diff --git a/projet_texte/interface.py b/projet_texte/interface.py
index e183995d524b35d846a5e283992591189dd50401..f4c05d8608f94a957758b3f199f4b094a1546e2c 100644
--- a/projet_texte/interface.py
+++ b/projet_texte/interface.py
@@ -16,9 +16,11 @@ from Bio import Entrez
from Bio import SeqIO
import threading
# --- functions ---
+is_active = True
def function_parser(v, EtatCheckButton, resultat, root):
#print(v.get())
+ global is_active
regions = Selection(EtatCheckButton,resultat)
#print(regions)
# p = subprocess.run("ls", shell=True, stdout=subprocess.PIPE)
@@ -56,19 +58,24 @@ def function_parser(v, EtatCheckButton, resultat, root):
"Viruses.ids"
]
- genome.create_log_file()
+ #genome.create_log_file()
print("Début téléchargement des génomes")
genome.download_genome_files(lst_files)
+ if(not is_active):
+ print("Arrêt demandé")
+ sys.exit()
#print("test_1")
if not group_name and not subgroup_name:
organism_by_kingdom = genome.regroup_organism_by_kingdom(lst_files[0],Kingdom)
dataframe_organism = genome.get_dataframe_kingdom(organism_by_kingdom, kingdom_name)
- print("fin du premier if")
elif subgroup_name:
# retourne un dataframe contenant le nom des organismes d'un sous groupe donnée
dataframe_organism = genome.get_organism_from_subgroup(lst_files[0],kingdom_name,group_name,subgroup_name)
#print(dataframe_organism)
+ if(not is_active):
+ print("Arrêt demandé")
+ sys.exit()
dataframe_organism = dataframe_organism.sort_values(["Kingdom", "Group", "SubGroup"])
dataframe_organism.reset_index(drop=True, inplace=True)
print("Téléchargement terminé")
@@ -80,6 +87,9 @@ def function_parser(v, EtatCheckButton, resultat, root):
# on recherche les nc par organisme
nc_by_organism = []
for i, organism in enumerate(organism_name):
+ if(not is_active):
+ print("Arrêt demandé")
+ sys.exit()
print(f"Dans {kingdom_name}/{organism_group[i]}/{organism_subgroup[i]}")
print(f"Regroupement des NC pour l'organisme {organism}")
ncs = genome.search_nc_by_organism(kingdom_name, organism)
@@ -95,6 +105,9 @@ def function_parser(v, EtatCheckButton, resultat, root):
handle.close()
if(len(organism[1]) > 1):
for r in record:
+ if(not is_active):
+ print("Arrêt demandé")
+ sys.exit()
print(f"Ecriture des regions pour {r.name}")
genome.write_available_feature(r.features, r, prefix, regions)
else:
@@ -108,10 +121,6 @@ def function_parser(v, EtatCheckButton, resultat, root):
continue
print("Parsing terminé")
-def thread_function_parser(v, EtatCheckButton, resultat, root):
- t = threading.Thread(target=function_parser, args=(v, EtatCheckButton, resultat, root))
- t.start()
-
def Selection(EtatCheckButton, resultat):
region = []
for i in range (10):
@@ -140,104 +149,121 @@ class Redirect():
# --- fonction principale ---
-def interface_main():
- root = tk.Tk()
-
- f = font.Font(size=18)
- f.configure(underline=True)
-
- g = font.Font(size=32)
-
- h = font.Font(size=24)
-
- root.geometry("1200x800")
- root.title('Projet Bioinformatique SDSC Groupe 1')
- # root.configure(bg='lightblue')
-
- label_1 = Label(root, text="GENOME")
- label_1['font'] = g
- label_1.place(x = 0, y = 0)
-
