app.py

import os
os.system("pip install streamlit pandas xlsxwriter openpyxl")

import streamlit as st
import pandas as pd
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. Only changed repeat frequencies will be shown in the result.")

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 Excel files (header starts from second row)
        df1 = pd.read_excel(uploaded_file1, header=1)
        df2 = pd.read_excel(uploaded_file2, header=1)

        # Automatically get ID and Name column
        id_col = df1.columns[0]
        name_col = df1.columns[1]
        repeat_cols = df1.columns[2:]

        # Ensure all column names are strings
        repeat_cols = [str(col) for col in repeat_cols]

        records = []

        for _, row1 in df1.iterrows():
            entry_id = row1[id_col]
            protein_name = row1[name_col]

            match = df2[(df2[id_col] == entry_id) & (df2[name_col] == protein_name)]
            if match.empty:
                continue
            row2 = match.iloc[0]

            for repeat in repeat_cols:
                freq1 = row1[repeat]
                freq2 = row2[repeat]
                if freq1 != freq2:
                    diff = abs(freq1 - freq2)
                    records.append({
                        id_col: entry_id,
                        name_col: protein_name,
                        "Repeat": str(repeat),
                        "Frequency File 1": freq1,
                        "Frequency File 2": freq2,
                        "Difference": diff
                    })

        if records:
            result_df = pd.DataFrame(records)
            result_df = result_df.sort_values(by="Difference", ascending=False)

            output = BytesIO()
            with pd.ExcelWriter(output, engine="openpyxl") as writer:
                result_df.to_excel(writer, index=False)
            output.seek(0)

            st.success("✅ Comparison complete! Only changed repeats are included.")
            st.download_button(
                label="📥 Download Changed Repeats Excel",
                data=output,
                file_name="changed_protein_repeats.xlsx",
                mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
            )
        else:
            st.info("No changes in repeat frequencies were found.")

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