print("Error: imgt-data.fasta file not detected for\'", species + \
"'. Please generate and place it in the appropriate Data subdirectory.")
sys.exit()
# If so, check the modification time for the imgt-data.fasta file, assuming that's the last download time
input_imgt_file = species_dir + 'imgt-data.fasta'
mod_date = datetime.fromtimestamp(
os.path.getmtime(input_imgt_file)).strftime('%Y-%m-%d')
# Then read through the FASTA and sort into the appropriate chains
with open(input_imgt_file, 'rU') as in_file, \
open(species_dir + 'TRA.fasta', 'w') as TRA, \
open(species_dir + 'TRB.fasta', 'w') as TRB:
prot = coll.defaultdict(coll.defaultdict)
for fasta_id, seq, blank in fxn.read_fa(in_file):
gene, allele = fasta_id.split('|')[1].split('*')
# NB: TRDV included with TRA genes due to the evidence that even non 'TRAV/DV' genes can recombine with TRAJ
if 'TRA' in gene or 'TRDV' in gene:
TRA.write(fxn.fastafy(fasta_id, seq))
elif 'TRB' in gene:
TRB.write(fxn.fastafy(fasta_id, seq))
# Finally log the dates
log_txt = 'imgt-data.fasta_last_modified ' + mod_date + '\nsplit-imgt-data.py_last_run ' + fxn.today(
)
with open(species_dir + 'data-production-date.txt', 'w') as log_file:
log_file.write(log_txt)
fxn.check_scripts_dir()
sns.set(font="Arial", font_scale=1.5)
# Sort directories, get data
plot_dir = fxn.plot_dir + fxn.get_date() + '-mouse-proteome-check/'
if not os.path.exists(plot_dir):
os.mkdir(plot_dir)
# Read proteome into dict
mouse_proteome_file = [
x for x in os.listdir(fxn.base_data_dir) if '_mouse.fasta' in x
][0]
mouse_proteins = coll.defaultdict()
with gzip.open(fxn.base_data_dir + mouse_proteome_file, 'rU') as in_file:
for protein, seq, blank in fxn.read_fa(in_file):
mouse_proteins[protein.split(' ')[0]] = seq
# Then scroll through non-predicted binder files, build an AC trie of all the peptides per file
data_dir = '../Data/NonPredictedBinders/'
matches = coll.defaultdict(fxn.nest_counter)
all_peptides = coll.defaultdict(list)
for f in [x for x in os.listdir(data_dir) if x.endswith('.txt')]:
nam = f.split('-')[0]
search_builder = AcoraBuilder()
peptides = []
# Build trie
with open(data_dir + f, 'rU') as in_file:
for line in in_file:
search_builder.add(line.rstrip())