- label_2 = Label(root, text="Statistiques sur les genes de la base GenBank", fg="blue")
- label_2['font'] = h
- label_2.place(x = 0, y = 35+32)
-
- label = Label(root, text="Sélectionner un Kingdom :")
- label['font'] = f
- label.place(x = 270, y = 120)
-
- v = StringVar()
- v.set("Eukaryota")
-
- R1 = Radiobutton(root, text="Eukaryota", variable=v, value="Eukaryota")
- R1.place(x = 270, y = 150)
-
- R2 = Radiobutton(root, text="Bacteria", variable=v, value="Bacteria")
- R2.place(x = 370, y = 150)
-
- R3 = Radiobutton(root, text="Archaea", variable=v, value="Archaea")
- R3.place(x = 470, y = 150)
-
- R4 = Radiobutton(root, text="Viruses", variable=v, value="Viruses")
- R4.place(x = 570, y = 150)
-
- resultat = ["CDS", "centromere", "intron", "mobile_element", "ncRNA", "rRNA", "telomere", "tRNA", "3'UTR", "5'UTR"]
-
- label = Label(root, text="Les choix des régions fonctionnelles :")
- label['font'] = f
- label.place(x = 270, y = 180)
-
- EtatCheckButton =[0 for i in range (10)]
- for i in range(10) :
- EtatCheckButton[i] = IntVar()
-
- c1 = tk.Checkbutton(root, text="CDS", variable=EtatCheckButton[0], onvalue=1, offvalue=0)
- c1.place(x = 270, y = 210)
- c1.select()
- c2 = tk.Checkbutton(root, text="centromere", variable=EtatCheckButton[1], onvalue=1, offvalue=0)
- c2.place(x = 370, y = 210)
- c2.select()
- c3 = tk.Checkbutton(root, text="intron", variable=EtatCheckButton[2], onvalue=1, offvalue=0)
- c3.place(x = 470, y = 210)
- c3.select()
- c4 = tk.Checkbutton(root, text="mobile_element", variable=EtatCheckButton[3], onvalue=1, offvalue=0)
- c4.place(x = 570, y = 210)
- c4.select()
- c5 = tk.Checkbutton(root, text="ncRNA", variable=EtatCheckButton[4], onvalue=1, offvalue=0)
- c5.place(x = 700, y = 210)
- c5.select()
- c6 = tk.Checkbutton(root, text="rRNA", variable=EtatCheckButton[5], onvalue=1, offvalue=0)
- c6.place(x = 270, y = 230)
- c6.select()
- c7 = tk.Checkbutton(root, text="telomere", variable=EtatCheckButton[6], onvalue=1, offvalue=0)
- c7.place(x = 370, y = 230)
- c7.select()
- c8 = tk.Checkbutton(root, text="tRNA", variable=EtatCheckButton[7], onvalue=1, offvalue=0)
- c8.place(x = 470, y = 230)
- c8.select()
- c9 = tk.Checkbutton(root, text="3'UTR", variable=EtatCheckButton[8], onvalue=1, offvalue=0)
- c9.place(x = 570, y = 230)
- c9.select()
- c10 = tk.Checkbutton(root, text="5'UTR", variable=EtatCheckButton[9], onvalue=1, offvalue=0)
- c10.place(x = 670, y = 230)
- c10.select()
-
- scroll = Scrollbar(root)
- scroll.pack(side=RIGHT, fill=Y)
-
- text = tk.Text(root, bg = "white", width=200, yscrollcommand=scroll.set)
- text.place(x = 0, y = 260)
- text.bind('<<Modified>>', showEnd)
-
- scroll.config(command=text.yview)
-
- old_stdout = sys.stdout
- sys.stdout = Redirect(text)
- button = tk.Button(root, text='Démarrer', command=lambda : thread_function_parser(v, EtatCheckButton, resultat,root))
- button.place(x = 580, y = 700)
-
-
- root.mainloop()
-
+class InterfaceManager():
+
+ def __init__(self) -> None:
+ self.root = tk.Tk()
+ self.f = font.Font(size=18)
+ self.f.configure(underline=True)
+
+ self.g = font.Font(size=30)
+
+ self.h = font.Font(size=20)
