Skip to content

add --check-long-deletion option #3

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

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

add --check-long-deletion option #3

Show file tree
Hide file tree
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
12 changes: 8 additions & 4 deletions bin/proviral
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,16 +46,19 @@ def cli():
@click.option(
'--run-hypermut/--no-hypermut', default=False
)
@click.option(
'--check-long-deletion/--ignore-long-deletion', default=False
)
@click.option(
'--include-small-orfs/--exclude-small-orfs', default=False)
@click.option(
'--working-folder',
default=os.getcwd()
)

def intact(input_file, subtype, include_packaging_signal,
include_rre, check_major_splice_donor_site, run_hypermut,
include_small_orfs, working_folder):
def intact(input_file, subtype, include_packaging_signal,
include_rre, check_major_splice_donor_site, run_hypermut,
check_long_deletion, include_small_orfs, working_folder):
"""
Check consensus sequences for intactness.
"""
Expand All @@ -69,7 +72,8 @@ def intact(input_file, subtype, include_packaging_signal,
try:
intact_sequences, non_intact_sequences, orfs, errors = it.intact(
folder, input_file, subtype, include_packaging_signal, include_rre,
check_major_splice_donor_site, run_hypermut, include_small_orfs
check_major_splice_donor_site, run_hypermut, check_long_deletion,
include_small_orfs
)
log.info('Intact sequences written to ' + intact_sequences)
log.info('Non-intact sequences written to ' + non_intact_sequences)
Expand Down
21 changes: 21 additions & 0 deletions intact/intact.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,7 +107,22 @@ def isHypermut(aln):
#/end isHypermut


def has_long_deletion(sequence, alignment):
"""
Determines whether the sequence has a long deletion in it.
Keyword Args:

sequence -- the query sequence.
alignment -- multiple sequence alignment object containing the
reference and query sequence.
"""
# NOTE: This is the same check that HIVSeqInR uses.
if len(sequence.seq) < 8000:
return IntactnessError(sequence.id,
LONGDELETION_ERROR,
"Query sequence contains a long deletion.")
return None
#/end has_long_deletion


def has_mutated_major_splice_donor_site(alignment,
Expand Down Expand Up @@ -554,6 +569,7 @@ def intact( working_dir,
include_rre,
check_major_splice_donor_site,
run_hypermut,
check_long_deletion,
include_small_orfs,
hxb2_forward_orfs = const.DEFAULT_FORWARD_ORFs,
hxb2_reverse_orfs = const.DEFAULT_REVERSE_ORFS,
Expand Down Expand Up @@ -667,6 +683,11 @@ def intact( working_dir,
if hypermutated is not None:
sequence_errors.append(hypermutated)

if check_long_deletion is not None:
long_deletion = has_long_deletion(sequence, alignment)
if long_deletion:
sequence_errors.append(long_deletion)

orfs[sequence.id] = hxb2_found_orfs
if len(sequence_errors) == 0:
intact_sequences.append(sequence)
Expand Down