stitch_list_fields = ['_name', 'V', 'J', 'C', '_CDR3', '_leader']
out_headers = [
'TCR_name', 'TRA_nt', 'TRB_nt', 'TRA_aa', 'TRB_aa', 'TRAV', 'TRAJ',
'TRA_CDR3', 'TRBV', 'TRBJ', 'TRB_CDR3', 'TRAC', 'TRBC', 'TRA_leader',
'TRB_leader', 'Linker', 'Linked_nt', 'Linked_aa', 'Warnings/Errors'
]
if __name__ == '__main__':
# Get input arguments, get the required data read in
fxn.check_scripts_dir()
input_args = vars(args())
codons = fxn.get_optimal_codons(input_args['codon_usage'],
input_args['species'].upper())
linker_dict = fxn.get_linker_dict()
tcr_dat = {}
tcr_functionality = {}
for c in ['TRA', 'TRB']:
tmp_tcr_dat, tmp_functionality = fxn.get_imgt_data(
c, st.gene_types, input_args['species'].upper())
tcr_dat[c] = tmp_tcr_dat
tcr_functionality[c] = tmp_functionality
# Then go through in file and stitch each TCR on each line
if not os.path.isfile(input_args['in_file']):
raise IOError(
specific_args['name'], used_alleles['v'], used_alleles['j'],
used_alleles['c'], specific_args['cdr3'], used_alleles['l'] + '(L)'
]
# TODO add information to output header if additional 5'/3' sequences specified?
return out_bits, stitched_nt, transl_offset
gene_types = list(fxn.regions.values())
if __name__ == '__main__':
# Get input arguments, determine the TCR chain in use, get codon table, then load the IMGT data in
fxn.check_scripts_dir()
input_args, chain = fxn.sort_input(vars(args()))
codons = fxn.get_optimal_codons(input_args['codon_usage_path'],
input_args['species'])
imgt_dat, tcr_functionality, partial = fxn.get_imgt_data(
chain, gene_types, input_args['species'])
if input_args['extra_genes']:
imgt_dat, tcr_functionality = fxn.get_additional_genes(
imgt_dat, tcr_functionality)
input_args['skip_c_checks'] = True
if input_args['preferred_alleles_path']:
preferred_alleles = fxn.get_preferred_alleles(
input_args['preferred_alleles_path'], gene_types, imgt_dat,
partial, chain)
else:
preferred_alleles = {}
start = time()
# Get species, in order of command line arg > inferred from input file name > default human
if input_args['species']:
if input_args['species'].upper() in fxn.find_species_covered():
species = input_args['species'].upper()
else:
raise IOError("No data available for requested species: " + input_args['species'])
else:
species_inference = fxn.infer_species(input_args['in_file'])
if species_inference:
species = species_inference
else:
species = 'HUMAN'
codons = fxn.get_optimal_codons(input_args['codon_usage'], species)
linker_dict = fxn.get_linker_dict()
tcr_dat = {}
tcr_functionality = {}
preferences = {}
# Figure out whether a/b or g/d
if input_args['receptor']:
input_receptor = input_args['receptor'].upper()
if ('A' in input_receptor or 'B' in input_receptor) and not ('G' in input_receptor or 'D' in input_receptor):
receptor = 'TRA/TRB'
elif ('G' in input_receptor or 'D' in input_receptor) and not ('A' in input_receptor or 'B' in input_receptor):
receptor = 'TRG/TRD'
else:
raise IOError("Unable to determine receptor from '-r' command string: " + input_receptor + ". ")
preferred_file = values['find_preferred_alleles']
just_file = preferred_file.split('/')[-1]
window['preferred_allele_button'].update(just_file)
elif event == 'Run Stitchr':
warning_msgs = coll.defaultdict(str)
window['linked_out'].update('')
window['linked_log'].update('')
# Disable stitchr button while code is running
window['Run Stitchr'].update(disabled=True)
# Loop through both chains, determine which are asked for, and read data in
codons = fxn.get_optimal_codons('', species)
outputs = coll.defaultdict()
# If additional genes provided, read in and run rudimentary checks
if values['additional_genes'] != extra_gene_text + '\n':
outputs['additional_fastas_raw'] = [
x for x in read_fasta_box(
values['additional_genes'].split('\n') + ['>\n'])
][:-1]
# Check no redundant gene names
if len(list(set([x[0] for x in outputs['additional_fastas_raw']]))) != \
len(outputs['additional_fastas_raw']):
window['additional_genes'].update(
"Multiple FASTAs detected with the same identifier name.\n"
"Additional genes ignored; correct and retry")