def create_uni_struct(pdb_df):
""" Creates a DataFrame that has UniProt ID and composite
structure for UniProt.
Args:
pdb_df (DataFrame): A DataFrame produced by create_composite.
Returns:
df (DataFrame): A new DataFrame with UniProt ID and
composite UniProt structure.
"""
uni_struct = {'SP_PRIMARY': [], 'STRUCT': []}
uni_list = read_pdb_chain_uniprot_uniIDs(pdb_df)
progress = ProgressBar(
len(uni_list),
approx_percentage=1,
start_msg="Creating DataFrame with ID and composite structure.",
end_msg="Done creating DataFrame with ID and composite structure."
)
for uni in uni_list:
pdbs = pdb_df[pdb_df.SP_PRIMARY == uni]
struct_list = []
assert len(pdbs.index) > 1
for i, row in pdbs.iterrows():
struct_list.append(row.SEC_STRUCT)
assert len(struct_list) > 1
for struct in struct_list:
assert len(struct) > 0
assert len(struct) == len(struct_list[0])
assert len(struct_list) == len(pdbs.index)
comp_struct = _uni_struct(struct_list)
uni_struct['SP_PRIMARY'].append(uni)
uni_struct['STRUCT'].append(comp_struct)
progress.inc()
df = pd.DataFrame(uni_struct)
return df
def _initialize_uniprot_list(self):
self.uni_list = read_pdb_chain_uniprot_uniIDs(self.df)
return None
