This script generates box plot for methylation frequency 25% 50% et 75%

boxplot_methylation_frequency.py

+import pandas as pd
+import matplotlib.pyplot as plt
+import numpy as np
+
+# Reading files:
+bed1 = pd.read_csv("C:\\Users\\SCD UM\\Desktop\\methylation_frequency\\MET1_DSP.bed", sep='\t', names=['chro', 'start', 'end', 'freq'])
+bed2 = pd.read_csv("C:\\Users\\SCD UM\\Desktop\\methylation_frequency\\MET1_Tombo.bed", sep='\t', names=['chro', 'start', 'end', 'freq'])
+bed3 = pd.read_csv("C:\\Users\\SCD UM\\Desktop\\methylation_frequency\\MET1_Megalodon_freq_modified.bed", sep='\t', names=['chro', 'start', 'freq'])
+
+# Obtaining frequency data from bed1, bed2, and bed3
+freq1 = bed1["freq"]
+freq2 = bed2["freq"]
+freq3 = bed3["freq"]
+
+# Sorting frequency data
+freq1_sorted = np.sort(freq1)
+freq2_sorted = np.sort(freq2)
+freq3_sorted = np.sort(freq3)
+
+# Calculating quantiles for bed1
+quantile_25_1 = np.percentile(freq1_sorted, 25)
+quantile_50_1 = np.percentile(freq1_sorted, 50)
+quantile_75_1 = np.percentile(freq1_sorted, 75)
+
+# Calculating quantiles for bed2
+quantile_25_2 = np.percentile(freq2_sorted, 25)
+quantile_50_2 = np.percentile(freq2_sorted, 50)
+quantile_75_2 = np.percentile(freq2_sorted, 75)
+
+# Calculating quantiles for bed3
+quantile_25_3 = np.percentile(freq3_sorted, 25)
+quantile_50_3 = np.percentile(freq3_sorted, 50)
+quantile_75_3 = np.percentile(freq3_sorted, 75)
+
+# Slicing data for bed1
+donnees_25_1 = freq1_sorted[:int(len(freq1_sorted) * 0.25)]
+donnees_50_1 = freq1_sorted[int(len(freq1_sorted) * 0.25):int(len(freq1_sorted) * 0.50)]
+donnees_75_1 = freq1_sorted[int(len(freq1_sorted) * 0.50):int(len(freq1_sorted) * 0.75)]
+
+# Slicing data for bed2
+donnees_25_2 = freq2_sorted[:int(len(freq2_sorted) * 0.25)]
+donnees_50_2 = freq2_sorted[int(len(freq2_sorted) * 0.25):int(len(freq2_sorted) * 0.50)]
+donnees_75_2 = freq2_sorted[int(len(freq2_sorted) * 0.50):int(len(freq2_sorted) * 0.75)]
+
+# Slicing data for bed3
+donnees_25_3 = freq3_sorted[:int(len(freq3_sorted) * 0.25)]
+donnees_50_3 = freq3_sorted[int(len(freq3_sorted) * 0.25):int(len(freq3_sorted) * 0.50)]
+donnees_75_3 = freq3_sorted[int(len(freq3_sorted) * 0.50):int(len(freq3_sorted) * 0.75)]
+
+# Creating subplots
+fig, axes = plt.subplots(nrows=1, ncols=3, figsize=(12, 4))
+
+# Color definitions
+color_bed1 = 'lightblue'
+color_bed2 = 'lightgreen'
+color_bed3 = 'red'
+
+# Plotting boxplots for 25%
+boxes_25 = axes[0].boxplot([donnees_25_1, donnees_25_2, donnees_25_3], patch_artist=True, labels=["DeepSignalPlant", "Tombo", "Megalodon"])
+for i, box in enumerate(boxes_25['boxes']):
+    if i == 0:
+        box.set(facecolor=color_bed1)
+    elif i == 1:
+        box.set(facecolor=color_bed2)
+    elif i == 2:
+        box.set(facecolor=color_bed3)
+axes[0].set_title("Faible fréquence de méthylation")
+axes[0].set_ylabel("Fréquence de méthylation ")
+
+# Plotting boxplots for 50%
+boxes_50 = axes[1].boxplot([donnees_50_1, donnees_50_2, donnees_50_3], patch_artist=True, labels=["DeepSignalPlant", "Tombo", "Megalodon"])
+for i, box in enumerate(boxes_50['boxes']):
+    if i == 0:
+        box.set(facecolor=color_bed1)
+    elif i == 1:
+        box.set(facecolor=color_bed2)
+    elif i == 2:
+        box.set(facecolor=color_bed3)
+axes[1].set_title("Moyenne fréquence de méthylation")
+axes[1].set_ylabel("Fréquence de méthylation ")
+
+# Plotting boxplots for 75%
+boxes_75 = axes[2].boxplot([donnees_75_1, donnees_75_2, donnees_75_3], patch_artist=True, labels=["DeepSignalPlant", "Tombo", "Megalodon"])
+for i, box in enumerate(boxes_75['boxes']):
+    if i == 0:
+        box.set(facecolor=color_bed1)
+    elif i == 1:
+        box.set(facecolor=color_bed2)
+    elif i == 2:
+        box.set(facecolor=color_bed3)
+axes[2].set_title("Forte fréquence de méthylation")
+axes[2].set_ylabel("Fréquence de méthylation ")
+
+# Adjusting the layout
+plt.tight_layout()
+
+# Display the plot
+plt.show()