From 12c95ab1e0f770bba71e1b3b3cd99fc32825c0c4 Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Fri, 1 Aug 2025 10:58:09 +0200
Subject: [PATCH 01/18] Add cordis

---
 src/pyobo/sources/cordis.py | 3 +++
 1 file changed, 3 insertions(+)
 create mode 100644 src/pyobo/sources/cordis.py

diff --git a/src/pyobo/sources/cordis.py b/src/pyobo/sources/cordis.py
new file mode 100644
index 00000000..f8631bab
--- /dev/null
+++ b/src/pyobo/sources/cordis.py
@@ -0,0 +1,3 @@
+URL = "https://cordis.europa.eu/data/cordis-h2020projects-csv.zip"
+
+# see euscivoc, which is in skosxl format

From 285eb252f071d4f6035bedcfdfd2ab3945390cfa Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Mon, 11 Aug 2025 22:34:02 +0200
Subject: [PATCH 02/18] Update cordis.py

---
 src/pyobo/sources/cordis.py | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/src/pyobo/sources/cordis.py b/src/pyobo/sources/cordis.py
index f8631bab..3e6b4381 100644
--- a/src/pyobo/sources/cordis.py
+++ b/src/pyobo/sources/cordis.py
@@ -1,3 +1,38 @@
+"""Converter for CORDIS Projects."""
+
+from collections.abc import Iterable
+
+from pyobo import Obo, Reference, Term
+from pyobo.utils.path import ensure_path
+from pystow.utils import read_zipfile_csv
+
+__all__ = [
+    "CordisProjectGetter",
+]
+
 URL = "https://cordis.europa.eu/data/cordis-h2020projects-csv.zip"
+PREFIX = "cordis.project"
 
 # see euscivoc, which is in skosxl format
+
+
+class CordisProjectGetter(Obo):
+    """An ontology representation of cordis projects."""
+
+    ontology = PREFIX
+    dynamic_version = True
+
+    def iter_terms(self, force: bool = False) -> Iterable[Term]:
+        """Iterate over terms in the ontology."""
+        return iter_terms()
+
+
+def iter_terms() -> Iterable[Term]:
+    """Iterate over CPT terms."""
+    path = ensure_path("cordis", url=URL)
+    df = read_zipfile_csv(path, "project.csv", sep='\t')
+    print(df.head())
+
+
+if __name__ == "__main__":
+    CordisProjectGetter.cli()

From 24c856c20a0c77f9aa11506c5398c9756a99f007 Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Tue, 12 Aug 2025 00:50:26 +0200
Subject: [PATCH 03/18] Update cordis.py

---
 src/pyobo/sources/cordis.py | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/src/pyobo/sources/cordis.py b/src/pyobo/sources/cordis.py
index 3e6b4381..ce4fdd3f 100644
--- a/src/pyobo/sources/cordis.py
+++ b/src/pyobo/sources/cordis.py
@@ -2,9 +2,10 @@
 
 from collections.abc import Iterable
 
-from pyobo import Obo, Reference, Term
+from pystow.utils import open_zip_reader
+
+from pyobo import Obo, Term
 from pyobo.utils.path import ensure_path
-from pystow.utils import read_zipfile_csv
 
 __all__ = [
     "CordisProjectGetter",
@@ -13,6 +14,7 @@
 URL = "https://cordis.europa.eu/data/cordis-h2020projects-csv.zip"
 PREFIX = "cordis.project"
 
+
 # see euscivoc, which is in skosxl format
 
 
@@ -30,8 +32,18 @@ def iter_terms(self, force: bool = False) -> Iterable[Term]:
 def iter_terms() -> Iterable[Term]:
     """Iterate over CPT terms."""
     path = ensure_path("cordis", url=URL)
-    df = read_zipfile_csv(path, "project.csv", sep='\t')
-    print(df.head())
+    # df = read_zipfile_csv(path, "project.csv", sep=';', engine="python")
+    i = 0
+
+    with open_zip_reader(path, "project.csv", delimiter=";") as reader:
+        header = next(reader)
+        for _row in reader:
+            i += 1
+            if i > 10:
+                break
+            dict(zip(header, _row, strict=False))
+
+    yield from []
 
 
 if __name__ == "__main__":

From 28cbe7e4f49ef45be872e060cbe2bca6b8a10fc3 Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Sun, 17 May 2026 14:15:27 -0400
Subject: [PATCH 04/18] Update CORDIS

---
 src/pyobo/sources/__init__.py              |  3 +
 src/pyobo/sources/cordis.py                | 50 ----------------
 src/pyobo/sources/cordis/__init__.py       |  9 +++
 src/pyobo/sources/cordis/cordis_basis.py   | 39 +++++++++++++
 src/pyobo/sources/cordis/cordis_project.py | 66 ++++++++++++++++++++++
 src/pyobo/sources/cordis/utils.py          | 14 +++++
 6 files changed, 131 insertions(+), 50 deletions(-)
 delete mode 100644 src/pyobo/sources/cordis.py
 create mode 100644 src/pyobo/sources/cordis/__init__.py
 create mode 100644 src/pyobo/sources/cordis/cordis_basis.py
 create mode 100644 src/pyobo/sources/cordis/cordis_project.py
 create mode 100644 src/pyobo/sources/cordis/utils.py

