From fe28cbd60f5d55a1c431a512ab10f1ab800ee275 Mon Sep 17 00:00:00 2001
From: Amandine PERRIN <amandine.perrin@pasteur.fr>
Date: Wed, 20 Sep 2023 16:12:10 +0200
Subject: [PATCH] Small speed improvment while extracting proteins
---
PanACoTA/align_module/get_seqs.py | 12 +++++++-----
1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/PanACoTA/align_module/get_seqs.py b/PanACoTA/align_module/get_seqs.py
index a8b61df0..b0af4000 100755
--- a/PanACoTA/align_module/get_seqs.py
+++ b/PanACoTA/align_module/get_seqs.py
@@ -265,11 +265,13 @@ def extract_sequences(to_extract, fasf, files_todo=None, outf=None):
previous_fp = None
# Extract sequence name
- # last_char = line.find(' ')
- # if last_char == -1:
- # last_char = len(line)
- # seq = line[1:last_char].strip()
- seq = line.strip().split()[0][1:]
+ last_char = line.find('\t')
+ if last_char == -1:
+ last_char = line.find(' ')
+ if last_char == -1:
+ last_char = len(line)
+ seq = line[1:last_char].strip()
+ # seq = line.strip().split()[0][1:]
# Seq is part of sequences to extract
if seq in to_extract:
--
GitLab