def load_molecules(filename: str, dbname='#'):
'''### load molecules from fasta file
#### params:
- filename: Your file name
- dbname: Name of your data base
*returns* -> dict with molecules
'''
molecules = {}
with open(filename) as file:
lines = file.read()
molecules_str = lines.split('>')[1::]
for molecule_str in molecules_str:
mol_str = molecule_str.split('\n', 1)
mol_str[1] = mol_str[1].replace('\n', '')
ignorable_alleles = ['N', 'L', 'Q', 'S', 'A', 'C']
name = mol_str[0].split(' ')
if len(name) > 2:
name = name[1]
elif len(name) > 1:
name = name[0]
else:
name = name[0]
if any(name.endswith(allele) for allele in ignorable_alleles):
print('ignorated ', name)
continue
if name:
if name.find(':') > 2:
name = ':'.join(name.split(':', 2)[:2])
if any(subname in molecules for subname in name):
continue
else:
name = 'None'
mol = Molecule(dbname=dbname, name=name, seq=mol_str[1])
molecules[name] = mol
return molecules
