Update app.py

app.py

@@ -236,6 +236,30 @@ if app_choice == "🔁 Protein Repeat Finder":
                 rows.append(row)
         result_df = pd.DataFrame(rows)
         st.dataframe(result_df)
+        
+    if st.checkbox("Repeat Cluster Visualization"):
+    repeat_counts = defaultdict(int)
+    for seq_data in st.session_state.all_sequences_data:
+        for _, _, freq_dict in seq_data:
+            for repeat, count in freq_dict.items():
+                repeat_counts[repeat] += count
+
+    if repeat_counts:
+        sorted_repeats = sorted(repeat_counts.items(), key=lambda x: x[1], reverse=True)
+        top_n = st.slider("Select number of top repeats to visualize", min_value=5, max_value=50, value=20)
+        top_repeats = sorted_repeats[:top_n]
+        repeats, counts = zip(*top_repeats)
+
+        plt.figure(figsize=(12, 6))
+        sns.barplot(x=list(repeats), y=list(counts), palette="viridis")
+        plt.xticks(rotation=45, ha='right')
+        plt.xlabel("Repeats")
+        plt.ylabel("Total Frequency")
+        plt.title("Top Repeat Clusters Across All Sequences")
+        st.pyplot(plt.gcf())
+    else:
+        st.warning("No repeat data available to visualize. Please upload files first.")
+
 
 elif app_choice == "📊 Protein Comparator":
     st.write("Upload two Excel files with protein data to compare repeat frequencies.")