diff --git a/tool_of_mapping_results_treatments.py b/tool_of_mapping_results_treatments.py
index 970a91c1ed52ae1417d2a9e881bed590ab8576d8..390541df7f4ba07e93f24f3731087a2a1e6dfa6c 100644
--- a/tool_of_mapping_results_treatments.py
+++ b/tool_of_mapping_results_treatments.py
@@ -6,20 +6,27 @@
# On part donc d'un tableur récapitulatif présentant en premiére ligne le nom des différents pathways retenues aprés filtrage par p-value inférieur à 0.05. Sur chaque colonne le nom des différents métabolites mapper dans cette voie.
# L'objectifs est de furnir un récapitulatifs des données présentants dans un premier temps dans combien de voies différentes un même métabolites à mapper puis dans un seccond temps un le pourcentage de recouvrement entre 2 voie métaboliques différentes.
-
-
+### Importing libraries
from random import randint
import numpy as np
import csv
+### Variables
+
+Pathways_a_enlever=['Metabolic pathways','Biosynthesis of secondary metabolites','Microbial metabolism in diverse environments','Carbon metabolism''2-Oxocarboxylic acid metabolism','Fatty acid metabolism','Biosynthesis of amino acids','Nucleotide metabolism','Biosynthesis of nucleotide sugars','Biosynthesis of cofactors','Degradation of aromatic compounds','Carbohydrate metabolism','Energy metabolism','Lipid metabolism','Nucleotide metabolism','Amino acid metabolism','Metabolism of other amino acids','Glycan biosynthesis and metabolism','Metabolism of cofactors and vitamins','Metabolism of terpenoids and polyketides','Biosynthesis of other secondary metabolites','Xenobiotics biodegradation and metabolism','Chemical structure transformation maps','Genetic Information Processing','Transcription','Translation','Folding, sorting and degradation','Replication and repair','Information processing in viruses','Environmental Information Processing','Membrane transport','Signal transduction','Signaling molecules and interaction','Cellular Processes','Transport and catabolism','Cell growth and death','Cellular community - eukaryotes','Cellular community - prokaryotes','Cell motility','Immune system','Organismal Systems','Endocrine system','Circulatory system','Digestive system','Excretory system','Nervous system','Sensory system','Development and regeneration','Aging','Environmental adaptation','Human Diseases','Cancer: overview''Cancer: specific types','Infectious disease: viral','Infectious disease: bacterial','Infectious disease: parasitic','Immune disease','Neurodegenerative disease','Substance dependence','Cardiovascular disease','Endocrine and metabolic disease','Drug resistance: antimicrobial','Drug resistance: antineoplastic','Drug Development','Chronology: Antiinfectives','Chronology: Antineoplastics','Chronology: Nervous system agents','Chronology: Other drugs','Target-based classification: G protein-coupled receptors','Target-based classification: Nuclear receptors','Target-based classification: Ion channels','Target-based classification: Transporters','Target-based classification: Enzymes','Structure-based classification','Skeleton-based classification']
+Fichier_a_traiter="fichier_test_programme_automatisation.csv"
+Sortie_Resemblance_des_pathways="table_de_resemblance_fichier_test_programme_automatisation.csv"
+Sortie_fréquence_des_metabolites="frequence_des_metabolites_fichier_test_programme_automatisation.csv"
+Sortie_pathways_de_chaque_metabolites="Metabolites_et_leurs_pathways_fichier_test_programme_automatisation.csv"
+### Function initialization
-def colonne(file, n, sep=";"):
+def colonne(file, n, sep=";"): # fill opening and recovery
with open(file,"r") as f:
r=csv.reader(f, delimiter = sep)
- lignes=list(r) # variable interne non utilisable
+ lignes=list(r)
res=[]
if (n < len(lignes[0])) and (n >= -len(lignes[0])):
for l in lignes :
@@ -27,8 +34,8 @@ def colonne(file, n, sep=";"):
return res
