changes count_effectors.py and gff_sort.py

scripts/count_effectors.py

@@ -36,9 +36,9 @@ def main(gff, output, fasta_file):
         for lignes in f1:
                 ligne = lignes.rstrip("\n")
                 col = ligne.split("\t")
-                id_1 = re.sub("ID=", "", col[8])
-                id_2 = re.sub(";Name=\w+", "", id_1)
-                if col[2] =="gene":
+                if col[2] == "gene":
+                    id_1 = re.sub("ID=", "", col[8])
+                    id_2 = re.sub(";Name=\w+", "", id_1)
                     gff_parse.append(col[0]+" "+col[1]+" "+col[2]+" "+id_2)
                     dico_gff[col[0]].append(id_2)
 

scripts/gff_sort.py

@@ -22,10 +22,10 @@ def main(gff, output, strain_name):
     with open(gff, "r") as f1:
         for lignes in f1:
             col = lignes.split("\t")
-            if re.search("gene",col[2]):
-                id_strain = re.sub("ID=","ID="+strain_name+"_",col[8])
-                prot_gff = re.sub(";","T0;",id_strain)
-                gene_gff.append(col[0]+"\t"+col[1]+"\t"+col[2]+"\t"+col[3]+"\t"+col[4]+"\t"+col[5]+"\t"+col[6]+"\t"+col[7]+"\t"+prot_gff)
+            id_strain = re.sub("ID=","ID="+strain_name+"_",col[8])
+            prot_gff = re.sub(";","T0;",id_strain)
+            prot_gff = re.sub("T0T0", "T0", prot_gff)
+            gene_gff.append(col[0]+"\t"+col[1]+"\t"+col[2]+"\t"+col[3]+"\t"+col[4]+"\t"+col[5]+"\t"+col[6]+"\t"+col[7]+"\t"+prot_gff)
 
     output_file = open(output,"w")
     for elem in gene_gff: