Update app.py

app.py

@@ -6,6 +6,10 @@ import biotite.structure.io as bsio
 import random
 import hashlib
 import urllib3
+from Bio.Blast import NCBIWWW, NCBIXML
+from Bio.Seq import Seq
+from Bio.SeqRecord import SeqRecord
+import time
 
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
@@ -31,6 +35,52 @@ def render_mol(pdb):
     pdbview.spin(True)
     showmol(pdbview, height = 500,width=800)
 
+# BLAST analysis function
+def perform_blast_analysis(sequence):
+    st.subheader('BLAST 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)
+        
+        try:
+            record = SeqRecord(Seq(sequence), id='random_protein')
+            result_handle = NCBIWWW.qblast("blastp", "swissprot", record.seq)
+            
+            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()
+                
+                # Calculate identity percentage
+                identity_percentage = (hsp.identities / alignment.length) * 100
+                
+                st.write(f"**Protein:** {protein_name}")
+                st.write(f"**Organism:** {organism}")
+                st.write(f"**Sequence Identity:** {identity_percentage:.2f}%")
+                
+                # Fetch protein function (if available)
+                if hasattr(alignment, 'description') and alignment.description:
+                    st.write(f"**Possible Function:** {alignment.description}")
+                
+                # 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})")
+            else:
+                st.write("No significant matches found.")
+        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.")
+
 # ESMfold
 def update(sequence, word1, word2, word3, sequence_length):
     headers = {
@@ -66,6 +116,9 @@ def update(sequence, word1, word2, word3, sequence_length):
             file_name='predicted.pdb',
             mime='text/plain',
         )
+
+        # Perform BLAST analysis
+        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.")
@@ -100,8 +153,6 @@ If you find interesting results from the sequence folding, you can explore furth
 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)!
 """)