Update app.py

app.py

@@ -7,58 +7,58 @@ from io import BytesIO
 
 st.set_page_config(page_title="Protein Repeat Comparator", layout="centered")
 st.title("🧬 Protein Repeat Comparator")
-st.write("Upload two Excel files (from 2nd row are frequencies). First column: Protein ID, Second column: Name.")
+st.write("Upload two Excel files with protein data. Frequency values should start from the second row.")
 
 uploaded_file1 = st.file_uploader("Upload First Excel File", type=["xlsx"])
 uploaded_file2 = st.file_uploader("Upload Second Excel File", type=["xlsx"])
 
 if uploaded_file1 and uploaded_file2:
     try:
-        # Read both Excel files assuming header is in 2nd row (i.e., row index 1)
+        # Read files, header starts at second row
         df1 = pd.read_excel(uploaded_file1, header=1)
         df2 = pd.read_excel(uploaded_file2, header=1)
 
-        # Ensure columns are strings
+        # Ensure column names are strings
         df1.columns = df1.columns.astype(str)
         df2.columns = df2.columns.astype(str)
 
         # Get ID and Name columns
         id_col = df1.columns[0]
         name_col = df1.columns[1]
-        repeat_cols = df1.columns[2:]  # all other columns are repeat names
+        repeat_columns = df1.columns[2:]  # Repeat columns start from index 2
 
-        records = []
+        differences = []
 
-        for idx, row1 in df1.iterrows():
+        for _, row1 in df1.iterrows():
             entry_id = row1[id_col]
             protein_name = row1[name_col]
 
-            # Get matching row from second file
             row2_match = df2[(df2[id_col] == entry_id) & (df2[name_col] == protein_name)]
             if row2_match.empty:
                 continue
+
             row2 = row2_match.iloc[0]
 
-            for repeat in repeat_cols:
-                freq1 = row1[repeat]
-                freq2 = row2[repeat]
+            for repeat_col in repeat_columns:
+                freq1 = row1[repeat_col]
+                freq2 = row2[repeat_col]
 
                 if pd.isna(freq1) or pd.isna(freq2):
-                    continue  # skip missing values
+                    continue
 
                 if freq1 != freq2:
                     diff = abs(freq1 - freq2)
-                    records.append({
+                    differences.append({
                         id_col: entry_id,
                         name_col: protein_name,
-                        "Repeat": repeat,
+                        "Repeat": repeat_col,
                         "Frequency File 1": freq1,
                         "Frequency File 2": freq2,
                         "Difference": diff
                     })
 
-        if records:
-            result_df = pd.DataFrame(records)
+        if differences:
+            result_df = pd.DataFrame(differences)
             result_df = result_df.sort_values(by="Difference", ascending=False)
 
             output = BytesIO()
@@ -66,15 +66,15 @@ if uploaded_file1 and uploaded_file2:
                 result_df.to_excel(writer, index=False)
             output.seek(0)
 
-            st.success("✅ Comparison complete! Only differences are shown below.")
+            st.success("✅ Comparison complete. Showing only changed repeats.")
             st.download_button(
-                label="📥 Download Result Excel",
+                label="📥 Download Excel",
                 data=output,
-                file_name="protein_repeat_diff.xlsx",
+                file_name="changed_repeats.xlsx",
                 mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
             )
         else:
-            st.info("No differences found between the two files.")
+            st.info("No changes in repeat frequencies were found.")
 
     except Exception as e:
         st.error(f"⚠️ Error: {e}")