From a84c6d476863b7320297d109db594704162586d3 Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Tue, 3 Dec 2024 21:47:01 +0100
Subject: [PATCH] Add GARD as a source (#262)

Closes #260
---
 src/pyobo/sources/__init__.py |  2 ++
 src/pyobo/sources/gard.py     | 60 +++++++++++++++++++++++++++++++++++
 2 files changed, 62 insertions(+)
 create mode 100644 src/pyobo/sources/gard.py

diff --git a/src/pyobo/sources/__init__.py b/src/pyobo/sources/__init__.py
index 29e4cdc4..22908b40 100644
--- a/src/pyobo/sources/__init__.py
+++ b/src/pyobo/sources/__init__.py
@@ -20,6 +20,7 @@
 from .expasy import ExpasyGetter
 from .famplex import FamPlexGetter
 from .flybase import FlyBaseGetter
+from .gard import GARDGetter
 from .geonames import GeonamesGetter
 from .gtdb import GTDBGetter
 from .gwascentral_phenotype import GWASCentralPhenotypeGetter
@@ -79,6 +80,7 @@
     "ExpasyGetter",
     "FamPlexGetter",
     "FlyBaseGetter",
+    "GARDGetter",
     "GTDBGetter",
     "GWASCentralPhenotypeGetter",
     "GWASCentralStudyGetter",
diff --git a/src/pyobo/sources/gard.py b/src/pyobo/sources/gard.py
new file mode 100644
index 00000000..032501b0
--- /dev/null
+++ b/src/pyobo/sources/gard.py
@@ -0,0 +1,60 @@
+"""Converter for GARD."""
+
+from collections.abc import Iterable
+
+import requests
+
+from pyobo.struct import Obo, Term, default_reference
+
+__all__ = [
+    "GARDGetter",
+]
+
+PREFIX = "gard"
+PP = "gard.category"
+URL = "https://rarediseases.info.nih.gov/assets/diseases.trimmed.json"
+
+
+class GARDGetter(Obo):
+    """An ontology representation of GARD."""
+
+    bioversions_key = ontology = PREFIX
+    dynamic_version = True
+
+    def iter_terms(self, force: bool = False) -> Iterable[Term]:
+        """Iterate over gene terms for GARD."""
+        yield from get_terms()
+
+
+def get_terms() -> Iterable[Term]:
+    """Get GARD terms."""
+    rows = requests.get(URL, timeout=5).json()
+    categories = {
+        category: default_reference(
+            prefix=PREFIX, identifier=category.lower().replace(" ", "_"), name=category
+        )
+        for row in rows
+        for category in row.get("diseaseCategories", [])
+    }
+    categories["uncategorized"] = default_reference(
+        prefix=PREFIX, identifier="uncategorized", name="Uncategorized Disease"
+    )
+    for category_reference in categories.values():
+        yield Term(reference=category_reference)
+
+    for row in rows:
+        term = Term.from_triple(PREFIX, identifier=str(row.pop("id")), name=row.pop("name"))
+        _name = row.pop("encodedName", None)
+        for synonym in row.pop("synonyms", []):
+            term.append_synonym(synonym)
+        for category in row.pop("diseaseCategories", ["uncategorized"]):
+            term.append_parent(categories[category])
+
+        _spanish_id = row.pop("spanishId", None)
+        _spanish_name = row.pop("spanishName", None)
+
+        yield term
+
+
+if __name__ == "__main__":
+    GARDGetter().write_default(write_obo=True, write_owl=True, force=True)