def write_sequeces(out_file, sequences_dict):
with open(out_file, 'wt') as writer:
for header in sequences_dict:
writer.write('>' + header + '\n')
writer.write('\n'.join(
utils.chunkstring(sequences_dict[header]['sequence'], 80)) +
'\n')
def clean_headers_reference_file(reference_file, outdir):
new_reference_file = reference_file
sequences, headers, headers_changed = get_sequence_information(
reference_file)
if headers_changed:
utils.Bcolors_print(
str('At least one of the following characters was found in sequences headers: {}.\n'
'Replacing those with _'.format(problematic_characters) +
'\n'), 'UNDERLINE')
new_reference_file = \
os.path.join(outdir, os.path.splitext(os.path.basename(reference_file))[0] + '.headers_renamed.fasta')
with open(new_reference_file, 'wt') as writer:
for i in sequences:
writer.write('>' + sequences[i]['header'] + '\n')
fasta_sequence_lines = utils.chunkstring(
sequences[i]['sequence'], 80)
for line in fasta_sequence_lines:
writer.write(line + '\n')
return new_reference_file, headers, sequences
def write_seq_from_sequence_dict(sequence_dict, out_fasta_file):
"""
Write a fasta file with sequences found in sequence_dict dictionary
Parameters
----------
sequence_dict : dict
Dictionary as follow
sequence_dict[counter] = {'header': without_greater_sign, 'sequence': seq, 'length': seq_length_int}
out_fasta_file : str
Path to output fasta file
Returns
-------
"""
with open(out_fasta_file, 'wt', newline='\n') as writer:
for _, seq_info in sequence_dict.items():
writer.write('>{header}\n'
'{seq}\n'.format(header=seq_info['header'],
seq='\n'.join(
utils.chunkstring(
seq_info['sequence'], 80))))
def write_sequence(reference_dict, writer):
for header, sequence in reference_dict.items():
writer.write('>' + header + '\n')
writer.write('\n'.join(utils.chunkstring(sequence, 80)) + '\n')