Update code/pdb_featureVector.py

code/pdb_featureVector.py

@@ -241,6 +241,17 @@ def pdb(input_set, mode, impute):
             structure = pdb_parser.get_structure(search, pdb_file_content)
             ppb = PPBuilder()
             pdb_data_list = pdb_data.split('\n')
+            pdb_data_list_sequence  = [i for i in pdb_data_list if  i.startswith('SEQRES')]
+            pdb_data_list_sequence = [ list(filter(None,i.split(' '))) for i in pdb_data_list_sequence] 
+            seqs =  {}
+            for i in pdb_data_list_sequence:
+                if i[2] in seqs.keys():
+                    seqs[i[2]] += i[4:]
+                else:
+                    seqs[i[2]]  = i[4:]
+            from Bio.PDB.Polypeptide import *
+            for key, val in seqs.items():
+                seqs[key] = ''.join([threeToOne(i) for i in val])
             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 != []]
@@ -272,7 +283,7 @@ def pdb(input_set, mode, impute):
                         st.write(f"Sequence: {sequence}")
                         pdb_fasta.at[index, 'pdbID'] = search
                         pdb_fasta.at[index, 'chain'] = chain_id
-                        pdb_fasta.at[index, 'pdbSequence'] = str(sequence)
+                        pdb_fasta.at[index, 'pdbSequence'] = str(seq[chain_id])
                         pdb_info.at[index, 'uniprotID'] = ', '.join(up)
                         pdb_info.at[index, 'pdbID'] = search
                         pdb_info.at[index, 'chain'] = chain_id