def write_filtered_sequences_and_stats(sequence_dict, sequence_report_general, filtered_sequence_file,
saveExcludedContigs):
if saveExcludedContigs:
path_excluded_contigs = os.path.splitext(filtered_sequence_file)[0] + '.excluded_contigs.fasta'
excluded_contigs = open(path_excluded_contigs, 'wt')
found_excluded_contigs = False
with open(os.path.join(os.path.dirname(filtered_sequence_file), str(
'assembly_mapping_report.sequences_filtered.' + os.path.splitext(os.path.basename(filtered_sequence_file))[
0]) + '.tab'), 'wt') as report_filtered:
with open(filtered_sequence_file, 'wt') as contigs_filtered:
fields = ['header', 'length']
report_filtered.write('\n'.join(
['#general', '>contigs', str(sequence_report_general['filtered']['contigs']), '>bp',
str(sequence_report_general['filtered']['bp'])]) + '\n')
report_filtered.write('#' + '\t'.join(fields) + '\n')
for i in range(1, len(sequence_dict) + 1):
if not sequence_dict[i]['discard']:
report_filtered.write('\t'.join([str(sequence_dict[i][f]) for f in fields]) + '\n')
contigs_filtered.write('>' + sequence_dict[i]['header'] + '\n' + '\n'.join(
utils.chunkstring(sequence_dict[i]['sequence'], 80)) + '\n')
else:
if saveExcludedContigs:
found_excluded_contigs = True
excluded_contigs.write('>' + sequence_dict[i]['header'] + '\n' + '\n'.join(
utils.chunkstring(sequence_dict[i]['sequence'], 80)) + '\n')
if saveExcludedContigs:
excluded_contigs.flush()
excluded_contigs.close()
if not found_excluded_contigs:
os.remove(path_excluded_contigs)
def plot_graphics(self, data):
global ticks
try:
ticks = [':'.join(chunkstring(x[0], 2)) for x in data]
print(data)
print(ticks)
int_time = list(range(len(data)))
temp1 = [float(x[1]) for x in data]
temp2 = [float(x[2]) for x in data]
press1 = [float(x[3]) for x in data]
press2 = [float(x[4]) for x in data]
for graph in [self.temp_graph, self.press_graph]:
graph.clear()
graph.axis.xaxis.set_major_formatter(FuncFormatter(tick_func))
graph.timelen = len(data)
self.temp_graph.axis.plot(int_time, temp1, 'C1', label='T1')
self.temp_graph.axis.plot(int_time, temp2, 'C3', label='T2')
self.temp_graph.axis.legend()
self.press_graph.axis.plot(int_time, press1, 'C4', label='P1')
self.press_graph.axis.plot(int_time, press2, 'C2', label='P2')
self.press_graph.axis.legend()
self.temp_graph.canvas.draw()
self.press_graph.canvas.draw()
except:
QtWidgets.QMessageBox.warning(self.MainWindow, "Ошибка",
"Лог-файл поврежден!")
def write_filtered_sequences_and_stats(sequence_dict, sequence_report_general,
filtered_sequence_file,
saveExcludedContigs):
if saveExcludedContigs:
path_excluded_contigs = os.path.splitext(
filtered_sequence_file)[0] + '.excluded_contigs.fasta'
excluded_contigs = open(path_excluded_contigs, 'wt')
found_excluded_contigs = False
with open(
os.path.join(
os.path.dirname(filtered_sequence_file),
str('assembly_mapping_report.sequences_filtered.' + os.path.
