Skip to content

ENH+BF: Format species names consistently in species_map, make matching more stringent for common names, improved testing #1866

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

Merged
yarikoptic merged 9 commits into from
Jun 1, 2026
Merged

ENH+BF: Format species names consistently in species_map, make matching more stringent for common names, improved testing #1866

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
1a2d7a9
enh: add Macaca radiata (bonnet macaque) to species_map
yarikoptic May 28, 2026
5a9d473
Initial plan
Copilot May 28, 2026
e98375c
fix: normalize species_map name formatting
Copilot May 28, 2026
1177640
Fix species_map exact part matching
Copilot May 29, 2026
2eadb00
Guard species common-name matching
Copilot May 29, 2026
fbe2f6c
Make matching more explicit for multiple values with common names as …
yarikoptic May 29, 2026
db81fa7
Make matching for common names more stringent - euqality not just con…
yarikoptic May 29, 2026
a8834c2
Fix species typing annotation
Copilot May 29, 2026
e85ef07
Merge branch 'enh-macaca-radiata' into copilot/wip-address-feedback-f…
CodyCBakerPhD May 29, 2026
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
17 changes: 12 additions & 5 deletions dandi/metadata/util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -332,7 +332,7 @@ def extract_cellLine(metadata: dict) -> str | None:

NCBITAXON_URI_TEMPLATE = "http://purl.obolibrary.org/obo/NCBITaxon_{}"

# common_names, prefix, uri, name
# common_names, prefix, uri, name ({current name} - {GenBank common name})
species_map = [
Comment thread
yarikoptic marked this conversation as resolved.
(
["mouse"],
Expand Down Expand Up @@ -386,25 +386,31 @@ def extract_cellLine(metadata: dict) -> str | None:
["c. elegans", "caenorhabditis elegans"],
"caenorhabditis",
NCBITAXON_URI_TEMPLATE.format("6239"),
"Caenorhabditis elegans",
"Caenorhabditis elegans - Roundworm",
),
(
["pig-tailed macaque", "pigtail monkey", "pigtail macaque"],
None,
NCBITAXON_URI_TEMPLATE.format("9545"),
"Macaca nemestrina",
"Macaca nemestrina - Pig-tailed macaque",
),
(
["bonnet macaque", "bonnet monkey", "radiata"],
None,
NCBITAXON_URI_TEMPLATE.format("9548"),
"Macaca radiata - Bonnet macaque",
),
(
["mongolian gerbil", "mongolian jird"],
None,
NCBITAXON_URI_TEMPLATE.format("10047"),
"Meriones unguiculatus",
"Meriones unguiculatus - Mongolian gerbil",
),
(
["common paper wasp"],
None,
NCBITAXON_URI_TEMPLATE.format("30207"),
"Polistes fuscatus",
"Polistes fuscatus - Common paper wasp",
),
]

Expand Down Expand Up @@ -486,6 +492,7 @@ def extract_species(metadata: dict) -> models.SpeciesType | None:
for common_names, prefix, uri, name in species_map:
if (
lower_value == name.lower()
or lower_value == name.partition(" - ")[0].lower()
Comment thread
yarikoptic marked this conversation as resolved.
Outdated
or any(key in lower_value for key in common_names)
or (prefix is not None and lower_value.startswith(prefix))
):
Expand Down
5 changes: 3 additions & 2 deletions dandi/tests/test_metadata.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -770,7 +770,7 @@ def test_species_all_possible(species: str) -> None:
assert species_rec.model_dump(mode="json", exclude_none=True) == {
"identifier": "http://purl.obolibrary.org/obo/NCBITaxon_10047",
"schemaKey": "SpeciesType",
"name": "Meriones unguiculatus",
"name": "Meriones unguiculatus - Mongolian gerbil",
}


Expand All @@ -782,9 +782,10 @@ def test_extract_unknown_species():

def test_species_map():
# all alternative names should be lower case
for common_names, *_ in species_map:
for common_names, _, _, name in species_map:
for key in common_names:
assert key.lower() == key
assert " - " in name


@pytest.mark.parametrize(
Expand Down