-Pathways_a_enlever=['Metabolic pathways','Biosynthesis of secondary metabolites','Microbial metabolism in diverse environments','Carbon metabolism''2-Oxocarboxylic acid metabolism','Fatty acid metabolism','Biosynthesis of amino acids','Nucleotide metabolism','Biosynthesis of nucleotide sugars','Biosynthesis of cofactors','Degradation of aromatic compounds','Carbohydrate metabolism','Energy metabolism','Lipid metabolism','Nucleotide metabolism','Amino acid metabolism','Metabolism of other amino acids','Glycan biosynthesis and metabolism','Metabolism of cofactors and vitamins','Metabolism of terpenoids and polyketides','Biosynthesis of other secondary metabolites','Xenobiotics biodegradation and metabolism','Chemical structure transformation maps','Genetic Information Processing','Transcription','Translation','Folding, sorting and degradation','Replication and repair','Information processing in viruses','Environmental Information Processing','Membrane transport','Signal transduction','Signaling molecules and interaction','Cellular Processes','Transport and catabolism','Cell growth and death','Cellular community - eukaryotes','Cellular community - prokaryotes','Cell motility','Immune system','Organismal Systems','Endocrine system','Circulatory system','Digestive system','Excretory system','Nervous system','Sensory system','Development and regeneration','Aging','Environmental adaptation','Human Diseases','Cancer: overview''Cancer: specific types','Infectious disease: viral','Infectious disease: bacterial','Infectious disease: parasitic','Immune disease','Neurodegenerative disease','Substance dependence','Cardiovascular disease','Endocrine and metabolic disease','Drug resistance: antimicrobial','Drug resistance: antineoplastic','Drug Development','Chronology: Antiinfectives','Chronology: Antineoplastics','Chronology: Nervous system agents','Chronology: Other drugs','Target-based classification: G protein-coupled receptors','Target-based classification: Nuclear receptors','Target-based classification: Ion channels','Target-based classification: Transporters','Target-based classification: Enzymes','Structure-based classification','Skeleton-based classification']
-def noms_pathways (file, sep=";") :
+
+def noms_pathways (file, sep=";",p_a_e=Pathways_a_enlever) :
with open(file,'r') as file_csv:
csv_reader = csv.reader(file_csv, delimiter = sep)
liste_nom_pathways=[]
@@ -40,15 +47,12 @@ def noms_pathways (file, sep=";") :
i_a_e=[]
p_retires=[]
for compteur in range (len(a_filtrer)):
- if a_filtrer[compteur] in Pathways_a_enlever:
+ if a_filtrer[compteur] in p_a_e:
i_a_e.append(compteur)
p_retires.append(a_filtrer[compteur])
- print(i_a_e)
- print(p_retires)
for retirer in p_retires :
- print(retirer)
a_filtrer.remove(retirer)
return (a_filtrer,i_a_e)
@@ -63,13 +67,9 @@ def traitement_des_pathways (file,sep=";"):
indice_reel=0
for p in range (Nombre_de_pathways_totale+len(i_e)):# création d'une variables pour chaque pathways
- if (p in i_e):
- print(indice_reel)
- else:
- print(indice_reel)
+ if (p not in i_e):
transitoire=colonne(file, p, sep=";")
Tout_les_pathways[indice_reel]=transitoire[1:len(transitoire)]
- print(Tout_les_pathways[indice_reel])
indice_reel+=1
for b in range (Nombre_de_pathways_totale): # on veut garder que les métabolites
@@ -163,7 +163,7 @@ def traitement_totale_couverture_pathways_et_métabolites(file,Fichier1,Fichier2
Frequences_des_metabolites=[Frequences_des_metabolites , metabolites_frequences_elevee]
- with open(Fichier1, 'w') as f: # possibiliter de rajouter des informations si nécessaires
+ with open(Fichier1, 'w') as f:
writer = csv.writer(f)
writer.writerow(resemblance_des_pathways)
@@ -179,6 +179,7 @@ def traitement_totale_couverture_pathways_et_métabolites(file,Fichier1,Fichier2
-# Ligne de commande pour obtenir les résultats : nécessite 1 fichier de résultat et 3 noms des fichiers de sorties
-traitement_totale_couverture_pathways_et_métabolites("Resultats_Constructeur_KEGG_ID_KEGG_MAPPs_MetaBridge_en_forme_pour_le_programme.csv",'table_de_resemblance_Resultats_Constructeur_KEGG_ID_KEGG_MAPPs_MetaBridge_en_forme_pour_le_programme.csv','frequence_des_metabolites_Resultats_Constructeur_KEGG_ID_KEGG_MAPPs_MetaBridge_en_forme_pour_le_programme.csv','Metabolites_et_leurs_pathways_Resultats_Constructeur_KEGG_ID_KEGG_MAPPs_MetaBridge_en_forme_pour_le_programme.csv')
+###Ligne de commande pour obtenir les résultats : nécessite 1 fichier de résultat et 3 noms des fichiers de sorties
+
+traitement_totale_couverture_pathways_et_métabolites(Fichier_a_traiter,Sortie_Resemblance_des_pathways,Sortie_fréquence_des_metabolites,Sortie_pathways_de_chaque_metabolites)