diff --git a/src/pyobo/sources/__init__.py b/src/pyobo/sources/__init__.py
index e3f6875b..60aa105e 100644
--- a/src/pyobo/sources/__init__.py
+++ b/src/pyobo/sources/__init__.py
@@ -17,6 +17,7 @@
 from .clinicaltrials import ClinicalTrialsGetter
 from .complexportal import ComplexPortalGetter
 from .conso import CONSOGetter
+from .cordis import CordisBasisGetter, CordisProjectGetter
 from .cpt import CPTGetter
 from .credit import CreditGetter
 from .cvx import CVXGetter
@@ -94,6 +95,8 @@
     "ChEMBLTissueGetter",
     "ClinicalTrialsGetter",
     "ComplexPortalGetter",
+    "CordisBasisGetter",
+    "CordisProjectGetter",
     "CreditGetter",
     "DepMapGetter",
     "DictybaseGetter",
diff --git a/src/pyobo/sources/cordis.py b/src/pyobo/sources/cordis.py
deleted file mode 100644
index ce4fdd3f..00000000
--- a/src/pyobo/sources/cordis.py
+++ /dev/null
@@ -1,50 +0,0 @@
-"""Converter for CORDIS Projects."""
-
-from collections.abc import Iterable
-
-from pystow.utils import open_zip_reader
-
-from pyobo import Obo, Term
-from pyobo.utils.path import ensure_path
-
-__all__ = [
-    "CordisProjectGetter",
-]
-
-URL = "https://cordis.europa.eu/data/cordis-h2020projects-csv.zip"
-PREFIX = "cordis.project"
-
-
-# see euscivoc, which is in skosxl format
-
-
-class CordisProjectGetter(Obo):
-    """An ontology representation of cordis projects."""
-
-    ontology = PREFIX
-    dynamic_version = True
-
-    def iter_terms(self, force: bool = False) -> Iterable[Term]:
-        """Iterate over terms in the ontology."""
-        return iter_terms()
-
-
-def iter_terms() -> Iterable[Term]:
-    """Iterate over CPT terms."""
-    path = ensure_path("cordis", url=URL)
-    # df = read_zipfile_csv(path, "project.csv", sep=';', engine="python")
-    i = 0
-
-    with open_zip_reader(path, "project.csv", delimiter=";") as reader:
-        header = next(reader)
-        for _row in reader:
-            i += 1
-            if i > 10:
-                break
-            dict(zip(header, _row, strict=False))
-
-    yield from []
-
-
-if __name__ == "__main__":
-    CordisProjectGetter.cli()
diff --git a/src/pyobo/sources/cordis/__init__.py b/src/pyobo/sources/cordis/__init__.py
new file mode 100644
index 00000000..82c34cb9
--- /dev/null
+++ b/src/pyobo/sources/cordis/__init__.py
@@ -0,0 +1,9 @@
+"""CORDIS sources."""
+
+from .cordis_basis import CordisBasisGetter
+from .cordis_project import CordisProjectGetter
+
+__all__ = [
+    "CordisBasisGetter",
+    "CordisProjectGetter",
+]
diff --git a/src/pyobo/sources/cordis/cordis_basis.py b/src/pyobo/sources/cordis/cordis_basis.py
new file mode 100644
index 00000000..570c4f0b
--- /dev/null
+++ b/src/pyobo/sources/cordis/cordis_basis.py
@@ -0,0 +1,39 @@
+"""Converter for CORDIS Projects."""
+
+from collections.abc import Iterable
+
+from pystow.utils import open_zip_reader
+
+from pyobo import Obo, Term
+from pyobo.sources.cordis.utils import get_cordis_path
+
+__all__ = [
+    "CordisBasisGetter",
+]
+
+PREFIX = "cordis.basis"
+
+
+class CordisBasisGetter(Obo):
+    """An ontology representation of cordis legal bases."""
+
+    ontology = PREFIX
+    dynamic_version = True
+
+    def iter_terms(self, force: bool = False) -> Iterable[Term]:
+        """Iterate over terms in the ontology."""
+        return iter_terms()
+
+
+def iter_terms() -> Iterable[Term]:
+    """Iterate over CORDIS legal basis terms."""
+    path = get_cordis_path()
+    with open_zip_reader(path, "legalBasis.csv", delimiter=";") as reader:
+        _header = next(reader)
+        unique = {row[1] for row in reader}
+        for identifier in sorted(unique):
+            yield Term.from_triple(PREFIX, identifier)
+
+
+if __name__ == "__main__":
+    CordisBasisGetter.cli(["--obo"])
diff --git a/src/pyobo/sources/cordis/cordis_project.py b/src/pyobo/sources/cordis/cordis_project.py
new file mode 100644
index 00000000..19840c9f
--- /dev/null
+++ b/src/pyobo/sources/cordis/cordis_project.py
@@ -0,0 +1,66 @@
+"""Converter for CORDIS Projects."""
+
+from collections.abc import Iterable
+
+from curies.vocabulary import acronym
+from pystow.utils import open_zip_reader
+from tqdm import tqdm
+
+from pyobo import Obo, Reference, Term, TypeDef, default_reference
+from pyobo.sources.cordis.utils import get_cordis_path
+
+__all__ = [
+    "CordisProjectGetter",
+]
+
+PREFIX = "cordis.project"
+
+
+# see euscivoc, which is in skosxl format
+
+HAS_LEGAL_BASIS = TypeDef(reference=default_reference(PREFIX, "hasLegalBasis"))
+
+
+class CordisProjectGetter(Obo):
+    """An ontology representation of cordis projects."""
+
+    ontology = PREFIX
+    typedefs = [HAS_LEGAL_BASIS]
+    dynamic_version = True
+
+    def iter_terms(self, force: bool = False) -> Iterable[Term]:
+        """Iterate over terms in the ontology."""
+        return iter_terms()
+
+
+def iter_terms() -> Iterable[Term]:
+    """Iterate over CPT terms."""
+    path = get_cordis_path()
+    # TODO might need to add additional parts
+    with open_zip_reader(path, "project.csv", delimiter=";") as reader:
+        header = next(reader)
+        for row in reader:
+            row = dict(zip(header, row, strict=False))
+            term = Term(
+                reference=Reference(
+                    prefix="cordis.project", identifier=row["id"], name=row["title"]
+                ),
+                # definition=row['objective'],
+            )
+            term.append_synonym(row["acronym"], type=acronym)
+            term.append_property(
+                HAS_LEGAL_BASIS, Reference(prefix="cordis.basis", identifier=row["legalBasis"])
+            )
+
+            doi = row["grantDoi"]
+            try:
+                doi_reference = Reference(prefix="doi", identifier=doi)
+            except ValueError:
+                tqdm.write(f"[{term.curie}] problem with DOI: {doi}")
+            else:
+                term.append_exact_match(doi_reference)
+            yield term
+
+
+if __name__ == "__main__":
+    CordisProjectGetter.cli(["--obo"])
diff --git a/src/pyobo/sources/cordis/utils.py b/src/pyobo/sources/cordis/utils.py
new file mode 100644
index 00000000..455d647d
--- /dev/null
+++ b/src/pyobo/sources/cordis/utils.py
@@ -0,0 +1,14 @@
+"""Utilities for CORDIS resources."""
+
+from pathlib import Path
+
+from pyobo.utils.path import ensure_path
+
+__all__ = ["get_cordis_path"]
+
+URL = "https://cordis.europa.eu/data/cordis-h2020projects-csv.zip"
+
+
+def get_cordis_path(version: str | None = None) -> Path:
+    """Get the CORDIS data dump."""
+    return ensure_path("cordis", url=URL, version=version)

From 4abaf24cd13e5180a266fb508644a2b7e4774d6a Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Mon, 18 May 2026 07:07:37 +0200
Subject: [PATCH 05/18] Update

---
 pyproject.toml                                |  2 +-
 src/pyobo/sources/__init__.py                 |  3 +-
 src/pyobo/sources/cordis/__init__.py          |  2 +
 src/pyobo/sources/cordis/cordis_basis.py      | 26 ++++++------
 .../sources/cordis/cordis_organization.py     | 40 +++++++++++++++++++
 src/pyobo/sources/cordis/cordis_project.py    | 16 +++-----
 src/pyobo/sources/cordis/cordis_topic.py      |  1 +
 src/pyobo/sources/cordis/utils.py             | 17 +++++++-
 8 files changed, 78 insertions(+), 29 deletions(-)
 create mode 100644 src/pyobo/sources/cordis/cordis_organization.py
 create mode 100644 src/pyobo/sources/cordis/cordis_topic.py

diff --git a/pyproject.toml b/pyproject.toml
index 4c849cb6..0d1eea8b 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -68,7 +68,7 @@ dependencies = [
     "humanize",
     "tabulate",
     "cachier",
-    "pystow>=0.8.11",
+    "pystow>=0.8.13",
     "bioversions>=0.10.11",
     "bioregistry>=0.13.48",
     "ssslm>=0.2.0",
diff --git a/src/pyobo/sources/__init__.py b/src/pyobo/sources/__init__.py
index 47449453..370e9779 100644
--- a/src/pyobo/sources/__init__.py
+++ b/src/pyobo/sources/__init__.py
@@ -17,7 +17,7 @@
 from .clinicaltrials import ClinicalTrialsGetter
 from .complexportal import ComplexPortalGetter
 from .conso import CONSOGetter
-from .cordis import CordisBasisGetter, CordisProjectGetter
+from .cordis import CordisBasisGetter, CordisOrganizationGetter, CordisProjectGetter
 from .cpt import CPTGetter
 from .credit import CreditGetter
 from .cvx import CVXGetter
@@ -98,6 +98,7 @@
     "ClinicalTrialsGetter",
     "ComplexPortalGetter",
     "CordisBasisGetter",
+    "CordisOrganizationGetter",
     "CordisProjectGetter",
     "CreditGetter",
     "DepMapGetter",
diff --git a/src/pyobo/sources/cordis/__init__.py b/src/pyobo/sources/cordis/__init__.py
index 82c34cb9..8bcc08a5 100644
--- a/src/pyobo/sources/cordis/__init__.py
+++ b/src/pyobo/sources/cordis/__init__.py
@@ -1,9 +1,11 @@
 """CORDIS sources."""
 
 from .cordis_basis import CordisBasisGetter
+from .cordis_organization import CordisOrganizationGetter
 from .cordis_project import CordisProjectGetter
 
 __all__ = [
     "CordisBasisGetter",
+    "CordisOrganizationGetter",
     "CordisProjectGetter",
 ]
diff --git a/src/pyobo/sources/cordis/cordis_basis.py b/src/pyobo/sources/cordis/cordis_basis.py
index 570c4f0b..673d8820 100644
--- a/src/pyobo/sources/cordis/cordis_basis.py
+++ b/src/pyobo/sources/cordis/cordis_basis.py
@@ -1,11 +1,9 @@
-"""Converter for CORDIS Projects."""
+"""Converter for CORDIS legal bases."""
 
 from collections.abc import Iterable
 
-from pystow.utils import open_zip_reader
-
-from pyobo import Obo, Term
-from pyobo.sources.cordis.utils import get_cordis_path
+from pyobo.sources.cordis.utils import open_cordis
+from pyobo.struct import Obo, Term
 
 __all__ = [
     "CordisBasisGetter",
@@ -15,7 +13,7 @@
 
 
 class CordisBasisGetter(Obo):
-    """An ontology representation of cordis legal bases."""
+    """An ontology representation of CORDIS legal bases."""
 
     ontology = PREFIX
     dynamic_version = True
@@ -25,15 +23,15 @@ def iter_terms(self, force: bool = False) -> Iterable[Term]:
         return iter_terms()
 
 
-def iter_terms() -> Iterable[Term]:
+def iter_terms(version: str | None = None) -> Iterable[Term]:
     """Iterate over CORDIS legal basis terms."""
-    path = get_cordis_path()
-    with open_zip_reader(path, "legalBasis.csv", delimiter=";") as reader:
-        _header = next(reader)
-        unique = {row[1] for row in reader}
-        for identifier in sorted(unique):
-            yield Term.from_triple(PREFIX, identifier)
+    with open_cordis("project.csv", version=version) as reader:
+        unique = {row["legalBasis"]: row["title"] for row in reader}
+        for identifier, name in sorted(unique):
+            yield Term.from_triple(PREFIX, identifier, name)
+
+    # TODO implement some kind of hierarchy?
 
 
 if __name__ == "__main__":
-    CordisBasisGetter.cli(["--obo"])
+    CordisBasisGetter.cli()
diff --git a/src/pyobo/sources/cordis/cordis_organization.py b/src/pyobo/sources/cordis/cordis_organization.py
new file mode 100644
index 00000000..06478a2c
--- /dev/null
+++ b/src/pyobo/sources/cordis/cordis_organization.py
@@ -0,0 +1,40 @@
+"""Converter for CORDIS organizations."""
+
+from collections.abc import Iterable
+
+from pyobo import Obo, Reference, Term
+from pyobo.sources.cordis.utils import open_cordis
+
+__all__ = [
+    "CordisOrganizationGetter",
+]
+
+PREFIX = "cordis.organization"
+
+
+class CordisOrganizationGetter(Obo):
+    """An ontology representation of CORDIS organizations."""
+
+    ontology = PREFIX
+    dynamic_version = True
+
+    def iter_terms(self, force: bool = False) -> Iterable[Term]:
+        """Iterate over terms in the ontology."""
+        return iter_terms()
+
+
+def iter_terms(version: str | None = None) -> Iterable[Term]:
+    """Iterate over CPT terms."""
+    # TODO might need to add additional parts
+    with open_cordis("organization.csv", version=version) as reader:
+        for row in reader:
+            term = Term(
+                reference=Reference(
+                    prefix="cordis.project", identifier=row["id"], name=row["title"]
+                ),
+            )
+            yield term
+
+
+if __name__ == "__main__":
+    CordisOrganizationGetter.cli(["--obo"])
diff --git a/src/pyobo/sources/cordis/cordis_project.py b/src/pyobo/sources/cordis/cordis_project.py
index 19840c9f..e3168f5d 100644
--- a/src/pyobo/sources/cordis/cordis_project.py
+++ b/src/pyobo/sources/cordis/cordis_project.py
@@ -1,13 +1,12 @@
-"""Converter for CORDIS Projects."""
+"""Converter for CORDIS projects."""
 
 from collections.abc import Iterable
 
 from curies.vocabulary import acronym
-from pystow.utils import open_zip_reader
 from tqdm import tqdm
 
 from pyobo import Obo, Reference, Term, TypeDef, default_reference
-from pyobo.sources.cordis.utils import get_cordis_path
+from pyobo.sources.cordis.utils import open_cordis
 
 __all__ = [
     "CordisProjectGetter",
@@ -15,7 +14,6 @@
 
 PREFIX = "cordis.project"
 
-
 # see euscivoc, which is in skosxl format
 
 HAS_LEGAL_BASIS = TypeDef(reference=default_reference(PREFIX, "hasLegalBasis"))
@@ -33,14 +31,10 @@ def iter_terms(self, force: bool = False) -> Iterable[Term]:
         return iter_terms()
 
