Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat: complex CDSs within augur ancestral #1333

Draft
wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

feat: complex CDSs within augur ancestral #1333

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 11 additions & 5 deletions augur/ancestral.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@
from Bio import SeqIO
from Bio.Seq import Seq
from Bio.SeqRecord import SeqRecord
from Bio.SeqFeature import CompoundLocation
from .utils import read_tree, InvalidTreeError, write_json, get_json_name
from treetime.vcf_utils import read_vcf, write_vcf
from collections import defaultdict
Expand Down Expand Up @@ -332,14 +333,19 @@ def run(args):
node["aa_sequences"][gene] = aa_result['tt'].sequence(T.root, as_string=True, reconstructed=True)

anc_seqs['reference'][gene] = aa_result['root_seq']
# FIXME: Note that this is calculating the end of the CDS as 3*length of translation
# this is equivalent to the annotation for single segment CDS, but not for cds
# with splicing and slippage. But auspice can't handle the latter at the moment.
anc_seqs['annotations'][gene] = {'seqid':args.annotation,
'type':feat.type,
'start': int(feat.location.start)+1,
'end': int(feat.location.start) + 3*len(anc_seqs['reference'][gene]),
'strand': {+1:'+', -1:'-', 0:'?', None:None}[feat.location.strand]}
if feat.type == "CDS" and type(feat.location) == CompoundLocation:
location = []
for seg in feat.location.parts:
location.append({"start": int(seg.start)+1, "end": int(seg.end)})
anc_seqs['annotations'][gene]["segments"] = location
else:
anc_seqs['annotations'][gene].update({
'start': int(feat.location.start)+1,
'end': int(feat.location.start) + 3*len(anc_seqs['reference'][gene]),
})

# Save ancestral amino acid sequences to FASTA.
if args.output_translations:
Expand Down
Loading