+
+ self.root.geometry("1200x800")
+ self.root.title('Projet Bioinformatique SDSC Groupe 1')
+ # root.configure(bg='lightblue')
+
+ self.label_1 = Label(self.root, text="GENOME")
+ self.label_1['font'] = self.g
+ self.label_1.place(x = 0, y = 0)
+
+ self.label_2 = Label(self.root, text="Acquisition des régions fonctionnelles dans les génomes", fg="blue")
+ self.label_2['font'] = self.h
+ self.label_2.place(x = 0, y = 35+32)
+
+ self.label = Label(self.root, text="Sélectionner un Kingdom :")
+ self.label['font'] = self.f
+ self.label.place(x = 270, y = 120)
+
+ self.v = StringVar()
+ self.v.set("Eukaryota")
+
+ self.R1 = Radiobutton(self.root, text="Eukaryota", variable=self.v, value="Eukaryota")
+ self.R1.place(x = 270, y = 150)
+
+ self.R2 = Radiobutton(self.root, text="Bacteria", variable=self.v, value="Bacteria")
+ self.R2.place(x = 370, y = 150)
+ self.R3 = Radiobutton(self.root, text="Archaea", variable=self.v, value="Archaea")
+ self.R3.place(x = 470, y = 150)
+ self.R4 = Radiobutton(self.root, text="Viruses", variable=self.v, value="Viruses")
+ self.R4.place(x = 570, y = 150)
+
+ self.resultat = ["CDS", "centromere", "intron", "mobile_element", "ncRNA", "rRNA", "telomere", "tRNA", "3'UTR", "5'UTR"]
+
+ self.label_3 = Label(self.root, text="Les choix des régions fonctionnelles :")
+ self.label_3['font'] = self.f
+ self.label_3.place(x = 270, y = 180)
+
+ self.EtatCheckButton =[0 for i in range (10)]
+ for i in range(10) :
+ self.EtatCheckButton[i] = IntVar()
+
+ self.c1 = tk.Checkbutton(self.root, text="CDS", variable=self.EtatCheckButton[0], onvalue=1, offvalue=0)
+ self.c1.place(x = 270, y = 210)
+ self.c1.select()
+ self.c2 = tk.Checkbutton(self.root, text="centromere", variable=self.EtatCheckButton[1], onvalue=1, offvalue=0)
+ self.c2.place(x = 370, y = 210)
+ self.c2.select()
+ self.c3 = tk.Checkbutton(self.root, text="intron", variable=self.EtatCheckButton[2], onvalue=1, offvalue=0)
+ self.c3.place(x = 470, y = 210)
+ self.c3.select()
+ self.c4 = tk.Checkbutton(self.root, text="mobile_element", variable=self.EtatCheckButton[3], onvalue=1, offvalue=0)
+ self.c4.place(x = 570, y = 210)
+ self.c4.select()
+ self.c5 = tk.Checkbutton(self.root, text="ncRNA", variable=self.EtatCheckButton[4], onvalue=1, offvalue=0)
+ self.c5.place(x = 700, y = 210)
+ self.c5.select()
+ self.c6 = tk.Checkbutton(self.root, text="rRNA", variable=self.EtatCheckButton[5], onvalue=1, offvalue=0)
+ self.c6.place(x = 270, y = 230)
+ self.c6.select()
+ self.c7 = tk.Checkbutton(self.root, text="telomere", variable=self.EtatCheckButton[6], onvalue=1, offvalue=0)
+ self.c7.place(x = 370, y = 230)
+ self.c7.select()
+ self.c8 = tk.Checkbutton(self.root, text="tRNA", variable=self.EtatCheckButton[7], onvalue=1, offvalue=0)
+ self.c8.place(x = 470, y = 230)
+ self.c8.select()
+ self.c9 = tk.Checkbutton(self.root, text="3'UTR", variable=self.EtatCheckButton[8], onvalue=1, offvalue=0)
+ self.c9.place(x = 570, y = 230)
+ self.c9.select()
+ self.c10 = tk.Checkbutton(self.root, text="5'UTR", variable=self.EtatCheckButton[9], onvalue=1, offvalue=0)
+ self.c10.place(x = 670, y = 230)
