Update prediction.py

prediction.py

@@ -11,34 +11,35 @@ def predict_sequence_label(sequence):
     Returns:
     int: The predicted label (0 or 1).
     """
+    
     def compute_aac_features(sequence):
-    """
-    Compute the Amino Acid Composition (AAC) features for a given sequence.
+        """
+        Compute the Amino Acid Composition (AAC) features for a given sequence.
 
-    Parameters:
-    sequence (str): A string representing the amino acid sequence.
+        Parameters:
+        sequence (str): A string representing the amino acid sequence.
 
-    Returns:
-    pd.DataFrame: DataFrame containing the AAC features for the sequence.
-    """
-    # Define the 20 standard amino acids
+        Returns:
+        pd.DataFrame: DataFrame containing the AAC features for the sequence.
+        """
+        # Define the 20 standard amino acids
         amino_acids = 'ACDEFGHIKLMNPQRSTVWY'
     
-    # Initialize a dictionary to hold the counts of each amino acid
+        # Initialize a dictionary to hold the counts of each amino acid
         aac_counts = {f"AAC_{aa}": 0 for aa in amino_acids}
     
-    # Calculate the length of the sequence
+        # Calculate the length of the sequence
         seq_length = len(sequence)
     
-    # Count the occurrences of each amino acid in the sequence
+        # Count the occurrences of each amino acid in the sequence
         for aa in sequence:
             if f"AAC_{aa}" in aac_counts:
                 aac_counts[f"AAC_{aa}"] += 1
     
-    # Convert counts to frequencies
+        # Convert counts to frequencies
         aac_features = {aa: count / seq_length for aa, count in aac_counts.items()}
     
-    # Convert the AAC features to a DataFrame
+        # Convert the AAC features to a DataFrame
         aac_features_df = pd.DataFrame([aac_features])
     
         return aac_features_df
@@ -53,3 +54,7 @@ def predict_sequence_label(sequence):
     prediction = saved_model.predict(aac_features_df)
     
     return prediction[0]
+
+# Example usage:
+# sequence = "YOUR_AMINO_ACID_SEQUENCE_HERE"
+# print(predict_sequence_label(sequence))