Update utils.py

utils.py

@@ -68,6 +68,24 @@ def plot_2d_comparison(dna_sequences_grouped, labels, mapping=mapping_easy):
     ax.legend(by_label.values(), by_label.keys())
     return fig
 
+# Function to plot a comparison of DNA sequences
+def plot_distrobutions(dna_sequences_grouped, labels, basepair, mapping=mapping_easy):
+    fig, ax = plt.subplots()
+    colors = plt.cm.rainbow(np.linspace(0, 1, len(dna_sequences_grouped)))
+    for count, (dna_sequences, color) in enumerate(zip(dna_sequences_grouped, colors)):
+        virus_y = []
+        for dna_sequence in dna_sequences:
+            mapped_coords = _dna_to_coordinates(dna_sequence, mapping)
+            cumulative_coords = _get_cumulative_coords(mapped_coords)
+            y = cumulative_coords[:, 1][basepair]
+            virus_y.append(y)
+        count_bins, bins = np.histogram(virus_y)
+        ax.stairs(count_bins, bins , color= color, label[count])
+    # Only show unique labels in the legend
+    handles, labels = ax.get_legend_handles_labels()
+    by_label = dict(zip(labels, handles))
+    ax.legend(by_label.values(), by_label.keys())
+    return fig
 
 ############################################################# Virus Dataset ########################################################
 #ds = load_dataset('Hack90/virus_tiny')