Create app.py

app.py

@@ -0,0 +1,49 @@
+import gradio as gr
+import pandas as pd
+
+def compare_protein_repeat_frequencies(file1, file2):
+    # Load both Excel files
+    df1 = pd.read_excel(file1.name)
+    df2 = pd.read_excel(file2.name)
+
+    # Ensure both have common structure
+    common_cols = df1.columns.intersection(df2.columns)
+    df1 = df1[common_cols]
+    df2 = df2[common_cols]
+
+    # Merge on Entry ID and Protein Name
+    merged = pd.merge(df1, df2, on=["Entry ID", "Protein Name"], suffixes=('_file1', '_file2'))
+
+    # Calculate differences
+    repeat_cols = common_cols[2:]  # exclude ID and Name
+    diff_data = {
+        "Entry ID": merged["Entry ID"],
+        "Protein Name": merged["Protein Name"]
+    }
+
+    for col in repeat_cols:
+        diff_data[col + "_diff"] = (merged[col + "_file1"] - merged[col + "_file2"]).abs()
+
+    # Create DataFrame of differences
+    diff_df = pd.DataFrame(diff_data)
+    diff_df["Total Difference"] = diff_df.iloc[:, 2:].sum(axis=1)
+    diff_df_sorted = diff_df.sort_values(by="Total Difference", ascending=False)
+
+    # Save and return
+    output_path = "comparison_output.xlsx"
+    diff_df_sorted.to_excel(output_path, index=False)
+    return output_path
+
+# Gradio UI
+interface = gr.Interface(
+    fn=compare_protein_repeat_frequencies,
+    inputs=[
+        gr.File(label="Upload First Excel File"),
+        gr.File(label="Upload Second Excel File")
+    ],
+    outputs=gr.File(label="Download Comparison Excel"),
+    title="Protein Repeat Comparator",
+    description="Upload two Excel files containing protein repeat data. The app will compare frequencies and return a sorted Excel file showing differences."
+)
+
+interface.launch()