From 073eb2a83f3d1dce315b17f5d754c75fe95f01f6 Mon Sep 17 00:00:00 2001
From: tdurand <theo.durand@etu.uca.fr>
Date: Thu, 9 Jun 2022 11:54:34 +0200
Subject: [PATCH] ADD good scripts
---
scripts/count_effectors.py | 6 +++---
scripts/gff_sort.py | 3 ++-
2 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/scripts/count_effectors.py b/scripts/count_effectors.py
index 1afcf32..97def27 100644
--- a/scripts/count_effectors.py
+++ b/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)
diff --git a/scripts/gff_sort.py b/scripts/gff_sort.py
index 6c465f3..fe5996c 100644
--- a/scripts/gff_sort.py
+++ b/scripts/gff_sort.py
@@ -25,7 +25,8 @@ def main(gff, output, strain_name):
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)
+ all_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"+all_gff)
output_file = open(output,"w")
for elem in gene_gff:
--
GitLab