Update code/pdb_featureVector.py

code/pdb_featureVector.py

@@ -244,6 +244,9 @@ def pdb(input_set, mode, impute):
             pdb_data_list = [i for i in pdb_data_list if i.startswith('DBREF')]
             pdb_data_list = [[list(filter(None,i.split(' '))) for j in i.split(' ') if j == 'UNP'] for i in pdb_data_list]
             pdb_data_list = [i for i in pdb_data_list if i != []]
+            pdb_data_list_uniprot = [[j[6] for j in i] for i in pdb_data_list]
+
+            
             #pdb_data_list = [[list(filter(None,j)) for j in i] for i in pdb_data_list]
             pdb_data_list = [[j[2] for j in i] for i in pdb_data_list]
             pdb_data_list = [i[0] for i in pdb_data_list]
@@ -251,7 +254,7 @@ def pdb(input_set, mode, impute):
                 for pp in ppb.build_peptides(model):
                     sequence = pp.get_sequence()
                     st.write(sequence)
-                for chain in model:
+                for chain, up in zip(model,pdb_data_list_uniprot ):
                     chain_id = chain.get_id()
                     # Extract UniProt ID if available in the chain's annotations
                     uniprot_ids = fetch_uniprot_ids(search)
@@ -270,7 +273,7 @@ def pdb(input_set, mode, impute):
                         pdb_fasta.at[index, 'pdbID'] = search
                         pdb_fasta.at[index, 'chain'] = chain_id
                         pdb_fasta.at[index, 'pdbSequence'] = str(sequence)
-                        pdb_info.at[index, 'uniprotID'] = ', '.join(uniprot_ids)
+                        pdb_info.at[index, 'uniprotID'] = ', '.join(up)
                         pdb_info.at[index, 'pdbID'] = search
                         pdb_info.at[index, 'chain'] = chain_id
                         pdb_info.at[index, 'resolution'] = resolution
@@ -278,7 +281,10 @@ def pdb(input_set, mode, impute):
 
         print()
         st.write()
+        st.write('pdb_info')
         st.write(pdb_info)
+        st.write('pdb_fasta')
+        st.write(pdb_fasta)
         print('PDB file processing finished..')
         for filename in list(Path(path_to_output_files / 'pdb_structures').glob("*")):
             try: