ça manque l'automatisation

VeennDiagramm_bed_files.py

-####-------- Intersection of bed files --------####
-# Autor: Fadwa EL KHADDAR
-# Lab : DIADE - IRD
-# University : Montpellier - France
-
-####-------- Intersection of bed files --------####
-# Autor: Fadwa EL KHADDAR
-# Lab : DIADE - IRD
-# University : Montpellier - France
-
-import os
-import subprocess
 import pandas as pd
-import matplotlib
 import matplotlib.pyplot as plt
-from matplotlib_venn import venn2_unweighted
-import argparse
-import tkinter as tk
-from matplotlib.backends.backend_tkagg import FigureCanvasTkAgg
-matplotlib.use('TkAgg')
-
-# Arguments
-parser = argparse.ArgumentParser(description="Venn Diagram of gff and bed files")
-parser.add_argument('-bed1', type=str, help="Path to the first bed file")
-parser.add_argument('-bed2', type=str, help="Path to the second bed file")
-args = parser.parse_args()
-
-bed1 = args.bed1
-bed2 = args.bed2
-
-# Extract file names
+from matplotlib_venn import venn2
+import os
+
+# Lecture des données des fichiers BED
+bed1 = "C:\\Users\\SCD UM\\Documents\\UpSetPlot\\BS-seq.bed"
+bed2 = "C:\\Users\\SCD UM\\Documents\\UpSetPlot\\Tombo.bed"
+
 filename1 = os.path.splitext(os.path.basename(bed1))[0]
 filename2 = os.path.splitext(os.path.basename(bed2))[0]
 
-# Intersection of bed files using bedtools
-command2 = subprocess.Popen(f"bedtools intersect -u -a {bed1} -b {bed2}", shell=True, stdout=subprocess.PIPE)
-output, error = command2.communicate()
-results = output.decode('utf-8').strip()
-
-# Create DataFrame
-columns = ["Chro", "Start", "End"]
-rows = [line.split('\t') for line in results.split('\n') if line]
-df = pd.DataFrame(rows, columns=columns)
-
-# Venn Diagram Construction
-count1 = df.shape[0]
-count2 = len(pd.read_csv(bed1, sep='\t'))
-count3 = len(pd.read_csv(bed2, sep='\t'))
-
-subset = (count2, count3, count1)
-venn2_unweighted(subset, set_labels=(filename1, filename2))
-fig, ax = plt.subplots()
-venn2_unweighted(subset, set_labels=(filename1, filename2), ax=ax)
-
-root = tk.Tk()
-root.title("Venn Diagram")
-
-canvas = FigureCanvasTkAgg(fig, master=root)
-canvas.draw()
-canvas.get_tk_widget().pack(side=tk.TOP, fill=tk.BOTH, expand=1)
-root.mainloop()
+bed1_data = pd.read_csv(bed1, sep='\t', names=['Chro', 'Start', 'End'])
+bed2_data = pd.read_csv(bed2, sep='\t', names=['Chro', 'Start', 'End'])
+
+# Conversion des colonnes 'Start' et 'End' en tuples (pour la comparaison)
+bed1_intervals = [(start, end) for start, end in zip(bed1_data['Start'], bed1_data['End'])]
+bed2_intervals = [(start, end) for start, end in zip(bed2_data['Start'], bed2_data['End'])]
+
+# Création des ensembles
+set1 = set(bed1_intervals)
+set2 = set(bed2_intervals)
+
+# Calcul de l'intersection et des ensembles uniques
+intersection = set1 & set2
+unique_set1 = set1 - set2
+unique_set2 = set2 - set1
+
+# Compter les éléments des ensembles
+count1 = len(unique_set1)
+count2 = len(unique_set2)
+count3 = len(intersection)
+
+# Construction du diagramme de Venn
+venn2(subsets=(count1, count2, count3), set_labels=(filename1, filename2))
+plt.title("")
+
+# Afficher le diagramme
+plt.show()