Spaces:
Sleeping
Sleeping
| 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 (from 2nd row are frequencies). First column: Protein ID, Second column: Name.") | |
| 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 assuming header is in 2nd row (i.e., row index 1) | |
| df1 = pd.read_excel(uploaded_file1, header=1) | |
| df2 = pd.read_excel(uploaded_file2, header=1) | |
| # Ensure columns are strings | |
| df1.columns = df1.columns.astype(str) | |
| df2.columns = df2.columns.astype(str) | |
| # Get ID and Name columns | |
| id_col = df1.columns[0] | |
| name_col = df1.columns[1] | |
| repeat_cols = df1.columns[2:] # all other columns are repeat names | |
| records = [] | |
| for idx, row1 in df1.iterrows(): | |
| entry_id = row1[id_col] | |
| protein_name = row1[name_col] | |
| # Get matching row from second file | |
| row2_match = df2[(df2[id_col] == entry_id) & (df2[name_col] == protein_name)] | |
| if row2_match.empty: | |
| continue | |
| row2 = row2_match.iloc[0] | |
| for repeat in repeat_cols: | |
| freq1 = row1[repeat] | |
| freq2 = row2[repeat] | |
| if pd.isna(freq1) or pd.isna(freq2): | |
| continue # skip missing values | |
| if freq1 != freq2: | |
| diff = abs(freq1 - freq2) | |
| records.append({ | |
| id_col: entry_id, | |
| name_col: protein_name, | |
| "Repeat": 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 differences are shown below.") | |
| st.download_button( | |
| label="📥 Download Result Excel", | |
| data=output, | |
| file_name="protein_repeat_diff.xlsx", | |
| mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet" | |
| ) | |
| else: | |
| st.info("No differences found between the two files.") | |
| except Exception as e: | |
| st.error(f"⚠️ Error: {e}") |