Update app.py

app.py

@@ -37,13 +37,12 @@ def render_mol(pdb):
 
 # BLAST analysis function
 def perform_blast_analysis(sequence):
-    st.subheader('BLAST Analysis')
+    st.subheader('Protein Analysis')
     with st.spinner("Analyzing generated protein... This may take a few minutes."):
         progress_bar = st.progress(0)
         for i in range(100):
             progress_bar.progress(i + 1)
-            if i == 99:  # Simulate longer process at the end
-                time.sleep(2)
+            time.sleep(0.1)  # Simulate analysis time
         
         try:
             record = SeqRecord(Seq(sequence), id='random_protein')
@@ -51,35 +50,29 @@ def perform_blast_analysis(sequence):
             
             blast_record = NCBIXML.read(result_handle)
             
-            st.write('Top BLAST Match:')
             if blast_record.alignments:
                 alignment = blast_record.alignments[0]  # Get the top hit
-                hsp = alignment.hsps[0]  # Get the first (best) HSP
                 
-                # Extract protein name and organism
-                title_parts = alignment.title.split('|')
-                protein_name = title_parts[-1].strip()
-                organism = title_parts[-2].split('OS=')[-1].split('OX=')[0].strip()
+                # Extract organism
+                organism = alignment.title.split('OS=')[-1].split('OX=')[0].strip()
                 
-                # Calculate identity percentage
-                identity_percentage = (hsp.identities / alignment.length) * 100
+                # Simplify organism name if it's too complex
+                organism = organism.split()[0] if len(organism.split()) > 1 else organism
                 
-                st.write(f"**Protein:** {protein_name}")
-                st.write(f"**Organism:** {organism}")
-                st.write(f"**Sequence Identity:** {identity_percentage:.2f}%")
+                st.write(f"**Estimated Organism:** This protein sequence shares similarities with proteins found in {organism}.")
                 
                 # Fetch protein function (if available)
                 if hasattr(alignment, 'description') and alignment.description:
-                    st.write(f"**Possible Function:** {alignment.description}")
+                    function = alignment.description.split('[')[0].strip()  # Remove organism info in brackets
+                    st.write(f"**Potential Function:** This protein might be involved in {function.lower()}.")
+                else:
+                    st.write("**Potential Function:** Unable to determine a specific function for this protein sequence.")
                 
-                # Link to BLAST
-                blast_link = f"https://blast.ncbi.nlm.nih.gov/Blast.cgi?PROGRAM=blastp&PAGE_TYPE=BlastSearch&LINK_LOC=blasthome"
-                st.markdown(f"[View full BLAST results]({blast_link})")
+                st.markdown("[Learn more about protein functions](https://www.nature.com/scitable/topicpage/protein-function-14123348/)")
             else:
-                st.write("No significant matches found.")
+                st.write("No close matches found. This might be a unique protein sequence!")
         except Exception as e:
-            st.error(f"An error occurred during BLAST analysis: {str(e)}")
-            st.write("Please try again later or contact support if the issue persists.")
+            st.error("An error occurred during protein analysis. Please try again later.")
 
 # ESMfold
 def update(sequence, word1, word2, word3, sequence_length):
@@ -137,14 +130,20 @@ sequence_length = st.sidebar.number_input("Sequence Length", min_value=50, max_v
 if st.sidebar.button('Generate and Predict'):
     if word1 and word2 and word3:
         sequence = generate_sequence_from_words([word1, word2, word3], sequence_length)
+        st.session_state.sequence = sequence  # Store the sequence in session state
         st.sidebar.text_area("Generated Sequence", sequence, height=100)
         st.sidebar.info("Note: The same words and sequence length will always produce the same sequence.")
         
         with st.spinner("Predicting protein structure... This may take a few minutes."):
             update(sequence, word1, word2, word3, sequence_length)
+        
+        # Add Analyze Protein button
+        if st.button('Analyze Protein'):
+            perform_blast_analysis(st.session_state.sequence)
     else:
         st.sidebar.warning("Please enter all three words to generate a sequence.")
 
+
 # Information display
 st.sidebar.markdown("""
 ## What to do next: