From 7028126ee0f11f5c54bc4f03413aa350a80bfa9a Mon Sep 17 00:00:00 2001
From: Fontrodona Nicolas <nicolas.fontrodona@ens-lyon.fr>
Date: Wed, 17 Feb 2021 09:45:18 +0100
Subject: [PATCH] src/download_encode_eclip/merge_eclip.py: modification of
merge_files function to remove the heading chr in the first bed column
---
src/download_encode_eclip/merge_eclip.py | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/src/download_encode_eclip/merge_eclip.py b/src/download_encode_eclip/merge_eclip.py
index 0e149311..db0df8d8 100644
--- a/src/download_encode_eclip/merge_eclip.py
+++ b/src/download_encode_eclip/merge_eclip.py
@@ -143,8 +143,8 @@ def merge_files(dfiles: Dict[str, List[Path]], target: str) -> None:
list_file = " ".join(map(str, dfiles[k]))
cmd = f"zcat {list_file} | sort -k1,1 -k2,2n > {tmp_out}"
cmd2 = f"bedtools merge -i {tmp_out} -s -c 4,5,6 " \
- f"-o collapse,mean,distinct | cut -f1-3,5-7 | gzip -c " \
- f"> {res_out}"
+ f"-o collapse,mean,distinct | cut -f1-3,5-7 | sed 's/^chr//g' " \
+ f"| gzip -c > {res_out}"
sp.check_output(cmd, shell=True)
sp.check_output(cmd2, shell=True)
tmp_out.unlink()
--
GitLab