splitext(os.path.basename(filtered_sequence_file))[0]) +
'.tab'), 'wt') as report_filtered:
with open(filtered_sequence_file, 'wt') as contigs_filtered:
fields = ['header', 'length']
report_filtered.write('\n'.join([
'#general', '>contigs',
str(sequence_report_general['filtered']['contigs']), '>bp',
str(sequence_report_general['filtered']['bp'])
]) + '\n')
report_filtered.write('#' + '\t'.join(fields) + '\n')
for i in range(1, len(sequence_dict) + 1):
if not sequence_dict[i]['discard']:
report_filtered.write(
'\t'.join([str(sequence_dict[i][f])
for f in fields]) + '\n')
contigs_filtered.write(
'>' + sequence_dict[i]['header'] + '\n' + '\n'.join(
utils.chunkstring(sequence_dict[i]['sequence'],
80)) + '\n')
else:
if saveExcludedContigs:
found_excluded_contigs = True
excluded_contigs.write(
'>' + sequence_dict[i]['header'] + '\n' +
'\n'.join(
utils.chunkstring(sequence_dict[i]['sequence'],
80)) + '\n')
if saveExcludedContigs:
excluded_contigs.flush()
excluded_contigs.close()
if not found_excluded_contigs:
os.remove(path_excluded_contigs)
def on_finish_fetching(self):
if pyboard.last_operation:
self.update_status('Выберите файл')
files_raw = ''.join([chr(x) for x in pyboard.recieved_file])
if files_raw != 'no':
files = [
'.'.join(chunkstring(x, 2))
for x in chunkstring(files_raw, 10)
]
print(files)
for filename in files:
self.files_list.addItem(filename)
self.open_butt.setEnabled(True)
else:
QtWidgets.QMessageBox.error(self, "Ошибка",
"Не удалось получить список файлов")
self.fetching_list = False
def clean_novel_alleles(novel_alleles, scheme_mlst, profile):
"""
Clean the fasta file with the novel alleles produced by mlst
Parameters
----------
novel_alleles : str
Path for fasta file containing the novel alleles
scheme_mlst : str
MLST schema found by mlst
profile : list
List of strings with the profile found
Returns
-------
"""
unknown_genes = []
for gene_allele in profile:
gene = gene_allele.split('(')[0]
try:
allele = gene_allele.split('(')[1].rstrip(')')
if allele.startswith('~'):
unknown_genes.append(gene)
except IndexError as e:
print('WARNING: {}'.format(e))
try:
novel_alleles_keep = {}
if len(unknown_genes) > 0:
reader = open(novel_alleles, mode='rt') # TODO: newline=None in Python3
fasta_iter = (g for k, g in itertools_groupby(reader, lambda x: x.startswith('>')))
for header in fasta_iter:
# header = header.__next__()[1:].rstrip('\r\n') # TODO: Python3
header = header.next()[1:].rstrip('\r\n')
# seq = ''.join(s.rstrip('\r\n') for s in fasta_iter.__next__()) # TODO: Python3
seq = ''.join(s.rstrip('\r\n') for s in fasta_iter.next())
if header.startswith(scheme_mlst):
gene = header.split('.')[1].split('~')[0]
if gene in unknown_genes:
novel_alleles_keep[header] = seq
reader.close()
os.remove(novel_alleles)
if len(novel_alleles_keep) > 0:
with open(novel_alleles, 'wt') as writer:
for header, seq in novel_alleles_keep.items():
writer.write('>{}\n'.format(header))
writer.write('\n'.join(utils.chunkstring(seq, 80)) + '\n')
except OSError as e: # TODO: FileNotFoundError in Python3
print('An unknown ST was found but no novel alleles fasta file was produced by mlst software:\n'
'{}'.format(e))
def on_download_existing_finished(self, status):
print("BEGIN PARSING")
print(pyboard.recieved_file)
files_raw = ''.join([chr(x) for x in pyboard.recieved_file])
print("EDITOR data", files_raw)
if files_raw != 'no':
files = chunkstring(files_raw, 3)
self.recipes_list.clear()
for filename in files:
self.recipes_list.addItem(filename)
self.open_button.setEnabled(True)
self.save_button.setEnabled(True)
self.warn('Список существующих рецептов получен!')
