import streamlit as st
import pandas as pd

st.set_page_config(page_title="Protein Repeat Comparator", layout="centered")
st.title("🧬 Protein Repeat Comparator")
st.write("Upload two Excel files containing protein repeat frequencies. The tool will compare the values and return a sorted Excel file based on frequency differences.")

# File upload
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
        df1 = pd.read_excel(uploaded_file1)
        df2 = pd.read_excel(uploaded_file2)

        # Ensure structure compatibility
        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'))

        # Compute differences
        repeat_cols = common_cols[2:]
        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()

        diff_df = pd.DataFrame(diff_data)
        diff_df["Total Difference"] = diff_df.iloc[:, 2:].sum(axis=1)
        sorted_diff = diff_df.sort_values(by="Total Difference", ascending=False)

        # Save to Excel
        output_file = "protein_repeat_comparison.xlsx"
        sorted_diff.to_excel(output_file, index=False)

        st.success("✅ Comparison complete!")
        with open(output_file, "rb") as f:
            st.download_button(
                label="📥 Download Comparison Excel",
                data=f,
                file_name=output_file,
                mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
            )

    except Exception as e: 
        st.error(f"⚠️ Error: {e}")