Update code/pdb_featureVector.py

code/pdb_featureVector.py

@@ -236,15 +236,36 @@ def pdb(input_set, mode, impute):
                 path_pdb = 'out_files/pdb/pdb_structures'
                 st.write('path for pdb: ', path_pdb)
                 file = pdbl.retrieve_pdb_file(search, pdir=path_pdb, file_format="pdb")
+                
                 st.write('file: ', file)
-                existing_pdb = list(Path(path_to_output_files / 'pdb_structures').glob("*"))
                 
+                existing_pdb = list(Path(path_to_output_files / 'pdb_structures').glob("*"))
                 st.write('after download:', existing_pdb)
-                st.write(Path(path_to_output_files / 'pdb_structures') , path_pdb)
                 
                 existing_pdb = list(glob.glob(f"{path_pdb}/*"))
                 st.write('after download 2:', existing_pdb)
 
+                st.write('NEW MWTHID')
+
+
+                
+                                
+                # Define the URL to retrieve the PDB file
+                url = f"https://files.rcsb.org/download/{search}.pdb"
+                
+                # Send an HTTP GET request to the PDB website to download the PDB file
+                response = requests.get(url)
+                
+                # Check if the request was successful
+                if response.status_code == 200:
+                    # Save the PDB file to a local file
+                    with open(f"path_pdb/{search}.pdb", "wb") as f:
+                        f.write(response.content)
+                    st.write(f"PDB file {search}.pdb downloaded successfully.")
+                else:
+                    st.write(f"Failed to retrieve PDB file for {search}.")
+
+    
                 resolution_method = parser.get_structure(search, file)
                 for record in SeqIO.parse(file, "pdb-seqres"):
                     if record.dbxrefs[0].split(':')[0] == 'UNP':
@@ -398,7 +419,8 @@ def pdb(input_set, mode, impute):
         pdb_fasta = None
         pdb_info = None
         pdbs = None
-        existing_pdb = None
+        
+        g_pdb = None
         with_pdb_size = len(with_pdb.drop_duplicates(['datapoint']))
         with_pdb = None