test ajout transposon

R/biogrid_window_opt.R

@@ -28,7 +28,7 @@ construct_id2 = function(organism, uniprot, sequence, mainpath) {
   
   setwd(mainpath)
   cat("\n CAT 1 :",mainpath)
-  command <- paste("python", "thesaurusPy.py", paste0("\"", uniprot, "\""),  paste0("\"",sortie, "\""), organisme, sep = " ")
+  command <- paste("python3", "thesaurusPy.py", paste0("\"", uniprot, "\""),  paste0("\"",sortie, "\""), organisme, sep = " ")
   cat("\n CAT 2 :",command)
   system(command)
   
@@ -92,7 +92,7 @@ format_database = function(organism,organismID, putative, file, uniprot, pathrac
   path <- paste(system.file(package = "appinetwork"), "biogridPy.py", sep = "/")
   file.copy(path, pathracine)
   path.copy <- paste(pathracine, "biogridPy.py", sep = "/")
-  command <- paste("python", "biogridPy.py",   paste0("\"", uniprotfile, "\""), paste0("\"",sortie, "\""), putative, sep = " ")
+  command <- paste("python3", "biogridPy.py",   paste0("\"", uniprotfile, "\""), paste0("\"",sortie, "\""), putative, sep = " ")
   system(command)
   
   file.remove(path.copy)

R/thesaurus_window.R

@@ -26,7 +26,7 @@ construct_id = function(organism, uniprot, sequence, mainpath) {
   
   setwd(mainpath)
   cat("\n CAT 1 :",mainpath)
-  command <- paste("python", "thesaurusPy.py", paste0("\"", uniprot, "\""), paste0("\"",sortie, "\""), organisme, sep = " ")
+  command <- paste("python3", "thesaurusPy.py", paste0("\"", uniprot, "\""), paste0("\"",sortie, "\""), organisme, sep = " ")
   
   cat("\n CAT 2 :",command)
   system(command)

inst/thesaurusPy.py

@@ -39,6 +39,8 @@ ORF = 'NA'
 Iso = 'NA'
 ISO = 'NA'
 NIso = 'NA'
+Putative = "FALSE"
+Transposon = "FALSE"
 
 for i in fichier :
 
@@ -120,6 +122,21 @@ for i in fichier :
 		else :
 			Biogrid = 'NA'
 
+    	# Recuperation du RecName : Putative, Transposon
+	elif i[0:13] == "DE   RecName:" :
+		if Putative == "FALSE" :
+			Putative = re.search(r"(DE   RecName:)(\s)*(Full=Putative)(.)*", i)
+			if Putative is not None:
+				Putative = "TRUE"
+			else :
+				Putative = "FALSE"
+		if Transposon == "FALSE" :
+			Transposon = re.search(r"(DE   RecName:)(\s)*(Full=Transposon)(.)*", i)
+			if Transposon is not None:
+				Transposon = "TRUE"
+			else :
+				Transposon = "FALSE"
+
 	# Recuperation du nombre d'isoformes
 	elif i[0:2] == "CC" :
 		if NIso == 'NA' :
@@ -400,7 +417,7 @@ for i in fichier :
 			for B in range(0,b) :
 				Biogrid = str(BIOGRID[B]) + ';'
 
-		ligne = ID + "\t" + Biogrid + "\t" + Name + "\t" + Ref + "\t" + NameProt + "\t" + ORF + "\t" + Iso + "\t" + NIso
+		ligne = ID + "\t" + Biogrid + "\t" + Name + "\t" + Ref + "\t" + NameProt + "\t" + ORF + "\t" + Iso + "\t" + NIso + "\t" + Putative + "\t" + Transposon
 		donnees.append(ligne)
 
 		ligne = 'NA'
@@ -416,6 +433,8 @@ for i in fichier :
 		ISO = 'NA'
 		NIso = 'NA'
 		test = 0
+		Putative = "FALSE"
+		Transposon = "FALSE"
 
 fichier.close()
 
@@ -423,7 +442,7 @@ fichier.close()
 
 sortie = open(thesaurus,'w')
 
-sortie.write("Uniprot-ID\tBiogrid-ID\tGene-Name\tRef-Seq\tProtein-Name\tGene-ID\tOld-Uniprot-IDs\tIsoformes")
+sortie.write("Uniprot-ID\tBiogrid-ID\tGene-Name\tRef-Seq\tProtein-Name\tGene-ID\tOld-Uniprot-IDs\tIsoformes\tPutative\tTransposon")
 
 N = len(donnees)
 for i in range(0,N) :