import streamlit as st

# Function to find matches between reference and query sequences
def find_matches(reference, query):
    matches = ""
    for ref_char, query_char in zip(reference, query):
        if ref_char == query_char:
            matches += ref_char.upper()
        else:
            matches += "-"
    match_percentage = (matches.count("-") / len(reference)) if len(reference) else 0
    return matches, round((1 - match_percentage) * 100, 2)

# Streamlit app
st.title("DNA Sequence Matching 🧬")
st.subheader("Analyze the similarity between two DNA sequences")

# Input fields for sequences
reference = st.text_area(
    "Enter Reference DNA Sequence:",
    placeholder="e.g., ACTGACTGACTG"
).strip().upper()

query = st.text_area(
    "Enter Query DNA Sequence:",
    placeholder="e.g., ACTGTTTGACTG"
).strip().upper()

# Validate input
if st.button("Match DNA Sequences"):
    if not reference or not query:
        st.error("Please provide both Reference and Query DNA sequences.")
    elif len(reference) != len(query):
        st.error("The Reference and Query sequences must have the same length.")
    else:
        # Find matches and calculate percentage
        matches, percentage = find_matches(reference, query)

        # Display results
        st.write("**Reference Sequence:**")
        st.code(reference)
        st.write("**Query Sequence:**")
        st.code(query)
        st.write("**Matching Sequence:**")
        st.code(matches)
        st.success(f"Match Percentage: {percentage}%")

st.write("Note: Sequences must be of the same length for accurate matching.")