Update app.py

app.py

@@ -204,6 +204,7 @@ def generate_peptide_for_single_sequence(model, tokenizer, protein_seq, peptide_
         
         # Add the generated binder and its PPL to the results list
         binders_with_ppl_plddt.append([generated_binder, ppl_value, plddt_value, iPTM_value])
+        print("207:binders_with_ppl_plddt: ",binders_with_ppl_plddt)
 
     return binders_with_ppl_plddt
 
@@ -255,10 +256,12 @@ def predict_peptide_from_file(base_model_path, finetuned_model_path, file_obj, p
     for i, row in input.iterrows():
         seq = row['Receptor Sequence']
         binders = generate_peptide_for_single_sequence(loaded_model, tokenizer, seq, peptide_length, top_k, num_binders)
-        for binder, ppl in binders:
-            results.append([seq, binder, ppl, plddt])
-        print("Predicted sample: binder, ppl", i, binder, ppl )
-    results_df = pd.DataFrame(results, columns=['Input Sequence', 'Binder', 'Pseudo Perplexity', 'pLDDT', 'iPTM'])
+        results_i = []
+        for binder, ppl, plddt, iptm in binders:    
+            results.append([seq, binder, ppl, plddt, iptm])
+        #peptide_lp = results_i['Binder'][results_df['PPL'].idxmin()] #Choosing the one with the lowest perplexity  
+        
+    results_df = pd.DataFrame(results, columns=['Input Sequence', 'Binder', 'PPL', 'pLDDT', 'iPTM'])
     
     timestamp = datetime.now().strftime('%Y-%m-%d_%H')
     outpath = (