def save_defaults(self, overwrite=False):
"""Saves species in the right display box to a user specified species text file."""
desired_file = self.selected_default
if not overwrite:
print('should be asking for save file name')
desired_file = fasta_lib.save_file(self.script_path, [('Text files', '*.txt')],
default_file=os.path.split(self.selected_default)[1],
title_string='Specify a default species file name')
if desired_file:
try:
# write default species list to file
items = self.tree_right.get_children()
databases = [self.tree_right.item(item)['values'] for item in items]
for database in databases:
database[-1] = database[-1].rstrip(r"""\'"*""") # seem to accumulate EOL characters
# Remove duplicates
db_set = set(tuple(x) for x in databases)
databases = sorted([list(x) for x in db_set], key=lambda y: int(y[0])) # sort DBs by taxon
with open(desired_file, "w") as defaults_txt:
self.selected_default = desired_file
for database in databases:
defaults_txt.write("{}\n".format(database))
self.status_bar.config(text="Databases saved to species text file")
except OSError:
messagebox.showwarning("Invalid Filename!", "Cannot save species list to selected folder!")
# control flags
KEEP_CONTAMS = False
# get the files, etc.
list_file_name = fasta_lib.get_file(os.getcwd(), [('Text files', '*.txt')],
'Browse to accession list text file')
if not list_file_name: sys.exit()
results_location = os.path.split(list_file_name)[0]
database_name = fasta_lib.get_file(r'C:\Xcalibur\database',
[('FASTA files', '*.fasta')],
'Select the database')
if not database_name: sys.exit()
new_name = os.path.split(database_name)[1]
new_name = os.path.splitext(new_name)[0]
subset_DB_name = fasta_lib.save_file(results_location,
[('FASTA files', '*.fasta')],
default_file=new_name + '_subset.fasta',
title_string='Name of subset database')
if not subset_DB_name: sys.exit()
if os.path.splitext(subset_DB_name)[1] == '':
subset_DB_name += '.fasta'
# open the accession list file and save accessions in dictionary
print('=======================================================')
print(' make_subset_DB_from_list.py, Phil Wilmarth, OHSU 2018 ')
print('=======================================================')
print('Processing accessions file:', time.ctime())
IDs = {}
read = 0
for acc in open(list_file_name, 'r'):
# this assumes accessions from PAW pipeline results files
try:
database = os.getcwd()
print('Select the FASTA file with extra sequences')
extra_file = fasta_lib.get_file(database,
[('FASTA files', '*.fasta'), ('All files', '*.*')],
'Select Extra Sequences (FASTA format)')
if extra_file == '': sys.exit() # cancel button response
extra_name = os.path.split(extra_file)[1]
extra_name = extra_name.split('.fasta')[0]
print('Select the main FASTA file')
fasta_file = fasta_lib.get_file(database, [('FASTA files', '*.fasta'),
('GZipped files', '*.gz'),
('All files', '*.*')],
'Select FASTA database file')
if fasta_file == '': sys.exit() # cancel button response
default = os.path.split(fasta_file)[0]
fasta_name = os.path.split(fasta_file)[1]
default_file = extra_name + '_' + fasta_name
print('Select location and name for new FASTA database')
output_file = fasta_lib.save_file(default, [('FASTA files', '*.fasta'),
('All files', '*.*')],
default_file, 'Output filename and location')
if output_file == '': sys.exit() # cancel button response
# call add extras and reverse function
fasta_add_extras(extra_file, fasta_file, output_file)
# end
