app.py

import streamlit as st
import numpy as np
from Bio.Seq import Seq

def calculate_gc_content(seq):
    gc_count = seq.count('G') + seq.count('C')
    total_count = len(seq)
    return (gc_count / total_count) * 100 if total_count > 0 else 0

def find_potential_regulatory_regions(seq, window_size=50, gc_threshold=60):
    gc_content = []
    for i in range(len(seq) - window_size + 1):
        window = seq[i:i+window_size]
        gc_content.append(calculate_gc_content(window))
    
    regulatory_regions = []
    in_region = False
    start = 0
    for i, gc in enumerate(gc_content):
        if gc > gc_threshold and not in_region:
            in_region = True
            start = i
        elif gc <= gc_threshold and in_region:
            in_region = False
            regulatory_regions.append((start, i + window_size))
    
    if in_region:
        regulatory_regions.append((start, len(seq)))
    
    return regulatory_regions

def analyze_dark_matter(sequence):
    seq = Seq(sequence)
    
    # Basic statistics
    length = len(seq)
    gc_content = calculate_gc_content(seq)
    
    # Look for common regulatory motifs
    tata_box = seq.count("TATAAA")
    caat_box = seq.count("CCAAT")
    
    # Find potential regulatory regions based on GC content
    regulatory_regions = find_potential_regulatory_regions(seq)
    
    return length, gc_content, tata_box, caat_box, regulatory_regions

# Streamlit app
st.title("Genomic Dark Matter Analyzer")

sequence = st.text_area("Paste your DNA sequence here", height=150)

if st.button("Analyze"):
    if sequence:
        length, gc_content, tata_box, caat_box, regulatory_regions = analyze_dark_matter(sequence)
        
        st.write(f"Sequence Length: {length}")
        st.write(f"Overall GC Content: {gc_content:.2f}%")
        st.write(f"TATA Box motifs: {tata_box}")
        st.write(f"CAAT Box motifs: {caat_box}")
        
        st.subheader("Potential Regulatory Regions (based on GC content):")
        for start, end in regulatory_regions:
            st.write(f"Region from base {start} to {end}")
        
        # Visualize the sequence with highlighted regions
        highlighted_seq = list(sequence)
        for start, end in regulatory_regions:
            for i in range(start, min(end, len(highlighted_seq))):
                highlighted_seq[i] = f"<span style='background-color: yellow'>{highlighted_seq[i]}</span>"
        
        st.markdown("".join(highlighted_seq), unsafe_allow_html=True)
    else:
        st.write("Please enter a DNA sequence.")