Updated

.ipynb_checkpoints/app-checkpoint.py

@@ -182,16 +182,6 @@ def generate_results_text(pdb_id, segment, residues_by_bracket, protein_residues
     return result_str
 
 
-def predict_utils(sequence):
-    input_ids = tokenizer(" ".join(sequence), return_tensors="pt").input_ids.to(device)
-    with torch.no_grad():
-        outputs = model(input_ids).logits.detach().cpu().numpy().squeeze()
-
-    # Calculate scores and normalize them
-    raw_scores = expit(outputs[:, 1] - outputs[:, 0])
-    normalized_scores = normalize_scores(raw_scores)
-
-    return raw_scores,normalized_scores
 
 
 def process_pdb(pdb_id_or_file, segment, score_type='normalized'):
@@ -632,6 +622,17 @@ with gr.Blocks(css="""
         outputs=[predictions_output, molecule_output, download_output]
     )
 
+    def predict_utils(sequence):
+        input_ids = tokenizer(" ".join(sequence), return_tensors="pt").input_ids.to(device)
+        with torch.no_grad():
+            outputs = model(input_ids).logits.detach().cpu().numpy().squeeze()
+    
+        # Calculate scores and normalize them
+        raw_scores = expit(outputs[:, 1] - outputs[:, 0])
+        normalized_scores = normalize_scores(raw_scores)
+    
+        return raw_scores,normalized_scores
+
     #gr.Interface(
     #fn=predict_utils,
     #inputs=gr.Textbox(),

app.py

@@ -182,16 +182,6 @@ def generate_results_text(pdb_id, segment, residues_by_bracket, protein_residues
     return result_str
 
 
-def predict_utils(sequence):
-    input_ids = tokenizer(" ".join(sequence), return_tensors="pt").input_ids.to(device)
-    with torch.no_grad():
-        outputs = model(input_ids).logits.detach().cpu().numpy().squeeze()
-
-    # Calculate scores and normalize them
-    raw_scores = expit(outputs[:, 1] - outputs[:, 0])
-    normalized_scores = normalize_scores(raw_scores)
-
-    return raw_scores,normalized_scores
 
 
 def process_pdb(pdb_id_or_file, segment, score_type='normalized'):
@@ -632,6 +622,17 @@ with gr.Blocks(css="""
         outputs=[predictions_output, molecule_output, download_output]
     )
 
+    def predict_utils(sequence):
+        input_ids = tokenizer(" ".join(sequence), return_tensors="pt").input_ids.to(device)
+        with torch.no_grad():
+            outputs = model(input_ids).logits.detach().cpu().numpy().squeeze()
+    
+        # Calculate scores and normalize them
+        raw_scores = expit(outputs[:, 1] - outputs[:, 0])
+        normalized_scores = normalize_scores(raw_scores)
+    
+        return raw_scores,normalized_scores
+
     #gr.Interface(
     #fn=predict_utils,
     #inputs=gr.Textbox(),