Update app.py

app.py

@@ -131,40 +131,53 @@ def visualize_sequence_impacts(sequence, kmers, shap_values, base_prob):
     # Sort by absolute impact
     kmer_impacts.sort(key=lambda x: abs(x[2]), reverse=True)
     
-    # Create the plot
-    fig = plt.figure(figsize=(20, max(10, len(kmer_impacts[:30])*0.3)))
+    # Limit display to top 30 k-mers
+    display_kmers = kmer_impacts[:30]
+    
+    # Calculate figure height based on number of k-mers
+    fig_height = min(20, max(8, len(display_kmers) * 0.4))
+    
+    # Create figure with controlled size
+    fig = plt.figure(figsize=(12, fig_height))
     ax = plt.gca()
     
     # Add title and base value
-    plt.text(0.01, 1.02, f"base value = {base_prob:.3f}", transform=ax.transAxes, fontsize=12)
+    plt.text(0.01, 1.02, f"base value = {base_prob:.3f}", transform=ax.transAxes, fontsize=10)
     
-    # Plot k-mers
-    y_position = 1
-    sequence_length = len(sequence)
+    # Plot k-mers with controlled spacing
+    y_spacing = 0.9 / max(len(display_kmers), 1)
+    y_position = 0.95
+    max_seq_display = 100  # Maximum sequence length to show
     
-    for pos, kmer, impact in kmer_impacts[:30]:  # Show top 30 most impactful k-mers
-        # Show sequence with highlighted k-mer
-        pre_sequence = sequence[:pos]
-        post_sequence = sequence[pos+k:]
+    for pos, kmer, impact in display_kmers:
+        # Truncate sequence display if too long
+        pre_sequence = sequence[max(0, pos-20):pos]
+        post_sequence = sequence[pos+k:min(pos+k+20, len(sequence))]
+        
+        # Add ellipsis if truncated
+        pre_ellipsis = "..." if pos > 20 else ""
+        post_ellipsis = "..." if pos+k+20 < len(sequence) else ""
         
         # Choose color based on impact
-        color = '#ffcccb' if impact > 0 else '#cce0ff'  # Light red or light blue
+        color = '#ffcccb' if impact > 0 else '#cce0ff'
         arrow = '↑' if impact > 0 else '↓'
         
-        # Calculate text positions
-        plt.text(0.01, y_position, pre_sequence, fontsize=10)
-        plt.text(0.01 + len(pre_sequence)/(sequence_length*1.5), y_position, 
-                kmer, fontsize=10, bbox=dict(facecolor=color, alpha=0.3, pad=2))
-        plt.text(0.01 + (len(pre_sequence) + len(kmer))/(sequence_length*1.5), 
-                y_position, post_sequence, fontsize=10)
+        # Draw text elements
+        plt.text(0.01, y_position, f"{pre_ellipsis}{pre_sequence}", fontsize=9)
+        plt.text(0.01 + len(f"{pre_ellipsis}{pre_sequence}")/50, y_position,
+                kmer, fontsize=9, bbox=dict(facecolor=color, alpha=0.3, pad=1))
+        plt.text(0.01 + (len(f"{pre_ellipsis}{pre_sequence}") + len(kmer))/50,
+                y_position, f"{post_sequence}{post_ellipsis}", fontsize=9)
         
         # Add impact value
-        plt.text(0.8, y_position, f"{arrow} {impact:+.3f}", fontsize=10)
+        plt.text(0.8, y_position, f"{arrow} {impact:+.3f}", fontsize=9)
         
-        y_position -= 0.03
+        y_position -= y_spacing
     
     plt.axis('off')
-    plt.tight_layout()
+    
+    # Adjust layout with specific margins
+    plt.subplots_adjust(left=0.05, right=0.95, top=0.95, bottom=0.05)
     return fig
 
 def predict(file_obj, top_kmers=10, fasta_text=""):