+ self.c10.select()
+
+ self.scroll = Scrollbar(self.root)
+ self.scroll.pack(side=RIGHT, fill=Y)
+ self.text = tk.Text(self.root, bg = "white", width=200, yscrollcommand=self.scroll.set)
+ self.text.place(x = 0, y = 260)
+ self.text.bind('<<Modified>>', showEnd)
+ self.scroll.config(command=self.text.yview)
+ self.old_stdout = sys.stdout
+ sys.stdout = Redirect(self.text)
+ self.button = tk.Button(self.root, text='Démarrer', command=lambda : self.thread_function_parser(self.v, self.EtatCheckButton, self.resultat, self.root, self.button['text']))
+ self.button.place(x = 580, y = 700)
+
+
+ self.root.mainloop()
+
+ def thread_function_parser(self, v, EtatCheckButton, resultat, root, text):
+ global is_active
+ if (text == "Stop"):
+ is_active = False
+ self.button['text'] = "En attente"
+ self.button['state'] = DISABLED
+ self.waithere()
+ self.button['text'] = "Démarrer"
+ self.button['state'] = NORMAL
+ else:
+ is_active = True
+ self.text.delete('1.0', END)
+ self.button['text'] = "Stop"
+ t = threading.Thread(target=function_parser, args=(v, EtatCheckButton, resultat, root))
+ t.start()
+
+ def waithere(self):
+ var = IntVar()
+ self.root.after(3000, var.set, 1)
+ print("En attente de terminaison")
+ self.root.wait_variable(var)
# if __name__ == "__main__":
# interface_main()
diff --git a/projet_texte/main.py b/projet_texte/main.py
index c2192ff787553748a3a9ddad5b3df1cea068cf91..521a21bfdf1af4ff06d244b64bc09f590564d695 100644
--- a/projet_texte/main.py
+++ b/projet_texte/main.py
@@ -20,131 +20,4 @@ Entrez.email = "jeanlucphan84@gmail.com"
Entrez.api_key = "81005b6f8a9fdffc555ad15df06c18bcd409"
if __name__ == "__main__":
- #id_test = "NC_037304.1"
- #id_test = "NC_005562.1"
- """
- regions = ["CDS", "centromere", "intron", "mobile_element", "ncRNA", "rRNA", "telomere", "tRNA", "3'UTR", "5'UTR"]
-
- files_names = [
- "eukaryotes.txt",
- "overview.txt",
- "plasmids.txt",
- "prok_reference_genomes.txt",
- "prok_representative_genomes.txt",
- "prokaryotes.txt",
- "viruses.txt"
- ]
-
- ids_file = [
- "Archaea.ids",
- "Bacteria.ids",
- "Eukaryota.ids",
- "Mito_metazoa.ids",
- "Phages.ids",
- "Plasmids.ids",
- "Samples.ids",
- "Viroids.ids",
- "Viruses.ids",
- "dsDNA_Viruses.ids"
- ]
-
- lst_files = [
- "overview.txt",
- "Archaea.ids",
- "Bacteria.ids",
- "Eukaryota.ids",
- "Viruses.ids"
- ]
- """
-
- # ----------- Interface ----------------
-
- interface.interface_main()
-
-
- Kingdom = ["Archaea", "Bacteria", "Eukaryota", "Viruses"]
- regions = ["CDS", "centromere", "intron", "mobile_element", "ncRNA", "rRNA", "telomere", "tRNA", "3'UTR", "5'UTR"]
- # time.sleep(600)
-
- # Sélection du kingdom, group et sous group
- #kingdom_name = Kingdom[2]
- #group_name = "Plants"
- #subgroup_name = "Land Plants"
- #prefix = "Results/{}/{}/{}".format(kingdom_name, group_name, subgroup_name)
-
- # Téléchargment des fichiers se trouvant dans lst_files via ftp
- """
- genome.create_log_file()
- print("Début téléchargement des génomes")
- genome.download_genome_files(lst_files)
- if not group_name and not subgroup_name:
- organism_by_kingdom = genome.regroup_organism_by_kingdom(lst_files[0],Kingdom)
