VennDiagramm

VeennDiagramm_bed_files.py

 
 import os
 import subprocess
-import numpy as np
 import pandas as pd
-import  glob
-import sys
 import matplotlib
 import matplotlib.pyplot as plt
-#from matplotlib_venn import venn3
-import matplotlib.patches as mpatches
+from matplotlib_venn import venn3_unweighted
 import argparse
-import re
-from tkinter import *
+import tkinter as tk
+from matplotlib.backends.backend_tkagg import FigureCanvasTkAgg
 matplotlib.use('TkAgg')
 
+# Arguments
 parser = argparse.ArgumentParser(description="Venn Diagramm 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")
 parser.add_argument('-bed3', type=str, help="Path to the third bed file")
-
 args = parser.parse_args()
 
 bed1 = args.bed1
 bed2 = args.bed2
 bed3 = args.bed3
 
+# Extract file names
+
 filename1 = os.path.splitext(os.path.basename(bed1))[0]
 filename2 = os.path.splitext(os.path.basename(bed2))[0]
 filename3 = os.path.splitext(os.path.basename(bed3))[0]
 
-# Running awk for filtring gff file.
-
-
+# Intersection of bedfile , You have to load bedtools
 
-# Utilisation de la sortie de la première commande comme entrée pour la deuxième commande
 command2 = subprocess.Popen(f"multiIntersectBed -i  {bed1} {bed2} {bed3} ", shell=True, stdout=subprocess.PIPE)
 output, error = command2.communicate()
 results = output.decode('utf-8').strip()
-#print(results)
+
+# Creation of Dataframe
+
 columns = ["Chro", "Start", "End", "nb_overlap_file", "label_overlap_file","None1", "None2", "None3"]
 rows= [line.split('\t') for line in results.split('\n') if line]
 
 raw_dataframe=pd.DataFrame(rows, columns=columns)
-#print(raw_dataframe)
 df= raw_dataframe.loc[:, ["Chro", "Start", "End", "nb_overlap_file", "label_overlap_file"]]
-#print(df)
+
+# Conversion of values
 df['nb_overlap_file'] = df['nb_overlap_file'].astype(int)
 df['label_overlap_file'] = df['label_overlap_file'].astype(str)
-filtre1 = df[df['nb_overlap_file'] == 3]
-count1 = filtre1.shape[0]
-#print(count1)
 
 
-filtre2 = df.loc[(df['nb_overlap_file'] == 2) & (df['label_overlap_file'] == '1,3')]
-#print(len(filtre2))
+# Different filters
 
-filtre3 = df.loc[(df['nb_overlap_file'] == 2) & (df['label_overlap_file'] == '1,2')]
-print(filtre3)
+filtre1 = df[df['nb_overlap_file'] == 3]
+count1 = filtre1.shape[0]
 
-filtre4 = df[(df['nb_overlap_file'] == 1) & (df['label_overlap_file'] == '1')]
-#print(len(filtre4))
 
-filtre5 = df[(df['nb_overlap_file'] == 1) & (df['label_overlap_file'] == '2')]
-print(filtre5)
+filtre2 = df.loc[(df['nb_overlap_file'] == 2) & (df['label_overlap_file'] == '1,3')]
+count2 = filtre2.shape[0]
 
 
-filtre6 = df[(df['nb_overlap_file'] == 1) & (df['label_overlap_file'] == '3')]
-#print(len(filtre6))
+filtre3 = df.loc[(df['nb_overlap_file'] == 2) & (df['label_overlap_file'] == '1,2')]
+count3 = filtre3.shape[0]
 
 
-"""
-# Création de la liste des colonnes pour le DataFrame:
-columns = ["chromosome_f1", "start_f1", "end_f1", "feature", "chromosome_f2", "start_f2", "end_f2", "methylation", "overlap_length"]
+filtre4 = df.loc[(df['nb_overlap_file'] == 2) & (df['label_overlap_file'] == '2,3')]
+count4 = filtre4.shape[0]
 
-# Création de liste de ligne pout le DataFrame:
-rows= [line.split('\t') for line in intersection.split('\n') if line]
 
-#Cette ligne de code divise la chaîne intersection en une liste de listes,
-# où chaque sous-liste représente une ligne du tableau de l'intersection,
-# en filtrant les lignes vides.
+filtre5 = df[(df['nb_overlap_file'] == 1) & (df['label_overlap_file'] == '1')]
+count5=filtre5.shape[0]
 
-dataframe = pd.DataFrame(rows, columns=columns)
-methylated_counts = dataframe.groupby(['start_f1', 'end_f1']).size().reset_index(name='Methylated_cytosine')
 
-## Plotting pie Chart:
+filtre6 = df[(df['nb_overlap_file'] == 1) & (df['label_overlap_file'] == '2')]
+count6 = filtre6.shape[0]
 
-# Proportion de gènes avec et sans méthylation
-num_feature_methylated = len(set(dataframe['start_f1']))
-num_feature_unmethylated = nb_features - num_feature_methylated
 
-# Création de la figure
-fig, ax = plt.subplots(figsize=(6, 6))
+filtre7 = df[(df['nb_overlap_file'] == 1) & (df['label_overlap_file'] == '3')]
+count7 = filtre7.shape[0]
 
-# Données à représenter
-data = [num_feature_methylated, num_feature_unmethylated]
 
-# Labels pour le pie chart
-labels = ['Methylated', 'Unmethylated']
+# Venn Diagramm Construction
 
-# Couleurs pour chaque section du pie chart
-colors = ['#ffc107', '#007bff']
+subset=[count5,count6,count3,count7,count2,count4,count1]
+venn3_unweighted(subset, set_labels=(filename1, filename2,filename3))
+fig, ax = plt.subplots()
+venn3_unweighted(subset, set_labels=(filename1, filename2, filename3), ax=ax)
+fig, ax = plt.subplots()
+venn3_unweighted(subset, set_labels=(filename1, filename2, filename3), ax=ax)
 
-# Création du pie chart
-ax.pie(data, labels=labels, colors=colors, autopct='%1.1f%%', startangle=90)
+root = tk.Tk()
+root.title("Venn Diagram")
 
-# Ajout d'un titre
-ax.set_title(f'Proportion of methylated and unmethylated {feature}')
+canvas = FigureCanvasTkAgg(fig, master=root)
+canvas.draw()
+canvas.get_tk_widget().pack()
 
-# Affichage du graphique
-plt.show()
-"""
+root.mainloop()
\ No newline at end of file