Spaces:
Sleeping
Sleeping
File size: 2,458 Bytes
5cd21b9 b57c1d3 26343ed b57c1d3 5223b02 b57c1d3 5223b02 b533841 5223b02 b533841 5223b02 b533841 5223b02 26343ed 5223b02 26343ed b533841 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 |
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 both Excel files, assuming header is in second row
df1 = pd.read_excel(uploaded_file1, header=1)
df2 = pd.read_excel(uploaded_file2, header=1)
# Automatically detect first two columns
id_col = df1.columns[0]
name_col = df1.columns[1]
repeat_cols = df1.columns[2:]
records = []
for _, row1 in df1.iterrows():
entry_id = row1[id_col]
protein_name = row1[name_col]
# Match in second file
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": repeat,
"Frequency File 1": freq1,
"Frequency File 2": freq2,
"Difference": diff
})
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! Showing only changed repeats.")
st.download_button(
label="📥 Download Changed Repeats Excel",
data=output,
file_name="changed_protein_repeats.xlsx",
mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
)
except Exception as e:
st.error(f"⚠️ Error: {e}") |