YuuMJ1997/EukPhylo
1
0
Fork 0
mirror of http://43.156.76.180:8026/YuuMJ/EukPhylo.git synced 2025-12-27 05:20:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

Added annotation to 4_CountOGsDiamond.py

Browse Source
This commit is contained in:
Auden Cote-L'Heureux 2023-09-18 10:04:25 -04:00 committed by GitHub
parent 8e561dc735
commit 106b2e2d89
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
PTL1/Genomes/Scripts/4_CountOGsDiamond.py
View File

@ -1,6 +1,6 @@
#!/usr/bin/env python3.5
##__Updated__: 19_09_2017
##__Updated__: 18_09_2023 (by ACL)
##__Author__: Xyrus Maurer-Alcala; maurerax@gmail.com
##__Usage__: python 3g_GCodeTranslate.py --help
@ -246,6 +246,7 @@ def update_fasta(args):
hook_fasta = [file for file in os.listdir(args.databases + '/db_OG') if file.endswith('.fasta')][0]
#Getting average length in Hook: addition per 9/2023 update
OGLenDB = {}
for rec in SeqIO.parse(args.databases + '/db_OG/' + hook_fasta, 'fasta'):
if rec.id[-10:] not in OGLenDB:
@ -272,6 +273,7 @@ def update_fasta(args):
updated_prot_name = { keep_dict[i.description] : str(i.seq).rstrip('*') for i in protFasta if i.description in keep_dict.keys() }
updated_ntd_name = { keep_dict[i.description] : str(i.seq).rstrip('*') for i in ntdFasta if i.description in keep_dict.keys() }
#Additional length filter here per 9/2023 update
with open(args.aa_out,'w+') as w:
for rec in updated_prot_name:
og_number = re.split('OG.{1}_', rec)[1][:6]
@ -335,4 +337,4 @@ main()
# this script's gene family assignments. These gene family assignments are NON-EXHAUSTIVE
# and most Lineage-Specific families will be missed!
#
# If you have any questions contact Xyrus (author): maurerax@gmail.com
# If you have any questions contact Xyrus (author): maurerax@gmail.com