YuuMJ1997/EukPhylo
1
0
Fork 0
mirror of http://43.156.76.180:8026/YuuMJ/EukPhylo.git synced 2025-12-27 12:20:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

Adding allowance to backtranslating script for nucleotide sequences shorter than amino acid sequences by 3' trimming

Browse Source
This commit is contained in:
Auden Cote-L'Heureux 2023-08-10 10:40:19 -04:00 committed by GitHub
parent 29daa4932b
commit 943bc3461d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 18 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
Utilities/for_fastas/BacktranslateAlignment.py
View File

@ -58,26 +58,27 @@ def backtranslate(aa, nucls, output):
for rec in aa:
if(rec.id in nucls):
if len(nucls[rec.id]) == len(str(rec.seq).replace('-', '')) * 3:
running_seq = ''; c = 0; fail = False
for i, char in enumerate(str(rec.seq)):
if(char == '-'):
running_seq += '---'
else:
codon = nucls[rec.id][c:c+3]
if char == 'X' or codon in codons_per_aa[char]:
running_seq += codon
c += 3
else:
fail = True
if len(nucls[rec.id]) != len(str(rec.seq).replace('-', '')) * 3:
print('\nWARNING: The nucleotide sequence ' + rec.id + ' is not 3x the length of the corresponding amino acid sequence. Trying to translate this sequence by starting at the beginning and working forward until the amino acid sequence ends.\n')
nucls[rec.id] = nucls[rec.id][:len(str(rec.seq).replace('-', '')) * 3]
if fail:
print('\nWARNING: The nucleotide sequence ' + rec.id + ' does not match the corresponding amino acid sequence. This sequence will be missing from the alignment.\n')
running_seq = ''; c = 0; fail = False
for i, char in enumerate(str(rec.seq)):
if(char == '-'):
running_seq += '---'
else:
o.write('>' + rec.id + '\n')
o.write(running_seq + '\n\n')
codon = nucls[rec.id][c:c+3]
if char == 'X' or codon in codons_per_aa[char]:
running_seq += codon
c += 3
else:
fail = True
if fail:
print('\nWARNING: The nucleotide sequence ' + rec.id + ' does not match the corresponding amino acid sequence. This sequence will be missing from the alignment.\n')
else:
print('\nWARNING: The nucleotide sequence ' + rec.id + ' is not 3x the length of the corresponding amino acid sequence. This sequence will be missing from the alignment.\n')
o.write('>' + rec.id + '\n')
o.write(running_seq + '\n\n')
else:
print('\nWARNING: There is no nucleotide sequence for the amino acid sequence ' + rec.id + '. This sequence will be missing from the alignment.\n')