fixed cas9off

app.py

@@ -95,6 +95,7 @@ if selected_model == 'Cas9':
 
         pass
     elif target_selection == 'off-target':
+
         ENTRY_METHODS = dict(
             manual='Manual entry of target sequence',
             txt="txt file upload"
@@ -130,8 +131,18 @@ if selected_model == 'Cas9':
                 )
 
             # prediction button
-            st.button(label='Predict off-target effects', on_click=cas9off.CRISPR_net_predict,
-                      disabled=st.session_state.target_sequence is not None)
+            if st.button('Predict off-target effects'):
+                if st.session_state.entry_method == 'manual':
+                    user_input = st.session_state.manual_entry
+                    predictions = cas9off.process_input_and_predict(user_input, input_type='manual')
+                elif st.session_state.entry_method == 'txt':
+                    uploaded_file = st.session_state.txt_entry
+                    if uploaded_file is not None:
+                        # Read the uploaded file content
+                        file_content = uploaded_file.getvalue().decode("utf-8")
+                        predictions = cas9off.process_input_and_predict(file_content, input_type='manual')
+
+                st.session_state.off_target_results = predictions
             progress = st.empty()
 
             # input error display

cas9off.py

@@ -81,6 +81,44 @@ class Encoder:
             on_off_dim7_codes.append(np.concatenate((diff_code, dir_code)))
         self.on_off_code = np.array(on_off_dim7_codes)
 
+
+def process_input_and_predict(input_data, input_type='manual'):
+    """
+    Process the user input and predict using the CRISPR-Net model.
+
+    Args:
+    input_data: A string of manual input or the path to an input file.
+    input_type: 'manual' for manual input, 'file' for file input.
+
+    Returns:
+    A DataFrame with the off-target predictions.
+    """
+
+    if input_type == 'manual':
+        # Process manual input string into DataFrame
+        sequences = [seq.split(',') for seq in input_data.split('\n')]
+        inputs = pd.DataFrame(sequences, columns=['on_seq', 'off_seq'])
+    elif input_type == 'file':
+        # Read sequences from a file into DataFrame
+        inputs = pd.read_csv(input_data, delimiter=",", header=None, names=['on_seq', 'off_seq'])
+
+    # Encode the sequences
+    input_codes = []
+    for idx, row in inputs.iterrows():
+        on_seq = row['on_seq']
+        off_seq = row['off_seq']
+        en = Encoder(on_seq=on_seq, off_seq=off_seq)
+        input_codes.append(en.on_off_code)
+
+    # Convert to numpy array and reshape for the model
+    input_codes = np.array(input_codes)
+    input_codes = input_codes.reshape((len(input_codes), 1, 24, 7))
+
+    # Predict with CRISPR-Net model
+    inputs['CRISPR_Net_score'] = CRISPR_net_predict(input_codes)
+
+    return inputs
+
 def encode_on_off_seq_pairs(input_file):
     inputs = pd.read_csv(input_file, delimiter=",", header=None, names=['on_seq', 'off_seq'])
     input_codes = []