Update app.py

app.py

@@ -6,7 +6,7 @@ from hmmlearn import hmm
 # Function to encode DNA sequence
 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])
+    return np.array([encoding.get(base.upper(), -1) for base in seq])
 
 # Function to calculate GC content
 def calculate_gc_content(seq):
@@ -35,7 +35,11 @@ def analyze_dark_matter(sequence):
     
     # HMM analysis
     encoded_seq = encode_sequence(str(seq))
-    logprob, hidden_states = model.decode(encoded_seq.reshape(-1, 1))
+    valid_indices = encoded_seq != -1
+    if np.any(valid_indices):
+        logprob, hidden_states = model.decode(encoded_seq[valid_indices].reshape(-1, 1))
+    else:
+        hidden_states = []
     
     regulatory_regions = []
     current_start = None