Update app.py

app.py

@@ -111,6 +111,7 @@ def predict(file_obj):
     
     try:
         sequences = parse_fasta(text)
+        # For simplicity, process only the first sequence for plotting
         header, seq = sequences[0]
         
         raw_freq_vector = sequence_to_kmer_vector(seq)
@@ -149,10 +150,10 @@ def predict(file_obj):
         top_features.append("Others")
         top_values.append(others_sum)
         
-        # Set base_values and expected_value to 0.5 for the binary classification baseline
+        # Set base_values and expected_value to 0 for the binary classification starting point
         explanation = shap.Explanation(
             values=np.array(top_values),
-            base_values=0.5,  
+            base_values=0.0,  
             data=np.array([
                 raw_freq_vector[kmer_dict[feat]] if feat != "Others" 
                 else np.sum(raw_freq_vector[others_mask]) 
@@ -160,7 +161,7 @@ def predict(file_obj):
             ]),
             feature_names=top_features
         )
-        explanation.expected_value = 0.5
+        explanation.expected_value = 0.0
         
         fig = shap.plots._waterfall.waterfall_legacy(explanation, show=False)
         
@@ -202,3 +203,4 @@ iface = gr.Interface(
 
 if __name__ == "__main__":
     iface.launch(share=True)
+