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

Remove transcript "variant X" when transferring to genes #373

Merged
merged 2 commits into from
May 23, 2024
Merged

Remove transcript "variant X" when transferring to genes #373

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6ebc530
Remove transcript "variant X" when transferring to genes
MatBarba May 22, 2024
22733a2
Apply suggestions from code review
MatBarba May 23, 2024
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
7 changes: 7 additions & 0 deletions src/python/ensembl/io/genomio/gff3/extract_annotation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -230,13 +230,20 @@ def _transfer_description_up(self, child_feature: str) -> None:
for child_id, child in children_features.items():
child_description = child.get("description")
if child_description is not None:
child_description = self._clean_description(child_description)
# Check parent
parent_id = self.get_parent(parent_type, child_id)
parent = parent_features[parent_id]
parent_description = parent.get("description")
if parent_description is None:
parent["description"] = child_description

@staticmethod
def _clean_description(description: str) -> str:
MatBarba marked this conversation as resolved.
Show resolved Hide resolved
variant_re = re.compile(r", transcript variant [A-Z][0-9]+$", re.IGNORECASE)
description = re.sub(variant_re, "", description)
return description

@staticmethod
def product_is_informative(product: str, feat_ids: Optional[List[str]] = None) -> bool:
"""Returns True if the product name contains informative words, False otherwise.
Expand Down
24 changes: 16 additions & 8 deletions src/python/tests/gff3/test_extract_annotation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -312,14 +312,22 @@ def test_get_features(feat_type: str, expected_number: int, expected: ContextMan
@pytest.mark.parametrize(
"gene_desc, transc_desc, transl_desc, out_gene_desc, out_transc_desc",
[
(None, None, None, None, None),
("Foobar", None, None, "Foobar", None), # Only gene descriptions
("gene A", "transc B", "prod C", "gene A", "transc B"), # All descriptions set
(None, None, "Foobar", "Foobar", "Foobar"), # Transfer from transl
(None, "Foobar", None, "Foobar", "Foobar"), # Transfer from transc
(None, "Foobar", "Lorem", "Foobar", "Foobar"), # Transfer from transc, transl also set
("Hypothetical gene", "Predicted function", "Foobar", "Foobar", "Foobar"), # Non informative
(None, None, "Unknown product", None, None), # Non informative source
param(None, None, None, None, None),
MatBarba marked this conversation as resolved.
Show resolved Hide resolved
param("Foobar", None, None, "Foobar", None, id="Only gene description"),
param("gene A", "transc B", "prod C", "gene A", "transc B", id="All descriptions set"),
param(None, None, "Foobar", "Foobar", "Foobar", id="Transfer from transl"),
param(None, "Foobar", None, "Foobar", "Foobar", id="Transfer from transc"),
param(
None,
"Foobar, transcript variant X1",
None,
"Foobar",
"Foobar, transcript variant X1",
id="transcr with variant",
),
param(None, "Foobar", "Lorem", "Foobar", "Foobar", id="Transfer from transc, transl also set"),
param("Hypothetical gene", "Predicted function", "Foobar", "Foobar", "Foobar", id="Non informative"),
param(None, None, "Unknown product", None, None, id="Non informative source"),
],
)
@pytest.mark.dependency(depends=["get_features"])
Expand Down