Update app.py

app.py

@@ -1,6 +1,6 @@
 import streamlit as st
 import numpy as np
-from Bio.SeqUtils import GC
+from Bio.Seq import Seq
 from hmmlearn import hmm
 
 # Function to encode DNA sequence
@@ -8,6 +8,12 @@ def encode_sequence(seq):
     encoding = {'A': 0, 'C': 1, 'G': 2, 'T': 3}
     return np.array([encoding[base] for base in seq if base in encoding])
 
+# Function to calculate GC content
+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
+
 # Simple HMM model (this is a placeholder and would need proper training)
 model = hmm.MultinomialHMM(n_components=2, random_state=42)
 model.startprob_ = np.array([0.5, 0.5])
@@ -21,7 +27,7 @@ def analyze_dark_matter(sequence):
     
     # Basic statistics
     length = len(seq)
-    gc_content = GC(seq)
+    gc_content = calculate_gc_content(seq)
     
     # Look for common regulatory motifs
     tata_box = seq.count("TATAAA")