Update app.py

app.py

@@ -59,6 +59,23 @@ import streamlit as st
 from io import BytesIO
 import xlsxwriter
 
+# Function to process the Excel file
+def process_excel(excel_data):
+    # Custom logic to process each sheet within the Excel file
+    homorepeats = set()
+    sequence_data = []
+
+    for sheet_name in excel_data.sheet_names:
+        df = excel_data.parse(sheet_name)
+        for index, row in df.iterrows():
+            entry_id = row['Entry ID']
+            protein_name = row['Protein Name']
+            freq = {repeat: row[repeat] for repeat in df.columns[2:]}  # Assuming repeats start from 3rd column
+            sequence_data.append((entry_id, protein_name, freq))
+            homorepeats.update(freq.keys())
+    
+    return homorepeats, sequence_data
+
 # Function to generate and download Excel workbook with separate sheets for each input file
 def create_excel(sequences_data, homorepeats, filenames):
     output = BytesIO()
@@ -140,19 +157,3 @@ if uploaded_files:
             result_df = pd.DataFrame(rows)
             st.dataframe(result_df)
 
-# Function to process the Excel file
-def process_excel(excel_data):
-    # Custom logic to process each sheet within the Excel file
-    homorepeats = set()
-    sequence_data = []
-
-    for sheet_name in excel_data.sheet_names:
-        df = excel_data.parse(sheet_name)
-        for index, row in df.iterrows():
-            entry_id = row['Entry ID']
-            protein_name = row['Protein Name']
-            freq = {repeat: row[repeat] for repeat in df.columns[2:]}  # Assuming repeats start from 3rd column
-            sequence_data.append((entry_id, protein_name, freq))
-            homorepeats.update(freq.keys())
-    
-    return homorepeats, sequence_data