,ptr)
np.savez_compressed('output/path.npz', path=path)
q_3_1_c(path, observation)
def build_draft_genome_seq(task):
draft_genome_summary = {}
vc_summary_path = task.path.joinpath(task.id, task.id + '_vc_summary.json')
vc_dict = utils.load_json_file(vc_summary_path)
dominant_vc = {}
for ref_order in range(1, task.ref_num + 1):
dominant_vc[ref_order] = {}
draft_genome_summary[ref_order] = {
'conflicts': [],
'snv_list': [],
'error': [],
'file_path': ''
}
for vc_table in vc_dict.values():
for pos, snvs in vc_table[str(ref_order)].items():
ref = snvs['REF']
for snv, alns in snvs['SNV'].items():
for aligner in alns:
if Decimal(alns[aligner]['FREQ'][:-1]) / 100 > Decimal(
task.vc_threshold):
if dominant_vc[ref_order].get(pos) == None:
dominant_vc[ref_order][pos] = {
'REF': ref,
'ALT': {}
}
if dominant_vc[ref_order][pos]['ALT'].get(
snv) == None:
dominant_vc[ref_order][pos]['ALT'].update(
{snv: {
'SCORE': 0
}})
dominant_vc[ref_order][pos]['ALT'][snv][
'SCORE'] += 1
fasta_base_list = []
imported_ref = task.path.joinpath(
task.id, 'reference', '%s_ref_%d.fasta' % (task.id, ref_order))
ref_fasta_dict = utils.load_fasta_file(imported_ref)
for base in list(ref_fasta_dict.values())[0]:
fasta_base_list.append(base)
for pos, vc in dominant_vc[ref_order].items():
if len(vc['ALT']) > 1:
# skip conflict results
draft_genome_summary[ref_order]['conflicts'].append(pos)
else:
ref_mer = vc['REF']
alt_mer = list(vc['ALT'].keys())[0]
score = int(vc['ALT'][alt_mer]['SCORE'])
if score >= int(task.min_vc_score):
# apply snv onto reference sequence
i = 0
for base in ref_mer[1:]:
if fasta_base_list[int(pos) + i] != base:
draft_genome_summary[ref_order]['error'].append(
pos)
break
fasta_base_list[int(pos) + i] = ''
i += 1
fasta_base_list[int(pos) - 1] = alt_mer
# record apllied snv
draft_genome_summary[ref_order]['snv_list'].append(
'%s%s%s' % (ref_mer, pos, alt_mer))
draft_fasta_dict = {
'%s_draft_%d' % (task.id, ref_order): ''.join(fasta_base_list)
}
draft_cwd = task.path.joinpath(task.id, 'draft_genome')
draft_fasta_path = draft_cwd.joinpath('%s_draft_%d.fasta' %
(task.id, ref_order))
draft_genome_summary[ref_order]['file_path'] = str(draft_fasta_path)
Path.mkdir(draft_cwd, parents=True, exist_ok=True)
utils.build_fasta_file(draft_fasta_path, draft_fasta_dict)
utils.build_json_file(
draft_cwd.joinpath('%s_draft_summary.json' % task.id),
draft_genome_summary)
size=len(observation),
replace=True))
f = forward_algorithm(hmm_model, random_observation)
print(f[1, -1])
def q_2_b_iii(hmm_model, observation):
"""
calculating the log probability of observing chrom17.fasta given the model.
:return:
"""
repetitive_observation = 'A'*len(observation)
f = forward_algorithm(hmm_model, repetitive_observation)
print(f[1, -1])
if __name__ == '__main__':
from hmm import load_hmm_model_from_files
fasta_file_path = r'data/chrom17.fasta'
observation = load_fasta_file(fasta_file_path)
emission_input_file = r'data/initial_emission.tsv'
transition_input_file = r'data/initial_transition.tsv'
hmm_model = load_hmm_model_from_files(emission_input_file, transition_input_file)
q_2_b_i(hmm_model, observation)
#q_2_b_ii(hmm_model, observation)
#q_2_b_iii(hmm_model, observation)