- dataframe_organism = genome.get_dataframe_kingdom(organism_by_kingdom, kingdom_name)
- elif subgroup_name:
- # retourne un dataframe contenant le nom des organismes d'un sous groupe donnée
- dataframe_organism = genome.get_organism_from_subgroup(lst_files[0],kingdom_name,group_name,subgroup_name)
-
- dataframe_organism = dataframe_organism.sort_values(["Kingdom", "Group", "SubGroup"])
- dataframe_organism.reset_index(drop=True, inplace=True)
- print("Téléchargement terminé")
- # df_log = genome.read_log()
- print("Début extraction")
- # if (not df_log.empty):
- # print("Vérification des NC déjà traités")
- # last_organism = df_log.iloc[-1,1]
- # last_nc = df_log.iloc[-1,0]
- # df_last_index = dataframe_organism[dataframe_organism['#Organism/Name'] == last_organism]
- # if(not df_last_index.empty):
- # dataframe_organism.drop(dataframe_organism.index[:df_last_index.index[0]], inplace=True)
- organism_name = dataframe_organism["#Organism/Name"].tolist()
- organism_group = dataframe_organism["Group"].tolist()
- organism_subgroup = dataframe_organism["SubGroup"].tolist()
-
- # on recherche les nc par organisme
- nc_by_organism = []
- nc_to_parse = []
- #nc_to_remove = genome.remove_treated_nc()
- for i, organism in enumerate(organism_name):
- #if ((i >= 1) and (organism_subgroup[i] != organism_subgroup[i-1])):
- print(f"Dans {kingdom_name}/{organism_group[i]}/{organism_subgroup[i]}")
- print(f"Regroupement des NC pour l'organisme {organism}")
- ncs = genome.search_nc_by_organism(kingdom_name, organism)
- #nc_to_parse = [nc for nc in ncs if nc not in nc_to_remove]
- nc_by_organism.append([organism, ncs, organism_group[i], organism_subgroup[i]])
- #nc_to_parse = []
-
- # Pour un NC donné, extraction et écriture des séquences dans les fichiers par régions
- # Récupération du gene via id
- # if (not df_log.empty):
- # last_index = genome.search_last_nc_index(nc_by_organism, last_nc)
- # if (last_index != -1):
- # del nc_by_organism[:last_index]
- # del nc_by_organism[0][1][:nc_by_organism[0][1].index(last_nc)+1]
- print("Début extraction par organisme")
- for organism in nc_by_organism:
- prefix = "Results/{}/{}/{}/".format(kingdom_name, organism[2], organism[3])
- #print(prefix)
- #for nc in organism[1]:
- try:
- handle = Entrez.efetch(db="nucleotide",id=','.join(organism[1]), rettype="gb", retmode="text", style="withparts")
- record = SeqIO.read(handle, "genbank")
- handle.close()
- if(len(organism[1]) > 1):
- for r in record:
- #record = SeqIO.read(handle, "genbank")
- print(f"Ecriture des regions pour {r.name}")
- genome.write_available_feature(r.features, r, prefix, regions)
- else:
- print(f"Ecriture des regions pour {record.name}")
- genome.write_available_feature(record.features, record, prefix, regions)
- except KeyboardInterrupt:
- print("Arret du programme")
- sys.exit()
- except (ValueError, urllib.error.HTTPError):
- #print(f"Lecture du nc {record.name} impossible")
- continue
- #except :
- # print(f"Lecture du nc {nc} impossible")
- # continue
- print("Parsing terminé")
- """
+ app = interface.InterfaceManager()