Update app.py

app.py

@@ -67,6 +67,15 @@ mutation_site_headers = [
     4510, 4561, 4615, 4668, 4720, 4773, 4828, 4882
 ]
 
+# Built-in thresholds
+built_in_thresholds = {
+    3244: 0.5, 3297: 0.5, 3350: 0.5, 3399: 0.5, 3455: 0.5, 3509: 0.5, 3562: 0.5, 3614: 0.5,
+    3665: 0.5, 3720: 0.5, 3773: 0.5, 3824: 0.5, 3879: 0.5, 3933: 0.5, 3985: 0.5, 4039: 0.5,
+    4089: 0.5, 4145: 0.5, 4190: 0.5, 4245: 0.5, 4298: 0.5, 4349: 0.5, 4402: 0.5, 4455: 0.5,
+    4510: 0.5, 4561: 0.5, 4615: 0.5, 4668: 0.5, 4720: 0.5, 4773: 0.5, 4828: 0.5, 4882: 0.5
+}
+thresholds = pd.Series(built_in_thresholds)
+
 st.title("ASCII & Binary Label Converter")
 
 # Create tabs
@@ -157,32 +166,27 @@ with tab2:
 
 with tab3:
     st.write("Upload an Editing Frequency CSV or fill in manually:")
-    threshold_file = st.file_uploader("Upload Column Threshold CSV", type=["csv"], key="threshold")
     ef_file = st.file_uploader("Upload Editing Frequency CSV", type=["csv"], key="ef")
 
-    if threshold_file:
-        thresholds_df = pd.read_csv(threshold_file, index_col=0)
-        thresholds = thresholds_df.squeeze()
-
     if ef_file:
         ef_df = pd.read_csv(ef_file)
     else:
-        ef_df = pd.DataFrame(columns=thresholds.index if threshold_file else [])
+        ef_df = pd.DataFrame(columns=thresholds.index)
 
     edited_df = st.data_editor(ef_df, num_rows="dynamic")
 
     if st.button("Convert to Binary Labels"):
-        if threshold_file:
-            binary_df = edited_df.ge(thresholds).astype(int)
-            st.subheader("Binary Labels")
-            st.dataframe(binary_df)
-            st.download_button(
-                label="Download Binary Labels Table as CSV",
-                data=binary_df.to_csv(index=False),
-                file_name="ef_binary_labels_table.csv",
-                mime="text/csv"
-            )
-        else:
-            st.error("Please upload the threshold CSV file first.")
-
-# Future: integrate DNA editor mapping for each mutation site here
+        common_cols = list(set(edited_df.columns) & set(thresholds.index))
+        binary_part = edited_df[common_cols].ge(thresholds[common_cols]).astype(int)
+        non_binary_part = edited_df.drop(columns=common_cols, errors='ignore')
+        binary_df = pd.concat([non_binary_part, binary_part], axis=1)
+        st.subheader("Binary Labels")
+        st.dataframe(binary_df)
+        st.download_button(
+            label="Download Binary Labels Table as CSV",
+            data=binary_df.to_csv(index=False),
+            file_name="ef_binary_labels_table.csv",
+            mime="text/csv"
+        )
+
+# Future: integrate DNA editor mapping for each mutation site here