Update app.py

app.py

@@ -17,14 +17,12 @@ st.set_page_config(layout='wide')
 st.sidebar.title('🔮 GenPro2 Protein Generator & Structure Predictor')
 st.sidebar.write('GenPro2 is an end-to-end single sequence protein generator and structure predictor based [*ESMFold*](https://esmatlas.com/about) and the ESM-2 language model.')
 
-# Function to generate protein sequence from random words
 def generate_sequence_from_words(words, length):
     seed = ' '.join(words).encode('utf-8')
     random.seed(hashlib.md5(seed).hexdigest())
     amino_acids = "ACDEFGHIKLMNPQRSTVWY"
     return ''.join(random.choice(amino_acids) for _ in range(length))
 
-# stmol
 def render_mol(pdb):
     pdbview = py3Dmol.view()
     pdbview.addModel(pdb,'pdb')
@@ -35,7 +33,6 @@ def render_mol(pdb):
     pdbview.spin(True)
     showmol(pdbview, height = 500,width=800)
 
-# BLAST analysis function
 def perform_blast_analysis(sequence):
     st.subheader('Protein Analysis')
     with st.spinner("Analyzing generated protein... This may take a few minutes."):
@@ -53,17 +50,13 @@ def perform_blast_analysis(sequence):
             if blast_record.alignments:
                 alignment = blast_record.alignments[0]  # Get the top hit
                 
-                # Extract organism
                 organism = alignment.title.split('OS=')[-1].split('OX=')[0].strip()
-                
-                # Simplify organism name if it's too complex
                 organism = organism.split()[0] if len(organism.split()) > 1 else organism
                 
                 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:
-                    function = alignment.description.split('[')[0].strip()  # Remove organism info in brackets
+                    function = alignment.description.split('[')[0].strip()
                     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.")
@@ -74,7 +67,6 @@ def perform_blast_analysis(sequence):
         except Exception as e:
             st.error("An error occurred during protein analysis. Please try again later.")
 
-# ESMfold
 def update(sequence, word1, word2, word3, sequence_length):
     headers = {
         'Content-Type': 'application/x-www-form-urlencoded',
@@ -83,9 +75,9 @@ def update(sequence, word1, word2, word3, sequence_length):
         response = requests.post('https://api.esmatlas.com/foldSequence/v1/pdb/', 
                                  headers=headers, 
                                  data=sequence, 
-                                 verify=False,  # Disable SSL verification
-                                 timeout=300)  # Set a longer timeout
-        response.raise_for_status()  # Raise an exception for bad status codes
+                                 verify=False,
+                                 timeout=300)
+        response.raise_for_status()
         pdb_string = response.content.decode('utf-8')
         
         with open('predicted.pdb', 'w') as f:
@@ -94,11 +86,9 @@ def update(sequence, word1, word2, word3, sequence_length):
         struct = bsio.load_structure('predicted.pdb', extra_fields=["b_factor"])
         b_value = round(struct.b_factor.mean(), 2)
         
-        # Display protein structure
         st.subheader(f'Predicted protein structure using seed: {word1}, {word2}, and {word3} + length {sequence_length}')
         render_mol(pdb_string)
         
-        # plDDT value is stored in the B-factor field
         st.subheader('plDDT Score')
         st.write('plDDT is a per-residue estimate of the confidence in prediction on a scale from 0-100%.')
         st.info(f'Average plDDT: {int(b_value * 100)}%')
@@ -110,48 +100,41 @@ def update(sequence, word1, word2, word3, sequence_length):
             mime='text/plain',
         )
 
-        # Perform BLAST analysis
-        perform_blast_analysis(sequence)
+        st.markdown("""
+        ## What to do next:
+        If you find interesting results from the sequence folding, you can explore further:
+        1. Learn more about protein structures and sequences.
+        2. Visit the [Protein Data Bank (PDB)](https://www.rcsb.org/) for known protein structures.
+        3. Compare your folded structure with known functional proteins by downloading your results.
+        4. Read about similar proteins to gain insights into potential functions.
+        5. Click the "Analyze Protein" button below to get more information about your generated protein.
+
+        **Remember, this folding is based on randomly generated sequences. Interpret the results with caution.
+        Enjoy exploring the world of protein sequences! Share your high-confidence protein images with us on X [*@WandsAI*](https://x.com/wandsai)!
+        """)
+
+        if st.button('Analyze Protein'):
+            perform_blast_analysis(sequence)
+
     except requests.exceptions.RequestException as e:
         st.error(f"An error occurred while calling the API: {str(e)}")
         st.write("Please try again later or contact support if the issue persists.")
 
-# Streamlit app
 st.title("Word-Seeded Protein Sequence Generator and Structure Predictor")
 
-# Input for word-seeded sequence generation
 st.sidebar.subheader("Generate Sequence from Words")
 word1 = st.sidebar.text_input("Word 1")
 word2 = st.sidebar.text_input("Word 2")
 word3 = st.sidebar.text_input("Word 3")
 sequence_length = st.sidebar.number_input("Sequence Length", min_value=50, max_value=400, value=100, step=10)
 
-# Generate and predict button
 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:
-If you find interesting results from the sequence folding, you can explore further:
-1. Learn more about protein structures and sequences.
-2. Visit the [Protein Data Bank (PDB)](https://www.rcsb.org/) for known protein structures.
-3. Compare your folded structure with known functional proteins by downloading your results.
-4. Read about similar proteins to gain insights into potential functions.
-**Remember, this folding is based on randomly generated sequences. Interpret the results with caution.
-Enjoy exploring the world of protein sequences!  Share your high-confidence protein images with us on X [*@WandsAI*](https://x.com/wandsai)!
-""")
+        st.sidebar.warning("Please enter all three words to generate a sequence.")