Update app.py

app.py

@@ -146,7 +146,7 @@ def compute_pseudo_perplexity(model, tokenizer, protein_seq, binder_seq):
 
     end = time.time()
     elapsed = end - start
-    print(f'compute_pseudo_perplexity time: {elapsed:.4f} seconds')
+    #print(f'compute_pseudo_perplexity time: {elapsed:.4f} seconds')
     
     return pseudo_perplexity
 
@@ -173,9 +173,9 @@ def compute_plddt_iptm(protein_seq, binder_seq):
     
     end = time.time()
     elapsed = end - start
-    print(f'compute_plddt_iptm time: {elapsed:.4f} seconds')
+    #print(f'compute_plddt_iptm time: {elapsed:.4f} seconds')
     
-    return avg_plddt, iPTM
+    return avg_plddt, ptm
     
 def generate_peptide_for_single_sequence(model, tokenizer, protein_seq, peptide_length = 15, top_k = 3, num_binders = 5):
     start = time.time()
@@ -219,7 +219,7 @@ def generate_peptide_for_single_sequence(model, tokenizer, protein_seq, peptide_
 
     end = time.time()
     elapsed = end - start
-    print(f'generate_peptide_for_single_sequence: {elapsed:.4f} seconds')
+    #print(f'generate_peptide_for_single_sequence: {elapsed:.4f} seconds')
     
     return binders_with_ppl_plddt
 
@@ -269,8 +269,10 @@ def predict_peptide_from_file(base_model_path, finetuned_model_path, file_obj, m
     results = []
     
     for i, row in input.iterrows():
-        protein_seq = row['Receptor Sequence']
-        peptide_seq = row['Peptide Sequence']
+        #protein_seq = row['Receptor Sequence']
+        #peptide_seq = row['Peptide Sequence']
+        protein_seq = row['P_Sequence']
+        peptide_seq = row['p_Sequence']
         peptide_length = min([len(peptide_seq), max_peptide_length])  # use the same length of ground truth peptide length for prediction limited to max_peptide_length
 
         #get metrics for ground truth peptide