 
-def iter_terms() -> Iterable[Term]:
-    """Iterate over CPT terms."""
-    path = get_cordis_path()
-    # TODO might need to add additional parts
-    with open_zip_reader(path, "project.csv", delimiter=";") as reader:
-        header = next(reader)
+def iter_terms(version: str | None = None) -> Iterable[Term]:
+    """Iterate over CORDIS project terms."""
+    with open_cordis("project.csv", version=version) as reader:
         for row in reader:
-            row = dict(zip(header, row, strict=False))
             term = Term(
                 reference=Reference(
                     prefix="cordis.project", identifier=row["id"], name=row["title"]
diff --git a/src/pyobo/sources/cordis/cordis_topic.py b/src/pyobo/sources/cordis/cordis_topic.py
new file mode 100644
index 00000000..6db2a99f
--- /dev/null
+++ b/src/pyobo/sources/cordis/cordis_topic.py
@@ -0,0 +1 @@
+"""Converter for CORDIS topics."""
diff --git a/src/pyobo/sources/cordis/utils.py b/src/pyobo/sources/cordis/utils.py
index 455d647d..3339c658 100644
--- a/src/pyobo/sources/cordis/utils.py
+++ b/src/pyobo/sources/cordis/utils.py
@@ -1,14 +1,27 @@
 """Utilities for CORDIS resources."""
 
+import csv
+from collections.abc import Generator
 from pathlib import Path
 
+from pystow.utils import open_zip_dict_reader
+
 from pyobo.utils.path import ensure_path
 
-__all__ = ["get_cordis_path"]
+__all__ = ["get_cordis_path", "open_cordis"]
 
 URL = "https://cordis.europa.eu/data/cordis-h2020projects-csv.zip"
 
 
-def get_cordis_path(version: str | None = None) -> Path:
+def get_cordis_path(*, version: str | None = None) -> Path:
     """Get the CORDIS data dump."""
     return ensure_path("cordis", url=URL, version=version)
+
+
+def open_cordis(
+    inner_path: str, *, version: str | None = None
+) -> Generator[csv.DictReader[str], None, None]:
+    """Open a CORDIS CSV."""
+    path = get_cordis_path(version=version)
+    with open_zip_dict_reader(path, inner_path, delimiter=";") as reader:
+        yield reader

From 3940d985b943b66f934b304519ecbf52309a7764 Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Mon, 18 May 2026 07:14:52 +0200
Subject: [PATCH 06/18] Update pyproject.toml

---
 pyproject.toml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pyproject.toml b/pyproject.toml
index 0d1eea8b..077ae207 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -70,7 +70,7 @@ dependencies = [
     "cachier",
     "pystow>=0.8.13",
     "bioversions>=0.10.11",
-    "bioregistry>=0.13.48",
+    "bioregistry>=0.13.53",
     "ssslm>=0.2.0",
     "zenodo-client>=0.4.1",
     "class-resolver>=0.7.1",

From 8b85c811abdc7635fb8c79bbd3cc328a8d314bd1 Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Mon, 18 May 2026 07:48:46 +0200
Subject: [PATCH 07/18] Update

---
 src/pyobo/sources/cordis/cordis_basis.py      |  8 ++---
 .../sources/cordis/cordis_organization.py     | 32 +++++++++++++------
 src/pyobo/sources/cordis/cordis_project.py    | 29 +++++++++++++----
 src/pyobo/sources/cordis/utils.py             | 16 +++++++++-
 4 files changed, 63 insertions(+), 22 deletions(-)

diff --git a/src/pyobo/sources/cordis/cordis_basis.py b/src/pyobo/sources/cordis/cordis_basis.py
index 673d8820..eabcd46f 100644
--- a/src/pyobo/sources/cordis/cordis_basis.py
+++ b/src/pyobo/sources/cordis/cordis_basis.py
@@ -2,20 +2,18 @@
 
 from collections.abc import Iterable
 
-from pyobo.sources.cordis.utils import open_cordis
+from pyobo.sources.cordis.utils import BASIS_PREFIX, open_cordis
 from pyobo.struct import Obo, Term
 
 __all__ = [
     "CordisBasisGetter",
 ]
 
-PREFIX = "cordis.basis"
-
 
 class CordisBasisGetter(Obo):
     """An ontology representation of CORDIS legal bases."""
 
-    ontology = PREFIX
+    ontology = BASIS_PREFIX
     dynamic_version = True
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
@@ -28,7 +26,7 @@ def iter_terms(version: str | None = None) -> Iterable[Term]:
     with open_cordis("project.csv", version=version) as reader:
         unique = {row["legalBasis"]: row["title"] for row in reader}
         for identifier, name in sorted(unique):
-            yield Term.from_triple(PREFIX, identifier, name)
+            yield Term.from_triple(BASIS_PREFIX, identifier, name)
 
     # TODO implement some kind of hierarchy?
 
diff --git a/src/pyobo/sources/cordis/cordis_organization.py b/src/pyobo/sources/cordis/cordis_organization.py
index 06478a2c..42afe2d3 100644
--- a/src/pyobo/sources/cordis/cordis_organization.py
+++ b/src/pyobo/sources/cordis/cordis_organization.py
@@ -2,20 +2,22 @@
 
 from collections.abc import Iterable
 
-from pyobo import Obo, Reference, Term
-from pyobo.sources.cordis.utils import open_cordis
+from curies import vocabulary as v
+
+from pyobo import Annotation, Obo, Reference, Term
+from pyobo.sources.cordis.utils import ORGANIZATION_PREFIX, open_cordis
+from pyobo.struct.typedef import has_homepage
 
 __all__ = [
     "CordisOrganizationGetter",
 ]
 
-PREFIX = "cordis.organization"
-
 
 class CordisOrganizationGetter(Obo):
     """An ontology representation of CORDIS organizations."""
 
-    ontology = PREFIX
+    ontology = ORGANIZATION_PREFIX
+    typedefs = [has_homepage]
     dynamic_version = True
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
@@ -24,15 +26,27 @@ def iter_terms(self, force: bool = False) -> Iterable[Term]:
 
 
 def iter_terms(version: str | None = None) -> Iterable[Term]:
-    """Iterate over CPT terms."""
-    # TODO might need to add additional parts
+    """Iterate over CORDIS organization terms."""
     with open_cordis("organization.csv", version=version) as reader:
+        seen = set()
         for row in reader:
+            identifier = row["organisationID"]
+            if identifier in seen:
+                continue
+            seen.add(identifier)
             term = Term(
                 reference=Reference(
-                    prefix="cordis.project", identifier=row["id"], name=row["title"]
-                ),
+                    prefix=ORGANIZATION_PREFIX, identifier=identifier, name=row["name"]
+                )
             )
+            if short_name := row["shortName"]:
+                term.append_synonym(short_name, type=v.abbreviation)
+            if url := row["organizationURL"]:
+                term.append_property(Annotation.uri(has_homepage, url))
+            if vat := row["vatNumber"]:
+                term.append_exact_match(Reference(prefix="vat", identifier=vat))
+            term.append_exact_match(Reference(prefix="eu.rcn", identifier=row["rcn"]))
+            # TODO city, country, nutsCode
             yield term
 
 
diff --git a/src/pyobo/sources/cordis/cordis_project.py b/src/pyobo/sources/cordis/cordis_project.py
index e3168f5d..1c5c2d36 100644
--- a/src/pyobo/sources/cordis/cordis_project.py
+++ b/src/pyobo/sources/cordis/cordis_project.py
@@ -6,23 +6,27 @@
 from tqdm import tqdm
 
 from pyobo import Obo, Reference, Term, TypeDef, default_reference
-from pyobo.sources.cordis.utils import open_cordis
+from pyobo.sources.cordis.utils import (
+    BASIS_PREFIX,
+    ORGANIZATION_PREFIX,
+    PROJECT_PREFIX,
+    open_cordis,
+)
+from pyobo.struct.typedef import has_participant
 
 __all__ = [
     "CordisProjectGetter",
 ]
 
-PREFIX = "cordis.project"
-
 # see euscivoc, which is in skosxl format
 
-HAS_LEGAL_BASIS = TypeDef(reference=default_reference(PREFIX, "hasLegalBasis"))
+HAS_LEGAL_BASIS = TypeDef(reference=default_reference(PROJECT_PREFIX, "hasLegalBasis"))
 
 
 class CordisProjectGetter(Obo):
     """An ontology representation of cordis projects."""
 
-    ontology = PREFIX
+    ontology = PROJECT_PREFIX
     typedefs = [HAS_LEGAL_BASIS]
     dynamic_version = True
 
@@ -33,6 +37,7 @@ def iter_terms(self, force: bool = False) -> Iterable[Term]:
 
 def iter_terms(version: str | None = None) -> Iterable[Term]:
     """Iterate over CORDIS project terms."""
+    terms: dict[str, Term] = {}
     with open_cordis("project.csv", version=version) as reader:
         for row in reader:
             term = Term(
@@ -43,7 +48,7 @@ def iter_terms(version: str | None = None) -> Iterable[Term]:
             )
             term.append_synonym(row["acronym"], type=acronym)
             term.append_property(
-                HAS_LEGAL_BASIS, Reference(prefix="cordis.basis", identifier=row["legalBasis"])
+                HAS_LEGAL_BASIS, Reference(prefix=BASIS_PREFIX, identifier=row["legalBasis"])
             )
 
             doi = row["grantDoi"]
@@ -53,7 +58,17 @@ def iter_terms(version: str | None = None) -> Iterable[Term]:
                 tqdm.write(f"[{term.curie}] problem with DOI: {doi}")
             else:
                 term.append_exact_match(doi_reference)
-            yield term
+            terms[term.identifier] = term
+
+    with open_cordis("organizations.csv", version=version) as reader:
+        for row in reader:
+            project_id = row["projectID"]
+            organization_id = row["organizationID"]
+            terms[project_id].append_relationship(
+                has_participant,
+                Reference(prefix=ORGANIZATION_PREFIX, identifier=organization_id),
+                # TODO can add all sorts of annotations from this file, like the cost, role, ordinal
+            )
 
 
 if __name__ == "__main__":
diff --git a/src/pyobo/sources/cordis/utils.py b/src/pyobo/sources/cordis/utils.py
index 3339c658..7294527e 100644
--- a/src/pyobo/sources/cordis/utils.py
+++ b/src/pyobo/sources/cordis/utils.py
@@ -2,22 +2,36 @@
 
 import csv
 from collections.abc import Generator
+from contextlib import contextmanager
 from pathlib import Path
 
 from pystow.utils import open_zip_dict_reader
 
 from pyobo.utils.path import ensure_path
 
-__all__ = ["get_cordis_path", "open_cordis"]
+__all__ = [
+    "BASIS_PREFIX",
+    "ORGANIZATION_PREFIX",
+    "PROJECT_PREFIX",
+    "URL",
+    "get_cordis_path",
+    "open_cordis",
+]
 
