Update app.py

app.py

@@ -328,32 +328,70 @@ def compute_shap_difference(shap1_norm, shap2_norm):
     """Compute the SHAP difference between normalized sequences"""
     return shap2_norm - shap1_norm
 
-def plot_comparative_heatmap(shap_diff, title="SHAP Difference Heatmap"):
+def plot_comparative_heatmap(shap_diff, seq1_length, seq2_length, title="SHAP Difference Heatmap"):
     """
-    Plot heatmap using relative positions (0-100%)
+    Plot heatmap using both relative positions (0-100%) and actual sequence positions
+    
+    Parameters:
+        shap_diff: numpy array of SHAP differences
+        seq1_length: length of sequence 1
+        seq2_length: length of sequence 2
+        title: plot title
     """
     heatmap_data = shap_diff.reshape(1, -1)
     extent = max(abs(np.min(shap_diff)), abs(np.max(shap_diff)))
     
-    fig, ax = plt.subplots(figsize=(12, 1.8))
+    # Create figure with additional space for the second x-axis
+    fig, ax = plt.subplots(figsize=(12, 2.4))
+    
+    # Plot main heatmap
     cmap = get_zero_centered_cmap()
     cax = ax.imshow(heatmap_data, aspect='auto', cmap=cmap, vmin=-extent, vmax=extent)
     
-    # Create percentage-based x-axis ticks
+    # Create percentage-based x-axis ticks (top)
     num_ticks = 5
     tick_positions = np.linspace(0, shap_diff.shape[0]-1, num_ticks)
     tick_labels = [f"{int(x*100)}%" for x in np.linspace(0, 1, num_ticks)]
     ax.set_xticks(tick_positions)
     ax.set_xticklabels(tick_labels)
     
+    # Create second x-axis for actual positions (bottom)
+    ax2 = ax.twiny()
+    ax2.set_xlim(ax.get_xlim())
+    
+    # Calculate actual positions for both sequences
+    seq1_positions = np.linspace(0, seq1_length, num_ticks)
+    seq2_positions = np.linspace(0, seq2_length, num_ticks)
+    
+    # Format position labels with appropriate scaling
+    def format_position(x):
+        if x >= 1e6:
+            return f"{x/1e6:.1f}M"
+        elif x >= 1e3:
+            return f"{x/1e3:.0f}K"
+        else:
+            return f"{int(x)}"
+    
+    seq1_labels = [format_position(x) for x in seq1_positions]
+    seq2_labels = [format_position(x) for x in seq2_positions]
+    
+    # Set positions for bottom axis
+    ax2.set_xticks(tick_positions)
+    ax2.set_xticklabels([f"S1: {s1}\nS2: {s2}" for s1, s2 in zip(seq1_labels, seq2_labels)])
+    
+    # Add colorbar
     cbar = plt.colorbar(cax, orientation='horizontal', pad=0.25, aspect=40, shrink=0.8)
     cbar.ax.tick_params(labelsize=8)
     cbar.set_label('SHAP Difference (Seq2 - Seq1)', fontsize=9, labelpad=5)
     
+    # Adjust labels and layout
     ax.set_yticks([])
-    ax.set_xlabel('Relative Position in Sequence', fontsize=10)
+    ax.set_xlabel('Relative Position (%)', fontsize=10)
+    ax2.set_xlabel('Sequence Positions', fontsize=10)
     ax.set_title(title, pad=10)
-    plt.subplots_adjust(bottom=0.25, left=0.05, right=0.95)
+    
+    # Adjust layout to prevent label overlap
+    plt.subplots_adjust(bottom=0.35, left=0.05, right=0.95, top=0.85)
     
     return fig