diff --git a/projet_texte/genome.py b/projet_texte/genome.py
index e308b7336cf23fde3c87e6b4b6eeb30e15d58594..1e5c40c759500bcc1e2c188101b7cefde5b03d7b 100644
--- a/projet_texte/genome.py
+++ b/projet_texte/genome.py
@@ -26,6 +26,7 @@ def create_tree(df):
try:
Path(prefix).mkdir(parents=True, exist_ok=True)
except:
+ print(f"Erreur pour la création du dossier {prefix}")
continue
print("Regroupement des organismes par Kingdom")
@@ -114,7 +115,7 @@ def get_organism_from_subgroup(df, kingdom, group, subgroup):
#print("Regroupement terminé\n")
return result
-def search_nc_by_organism(kingdom, organism_name):
+def search_nc_by_organism(kingdom, organism_name, df_log):
'''
Renvoie tous les NC correspondant à un organisme
@@ -129,9 +130,19 @@ def search_nc_by_organism(kingdom, organism_name):
df = pd.read_csv(path, sep="\t", header=None)
df.columns = ["1", "NC", "3", "4", "5", "Organism", "7"]
df_tmp = df[df['NC'].str.contains('NC_')]
- nc_organism = df_tmp[["NC", "Organism"]]
- result = nc_organism.loc[nc_organism["Organism"] == organism_name, "NC"]
- return result.tolist()
+ nc_organism = df_tmp[["NC", "Organism"]]
+ result = nc_organism[[organism_name in organism for organism in nc_organism['Organism']]]["NC"]
+ #result = nc_organism.loc[nc_organism["Organism"].str.contains(organism_name, regex=False), "NC"]
+ #result = nc_organism.loc[nc_organism["Organism"].str.contains(organism_name), "NC"]
+ df_result = result.to_frame()
+
+ #df_result[~df_result.apply(tuple,1).isin(df_log.apply(tuple,1))]
+ res = pd.concat([df_result, df_log]).drop_duplicates(keep=False)
+ #res = res.reset_index(drop=True)
+ #df_gpby = res.groupby(list(res.columns))
+ #idx = [x[0] for x in df_gpby.groups.values() if len(x) == 1]
+ #res.reindex(idx)
+ return res['NC'].values.tolist()
def has_valid_boundary(a, b, max_length):
if ((not a.isdigit()) or (int(a) > max_length)):
@@ -144,7 +155,7 @@ def has_valid_boundary(a, b, max_length):
return False
return True
-def write_available_feature(record, prefix_path, regions, kingdom):
+def write_available_feature(record, prefix_path, regions, kingdom, name_organism):
'''
Renvoie les régions valides
@@ -155,7 +166,6 @@ def write_available_feature(record, prefix_path, regions, kingdom):
Liste correspondant à l'intersection des listes features et regions
'''
#print(f"Dans {prefix_path}")
- name_organism = record.annotations["organism"]
prefix = f"{prefix_path}{name_organism}"
range_index = ""
region_to_parse = []
@@ -295,8 +305,8 @@ def write_available_feature(record, prefix_path, regions, kingdom):
try:
with open(filename, 'a+') as external_file:
print("Dans",filename)
- print(name_request, file=external_file)
- print(feature.extract(record.seq), file=external_file)
+ #print(name_request, file=external_file)
+ #print(feature.extract(record.seq), file=external_file)
name_request = "intron {} {}: join({})".format(record.annotations["organism"], record.name, range_index)
for i in range(len(reverse_location) - 1):
feature_tmp = SeqFeature(FeatureLocation(reverse_location[i][1], reverse_location[i+1][0], strand=1), type="CDS")
@@ -311,8 +321,8 @@ def write_available_feature(record, prefix_path, regions, kingdom):
try:
with open(filename, 'a+') as external_file:
print("Dans",filename)
- print(name_request, file=external_file)
- print(feature.extract(record.seq), file=external_file)
+ #print(name_request, file=external_file)
+ #print(feature.extract(record.seq), file=external_file)
name_request = "intron {} {}: complement(join({}))".format(record.annotations["organism"], record.name, range_index)
for i in range(len(reverse_location) - 1):
feature_tmp = SeqFeature(FeatureLocation(reverse_location[len(reverse_location)-1-i-1][1], reverse_location[len(reverse_location)-1-i][0], strand=-1), type="CDS")
@@ -404,7 +414,7 @@ def read_log():
df = pd.read_csv(path, sep="\t", header=None)
df.columns = ["NC", "Organism", "Kingdom"]
return df
- return pd.DataFrame()
+ return pd.DataFrame(columns= ["NC", "Organism", "Kingdom"])
def search_last_nc_index(lst_nc, nc):
for i, ncs in enumerate(lst_nc):
diff --git a/projet_texte/interface.py b/projet_texte/interface.py
index b90a2454666fea532ca9c26d8e4e61afe87578a0..7e6e0472080c41f242e2c0f4b07b8baea39e70ad 100644
--- a/projet_texte/interface.py
+++ b/projet_texte/interface.py
@@ -75,7 +75,8 @@ class Redirect():
# --- fonction principale ---
-ctk.set_appearance_mode("System") # Modes: system (default), light, dark
+ctk.set_appearance_mode("dark")
+#ctk.set_appearance_mode("System") # Modes: system (default), light, dark
ctk.set_default_color_theme("blue") # Themes: blue (default), dark-blue, green
class InterfaceManager():
@@ -170,16 +171,17 @@ class InterfaceManager():
# file_image = Image.open("file.png")
# file_image = file_image.resize((16, 16), Image.ANTIALIAS)
# file_image = ImageTk.PhotoImage(file_image)
-
- ###Treeview Customisation (theme colors are selected)
+ ###Treeview Customisation (theme colors are selected)
treestyle = ttk.Style()
treestyle.theme_use('default')
treestyle.configure("Treeview", background="#565B5E",
foreground="#DCE4EE",
fieldbackground="#565B5E",
- borderwidth=0)
+ borderwidth=0,
+ font = 18,
+ rowheight = 28)
treestyle.map('Treeview', background=[('selected', "#1B73C2")],
foreground=[('selected', "#DCE4EE")])
@@ -192,14 +194,13 @@ class InterfaceManager():
self.frame_1.pack_propagate(0)
self.tree = ttk.Treeview(self.frame_1, show="tree")
- self.tree.pack(expand=1, fill="both",side = LEFT)
-
- #self.tree.place(x = 0, y = 270, width=500, height=387)
-
- self.text = ctk.CTkTextbox(self.frame_1)
+ self.tree.pack(expand=1, fill="both",side = LEFT)
+ self.scroll = Scrollbar(self.frame_1)
+ self.scroll.pack(side=RIGHT, fill=Y)
+ self.text = tk.Text(self.frame_1, bg = "white", yscrollcommand=self.scroll.set, font=18)
self.text.pack(expand=1, fill="both", side = RIGHT)
- #self.text.place(x = 500, y = 270)
self.text.bind('<<Modified>>', showEnd)
+ self.scroll.config(command=self.text.yview)
self.old_stdout = sys.stdout
sys.stdout = Redirect(self.text)
self.myvar = StringVar()
@@ -225,18 +226,20 @@ class InterfaceManager():
"Eukaryota.ids",
"Viruses.ids"
]
- self.button = ctk.CTkButton(self.root, text='Téléchargement fichiers', command=self.download_file)
- self.button.invoke()
- self.button.configure(state = DISABLED)
+ self.button = ctk.CTkButton(self.root, text='Démarrer', command=lambda : self.thread_function_parser(self.v, self.EtatCheckButton, self.resultat, self.root, self.button.cget("text")))
self.button.place(x = 580, y = 660)
- self.button.configure
+ self.button.place_forget()
+ self.button2 = ctk.CTkButton(self.root, text='Téléchargement fichiers', command=self.download_file)
+ self.button2.invoke()
+ self.button2.configure(state = DISABLED)
+ self.button2.place(x = 580, y = 660)
self.root.mainloop()
def download_file(self):
self.button.state = "disabled"
t = threading.Thread(target=self.extract_tree)
t.start()
- self.schedule_check(t)
+ #self.schedule_check(t)
def schedule_check(self,t):
self.root.after(1000, self.check_if_done, t)
@@ -280,7 +283,8 @@ class InterfaceManager():
genome.create_tree(self.df)
self.create_tree()
print("Génération de l'arborescence terminée")
- self.button.destroy()
+ self.button2.place_forget()
+ self.button2.destroy()
self.button = ctk.CTkButton(self.root, text='Démarrer', command=lambda : self.thread_function_parser(self.v, self.EtatCheckButton, self.resultat, self.root, self.button.cget("text")))
self.button.place(x = 580, y = 660)
@@ -301,7 +305,7 @@ class InterfaceManager():
def progress_3(self, Progressbar, longueur):
if Progressbar.get() < 1:
- Progressbar.set(Progressbar.get() + longueur)
+ Progressbar.set(longueur)
else:
print("The progress completed!")
@@ -409,7 +413,7 @@ class InterfaceManager():
if(not is_active):
print("Mise en pause de l'acquisition")
- while(self.button.text != "Stop"):
+ while(self.button.cget("text") != "Stop"):
pass
@@ -424,7 +428,7 @@ class InterfaceManager():
#print(dataframe_organism)
if(not is_active):
print("Mise en pause de l'acquisition")
- while(self.button.text != "Stop"):
+ while(self.button.cget("text") != "Stop"):
pass
dataframe_organism = dataframe_organism.sort_values(["Kingdom", "Group", "SubGroup"])
dataframe_organism.reset_index(drop=True, inplace=True)
@@ -442,28 +446,32 @@ class InterfaceManager():
# on recherche les nc par organisme
nc_by_organism = []
+ df_ncs_tmp = pd.DataFrame(columns= ["NC", "Organism", "Kingdom"])
+
for i, organism in enumerate(organism_name):
self.progress_2(self.Progressbar_2, longueur)
if(not is_active):
print("Mise en pause de l'acquisition")
- while(self.button.text != "Stop"):
+ while(self.button.cget("text") != "Stop"):
pass
print(f"Recherche des NC pour l'organisme {organism}")
- ncs = genome.search_nc_by_organism(kingdom_name, organism)
+ if (not df_log.empty):
+ df_ncs_tmp = df_log[[organism in o for o in df_log['Organism']]]["NC"].to_frame()
+ ncs = genome.search_nc_by_organism(kingdom_name, organism, df_ncs_tmp)
if(ncs):
print(f"Regroupement des NC pour l'organisme {organism}\n")
+ nc_by_organism.append([organism, ncs, organism_group[i], organism_subgroup[i]])
else:
- print(f"NC non trouvé pour l'organisme {organism}\n")
+ print(f"NC non trouvé ou déjà acquis pour l'organisme {organism}\n")
- nc_by_organism.append([organism, ncs, organism_group[i], organism_subgroup[i]])
- if (not df_log.empty):
- df_tmp = df_log.loc[df_log["Kingdom"] == kingdom_name]
- if (not df_tmp.empty):
- last_nc = df_tmp.iloc[-1,0]
- last_index = genome.search_last_nc_index(nc_by_organism, last_nc)
- if (last_index != -1):
- nc_by_organism = nc_by_organism[last_index:] + nc_by_organism[:last_index]
+ #if (not df_log.empty):
+ # df_tmp = df_log.loc[df_log["Kingdom"] == kingdom_name]
+ # if (not df_tmp.empty):
+ # last_nc = df_tmp.iloc[-1,0]
+ # last_index = genome.search_last_nc_index(nc_by_organism, last_nc)
+ # if (last_index != -1):
+ # nc_by_organism = nc_by_organism[last_index:] + nc_by_organism[:last_index]
# Pour un NC donné, extraction et écriture des séquences dans les fichiers par régions
# Récupération du gene via id
@@ -471,11 +479,15 @@ class InterfaceManager():
print(f"Fin de la recherche des NC pour {kingdom_name} {group_name} {subgroup_name}".center(80,"-"))
print("\n","Début d'extraction".center(80, "-"))
longueur_2 = len(nc_by_organism)
+ if (longueur_2 == 0):
+ self.progress_3(self.Progressbar_3, 1)
for organism in nc_by_organism:
self.progress_2(self.Progressbar_3, longueur_2)
prefix = "Results/{}/{}/{}/".format(kingdom_name, organism[2], organism[3])
for nc in organism[1]:
- try:
+ if (nc in df_log['NC'].unique()):
+ continue
+ try:
print(f"\nLecture de {nc}")
handle = Entrez.efetch(db="nucleotide",id=nc, rettype="gbwithparts", retmode="text")
record = SeqIO.read(handle, "genbank")
@@ -491,10 +503,11 @@ class InterfaceManager():
else:
if(not is_active):
print("Mise en pause de l'acquisition")
- while(self.button.text != "Stop"):
+ while(self.button.cget("text") != "Stop"):
pass
print(f"Ecriture des régions pour {record.name}")
- genome.write_available_feature(record, prefix, regions, kingdom_name)
+ genome.write_available_feature(record, prefix, regions, kingdom_name, organism[0])
+ df_log.loc[len(df_log)] = [nc, organism[0], kingdom_name]
is_active = False
self.button.configure(text = "Démarrer")
print("\n","Fin d'extraction".center(80, "-"),"\n")