Update code/pdb_featureVector.py

code/pdb_featureVector.py

@@ -226,12 +226,15 @@ def pdb(input_set, mode, impute):
         existing_pdb = [str(i) for i in existing_pdb]
         existing_pdb = [i.split('/')[-1].split('.')[0].lower() for i in existing_pdb]
         cnt = 0
+        st.write('existing_pdb', existing_pdb)
         for search in pdbs:
             st.write('PDBS', search)
             
             try:
                 if search.lower() not in existing_pdb:
+                    st.write(Path(path_to_output_files / 'pdb_structures'))
                     file = pdbl.retrieve_pdb_file(search, pdir=Path(path_to_output_files / 'pdb_structures'), file_format="pdb")
+                    st.write(file)
                 else:
                     print('PDB structure file exists..')
                     for filename in list(Path(path_to_output_files / 'pdb_structures').glob("*")):
@@ -250,6 +253,7 @@ def pdb(input_set, mode, impute):
                 resolution_method = parser.get_structure(search, file)
                 for record in SeqIO.parse(file, "pdb-seqres"):
                     if record.dbxrefs[0].split(':')[0] == 'UNP':
+                        st.write('RECORD', record)
                         pdb_fasta.at[index, 'pdbID'] = record.id.split(':')[0]
                         pdb_fasta.at[index, 'chain'] = record.id.split(':')[1]
                         pdb_fasta.at[index, 'pdbSequence'] = str(record.seq)
@@ -259,6 +263,7 @@ def pdb(input_set, mode, impute):
                         pdb_info.at[index, 'resolution'] = resolution_method.header['resolution']
                     index += 1
             except:
+                st.write('ERROR INDEX')
                 IndexError
                 pdb_info.at[index, 'uniprotID'] = 'nan'
                 pdb_info.at[index, 'pdbID'] = 'nan'