+#: A URL for the latest CORDIS data dump
 URL = "https://cordis.europa.eu/data/cordis-h2020projects-csv.zip"
 
+PROJECT_PREFIX = "cordis.project"
+ORGANIZATION_PREFIX = "cordis.organization"
+BASIS_PREFIX = "cordis.basis"
+
 
 def get_cordis_path(*, version: str | None = None) -> Path:
     """Get the CORDIS data dump."""
     return ensure_path("cordis", url=URL, version=version)
 
 
+@contextmanager
 def open_cordis(
     inner_path: str, *, version: str | None = None
 ) -> Generator[csv.DictReader[str], None, None]:

From aa4a941ace8929103fc5e2ec310eccf96c619162 Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Mon, 18 May 2026 07:54:12 +0200
Subject: [PATCH 08/18] Fix up

---
 src/pyobo/sources/cordis/cordis_basis.py        |  2 +-
 src/pyobo/sources/cordis/cordis_organization.py |  8 +++++---
 src/pyobo/sources/cordis/cordis_project.py      | 11 +++++++----
 3 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/src/pyobo/sources/cordis/cordis_basis.py b/src/pyobo/sources/cordis/cordis_basis.py
index eabcd46f..c5c8fc8a 100644
--- a/src/pyobo/sources/cordis/cordis_basis.py
+++ b/src/pyobo/sources/cordis/cordis_basis.py
@@ -25,7 +25,7 @@ def iter_terms(version: str | None = None) -> Iterable[Term]:
     """Iterate over CORDIS legal basis terms."""
     with open_cordis("project.csv", version=version) as reader:
         unique = {row["legalBasis"]: row["title"] for row in reader}
-        for identifier, name in sorted(unique):
+        for identifier, name in sorted(unique.items()):
             yield Term.from_triple(BASIS_PREFIX, identifier, name)
 
     # TODO implement some kind of hierarchy?
diff --git a/src/pyobo/sources/cordis/cordis_organization.py b/src/pyobo/sources/cordis/cordis_organization.py
index 42afe2d3..9aed07c7 100644
--- a/src/pyobo/sources/cordis/cordis_organization.py
+++ b/src/pyobo/sources/cordis/cordis_organization.py
@@ -4,7 +4,7 @@
 
 from curies import vocabulary as v
 
-from pyobo import Annotation, Obo, Reference, Term
+from pyobo import Obo, Reference, Term
 from pyobo.sources.cordis.utils import ORGANIZATION_PREFIX, open_cordis
 from pyobo.struct.typedef import has_homepage
 
@@ -12,6 +12,8 @@
     "CordisOrganizationGetter",
 ]
 
+ABBREVIATION = Reference.from_reference(v.abbreviation)
+
 
 class CordisOrganizationGetter(Obo):
     """An ontology representation of CORDIS organizations."""
@@ -40,9 +42,9 @@ def iter_terms(version: str | None = None) -> Iterable[Term]:
                 )
             )
             if short_name := row["shortName"]:
-                term.append_synonym(short_name, type=v.abbreviation)
+                term.append_synonym(short_name, type=ABBREVIATION)
             if url := row["organizationURL"]:
-                term.append_property(Annotation.uri(has_homepage, url))
+                term.annotate_uri(has_homepage, url)
             if vat := row["vatNumber"]:
                 term.append_exact_match(Reference(prefix="vat", identifier=vat))
             term.append_exact_match(Reference(prefix="eu.rcn", identifier=row["rcn"]))
diff --git a/src/pyobo/sources/cordis/cordis_project.py b/src/pyobo/sources/cordis/cordis_project.py
index 1c5c2d36..e22bcbfc 100644
--- a/src/pyobo/sources/cordis/cordis_project.py
+++ b/src/pyobo/sources/cordis/cordis_project.py
@@ -2,7 +2,7 @@
 
 from collections.abc import Iterable
 
-from curies.vocabulary import acronym
+from curies import vocabulary as v
 from tqdm import tqdm
 
 from pyobo import Obo, Reference, Term, TypeDef, default_reference
@@ -21,6 +21,7 @@
 # see euscivoc, which is in skosxl format
 
 HAS_LEGAL_BASIS = TypeDef(reference=default_reference(PROJECT_PREFIX, "hasLegalBasis"))
+ACRONYM = Reference.from_reference(v.acronym)
 
 
 class CordisProjectGetter(Obo):
@@ -35,7 +36,7 @@ def iter_terms(self, force: bool = False) -> Iterable[Term]:
         return iter_terms()
 
 
-def iter_terms(version: str | None = None) -> Iterable[Term]:
+def iter_terms(*, version: str | None = None) -> Iterable[Term]:
     """Iterate over CORDIS project terms."""
     terms: dict[str, Term] = {}
     with open_cordis("project.csv", version=version) as reader:
@@ -46,8 +47,8 @@ def iter_terms(version: str | None = None) -> Iterable[Term]:
                 ),
                 # definition=row['objective'],
             )
-            term.append_synonym(row["acronym"], type=acronym)
-            term.append_property(
+            term.append_synonym(row["acronym"], type=ACRONYM)
+            term.annotate_object(
                 HAS_LEGAL_BASIS, Reference(prefix=BASIS_PREFIX, identifier=row["legalBasis"])
             )
 
