Update ProtHGT_app.py

ProtHGT_app.py

@@ -5,7 +5,7 @@ import streamlit.components.v1 as components
 import pandas as pd
 
 
-with st.spinner("Please wait while we prepare the environment. This may take a few minutes only on the first run..."):
+with st.spinner("Please wait while we prepare the environment. This may take up to 10 minutes on the first run..."):
     # Run setup script if not already executed
     if not os.path.exists(".setup_done"):
         start_time = time.time()
@@ -109,9 +109,10 @@ with st.sidebar:
             protein_list = list(filter(None, protein_list))
             protein_list = list(dict.fromkeys(protein_list))
             
-            # filter out proteins that are not in available_proteins
-            protein_list = [p for p in protein_list if p in available_proteins]
+            # Check for proteins not in available_proteins
             proteins_not_found = [p for p in protein_list if p not in available_proteins]
+            # Filter to keep only available proteins
+            protein_list = [p for p in protein_list if p in available_proteins]
 
             if len(protein_list) > 1000:
                 st.error("Please upload a file with maximum 1000 protein IDs.")
@@ -119,6 +120,7 @@ with st.sidebar:
             else:
                 selected_proteins = protein_list
                 st.write(f"Loaded {len(selected_proteins)} proteins")
+                
                 if proteins_not_found:
                     st.error(f"Proteins not found in input knowledge graph: {', '.join(proteins_not_found)}")
                     st.warning("Currently, our system can generate predictions only for proteins included in our input knowledge graph. Real-time retrieval of relationship data from external source databases is not yet supported. However, we are actively working on integrating this capability in future updates.")