def clean_novel_alleles(novel_alleles, scheme_mlst, profile):
"""
Clean the fasta file with the novel alleles produced by mlst
Parameters
----------
novel_alleles : str
Path for fasta file containing the novel alleles
scheme_mlst : str
MLST schema found by mlst
profile : list
List of strings with the profile found
Returns
-------
"""
unknown_genes = []
for gene_allele in profile:
gene = gene_allele.split('(')[0]
try:
allele = gene_allele.split('(')[1].rstrip(')')
if allele.startswith('~'):
unknown_genes.append(gene)
except IndexError as e:
print('WARNING: {}'.format(e))
novel_alleles_keep = {}
if len(unknown_genes) > 0:
reader = open(novel_alleles,
mode='rt') # TODO: newline=None in Python3
fasta_iter = (
g
for k, g in itertools_groupby(reader, lambda x: x.startswith('>')))
for header in fasta_iter:
# header = header.__next__()[1:].rstrip('\r\n') # TODO: Python3
header = header.next()[1:].rstrip('\r\n')
# seq = ''.join(s.rstrip('\r\n') for s in fasta_iter.__next__()) # TODO: Python3
seq = ''.join(s.rstrip('\r\n') for s in fasta_iter.next())
if header.startswith(scheme_mlst):
gene = header.split('.')[1].split('~')[0]
if gene in unknown_genes:
novel_alleles_keep[header] = seq
reader.close()
os.remove(novel_alleles)
if len(novel_alleles_keep) > 0:
with open(novel_alleles, 'wt') as writer:
for header, seq in novel_alleles_keep.items():
writer.write('>{}\n'.format(header))
writer.write('\n'.join(utils.chunkstring(seq, 80)) + '\n')
def on_build_graph(self):
graph_file = QtWidgets.QFileDialog.getOpenFileName()[0]
if not graph_file: return
print(graph_file)
file_raw = open(graph_file).read()
print(file_raw)
try:
data = [[x[:4]] + list(chunkstring(x[4:], 5))
for x in file_raw.split('\n') if len(x) == 24]
except:
print('DATA INCORRECT')
QtWidgets.QMessageBox.error(self, "Ошибка", "Файл поврежден!")
else:
print("GRAFIC data", data)
self.plot_graphics(data)
def on_file_downloaded(self):
if pyboard.last_operation:
file_raw = ''.join([chr(x) for x in pyboard.recieved_file])
print(file_raw)
self.open_butt.setEnabled(True)
try:
data = [[x[:4]] + list(chunkstring(x[4:], 5))
for x in file_raw.split('\n') if len(x) == 24]
except:
print('DATA INCORRECT')
QtWidgets.QMessageBox.error(self, "Ошибка", "Файл поврежден!")
else:
print("GRAFIC data", data)
app.plot_graphics(data)
self.close()
else:
QtWidgets.QMessageBox.error(self, "Ошибка",
"Не удалось получить список файлов")
def translate(text):
# grab MS credentials:
config = configparser.ConfigParser()
config.read("config.cnf")
subscription_key = config.get('Translation', 'API_key')
endpoint = config.get('Translation', 'endpoint_url')
path = '/translate?api-version=3.0'
params = '&to=en'
constructed_url = endpoint + path + params
headers = {
'Ocp-Apim-Subscription-Key': subscription_key,
'Content-type': 'application/json',
'X-ClientTraceId': str(uuid.uuid4())
}
translated_text = ''
for chunk in chunkstring(text):
text_to_translate = [{'text': chunk}]
# post request
request = requests.post(constructed_url,
headers=headers,
json=text_to_translate)
response = request.json()
try:
translated_text += json.loads(
json.dumps(response,
sort_keys=True,
indent=4,
ensure_ascii=False,
separators=(',',
': ')))[0]['translations'][0]['text']
except KeyError: # doesn't seem to be critical.
print('skipping these many characters: ', len(chunk))
print('keyerror, whatever that means.')
continue
return translated_text