Update code/pdb_featureVector.py

code/pdb_featureVector.py

@@ -227,6 +227,8 @@ def pdb(input_set, mode, impute):
         existing_pdb = [i.split('/')[-1].split('.')[0].lower() for i in existing_pdb]
         cnt = 0
         for search in pdbs:
+            st.write('PDBS', search)
+            
             try:
                 if search.lower() not in existing_pdb:
                     file = pdbl.retrieve_pdb_file(search, pdir=Path(path_to_output_files / 'pdb_structures'), file_format="pdb")
@@ -367,7 +369,7 @@ def pdb(input_set, mode, impute):
         with_pdb.replace({'[]': 'nan'}, inplace=True)
         with_pdb.replace({'nan-nan': 'nan'}, inplace=True)
         with_pdb.replace({'': 'nan'}, inplace=True)
-
+        
         """
         STEP 7
         Do alignment for PDB
@@ -406,7 +408,7 @@ def pdb(input_set, mode, impute):
         print('Aligning sequences...\n')
         aligned_m = final_stage(dfM, annotation_list, Path(path_to_output_files / 'alignment_files'))
         aligned_nm = final_stage(dfNM, annotation_list, Path(path_to_output_files / 'alignment_files'))
-
+        st.write('aligned', aligned_m)
         # When PDB sequence is nan, it is wrongly aligned to the UniProt sequence. Fix them.
         for i in aligned_m.index:
             if aligned_m.at[i, 'pdbSequence'] == 'nan':
@@ -448,6 +450,7 @@ def pdb(input_set, mode, impute):
         yes_pdb_no_match = after_up_pdb_alignment[
             (after_up_pdb_alignment.pdbID != 'nan') & (after_up_pdb_alignment.mutationPositionOnPDB == 'nan')]
         no_pdb = no_pdb.copy()
+        st.write('pdb_aligned', pdb_aligned)
 
 
         print('PDB matching is completed...\n')