@@ -70,6 +71,8 @@ def iter_terms(version: str | None = None) -> Iterable[Term]:
                 # TODO can add all sorts of annotations from this file, like the cost, role, ordinal
             )
 
+    yield from terms.values()
+
 
 if __name__ == "__main__":
     CordisProjectGetter.cli(["--obo"])

From 2669049ecfe20b3953d7602dd166d47c9c19a8ea Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Mon, 18 May 2026 07:55:10 +0200
Subject: [PATCH 09/18] Cleanup

---
 src/pyobo/sources/cordis/cordis_organization.py | 2 +-
 src/pyobo/sources/cordis/cordis_project.py      | 2 +-
 src/pyobo/sources/cordis/cordis_topic.py        | 1 -
 3 files changed, 2 insertions(+), 3 deletions(-)
 delete mode 100644 src/pyobo/sources/cordis/cordis_topic.py

diff --git a/src/pyobo/sources/cordis/cordis_organization.py b/src/pyobo/sources/cordis/cordis_organization.py
index 9aed07c7..41125a03 100644
--- a/src/pyobo/sources/cordis/cordis_organization.py
+++ b/src/pyobo/sources/cordis/cordis_organization.py
@@ -53,4 +53,4 @@ def iter_terms(version: str | None = None) -> Iterable[Term]:
 
 
 if __name__ == "__main__":
-    CordisOrganizationGetter.cli(["--obo"])
+    CordisOrganizationGetter.cli()
diff --git a/src/pyobo/sources/cordis/cordis_project.py b/src/pyobo/sources/cordis/cordis_project.py
index e22bcbfc..3e7391b2 100644
--- a/src/pyobo/sources/cordis/cordis_project.py
+++ b/src/pyobo/sources/cordis/cordis_project.py
@@ -75,4 +75,4 @@ def iter_terms(*, version: str | None = None) -> Iterable[Term]:
 
 
 if __name__ == "__main__":
-    CordisProjectGetter.cli(["--obo"])
+    CordisProjectGetter.cli()
diff --git a/src/pyobo/sources/cordis/cordis_topic.py b/src/pyobo/sources/cordis/cordis_topic.py
deleted file mode 100644
index 6db2a99f..00000000
--- a/src/pyobo/sources/cordis/cordis_topic.py
+++ /dev/null
@@ -1 +0,0 @@
-"""Converter for CORDIS topics."""

From 6de93b21abae2cb843edeb585897e1c6fc4055de Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Mon, 18 May 2026 11:19:03 +0200
Subject: [PATCH 10/18] Update cordis_project.py

---
 src/pyobo/sources/cordis/cordis_project.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/pyobo/sources/cordis/cordis_project.py b/src/pyobo/sources/cordis/cordis_project.py
index 3e7391b2..ad0d6030 100644
--- a/src/pyobo/sources/cordis/cordis_project.py
+++ b/src/pyobo/sources/cordis/cordis_project.py
@@ -61,11 +61,11 @@ def iter_terms(*, version: str | None = None) -> Iterable[Term]:
                 term.append_exact_match(doi_reference)
             terms[term.identifier] = term
 
-    with open_cordis("organizations.csv", version=version) as reader:
+    with open_cordis("organization.csv", version=version) as reader:
         for row in reader:
             project_id = row["projectID"]
-            organization_id = row["organizationID"]
-            terms[project_id].append_relationship(
+            organization_id = row["organisationID"]
+            terms[project_id].annotate_object(
                 has_participant,
                 Reference(prefix=ORGANIZATION_PREFIX, identifier=organization_id),
                 # TODO can add all sorts of annotations from this file, like the cost, role, ordinal

From 5326fb9f9fb6301d71d2c8bc56855cd51b81278e Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Mon, 18 May 2026 13:43:44 +0200
Subject: [PATCH 11/18] Update

---
 src/pyobo/sources/__init__.py            |  8 +++++-
 src/pyobo/sources/cordis/__init__.py     |  2 ++
 src/pyobo/sources/cordis/cordis_topic.py | 33 ++++++++++++++++++++++++
 src/pyobo/sources/cordis/utils.py        | 11 +++++++-
 src/pyobo/struct/struct_utils.py         |  2 +-
 5 files changed, 53 insertions(+), 3 deletions(-)
 create mode 100644 src/pyobo/sources/cordis/cordis_topic.py

diff --git a/src/pyobo/sources/__init__.py b/src/pyobo/sources/__init__.py
index 370e9779..d61f344d 100644
--- a/src/pyobo/sources/__init__.py
+++ b/src/pyobo/sources/__init__.py
@@ -17,7 +17,12 @@
 from .clinicaltrials import ClinicalTrialsGetter
 from .complexportal import ComplexPortalGetter
 from .conso import CONSOGetter
-from .cordis import CordisBasisGetter, CordisOrganizationGetter, CordisProjectGetter
+from .cordis import (
+    CordisBasisGetter,
+    CordisOrganizationGetter,
+    CordisProjectGetter,
+    CordisTopicGetter,
+)
 from .cpt import CPTGetter
 from .credit import CreditGetter
 from .cvx import CVXGetter
@@ -100,6 +105,7 @@
     "CordisBasisGetter",
     "CordisOrganizationGetter",
     "CordisProjectGetter",
+    "CordisTopicGetter",
     "CreditGetter",
     "DepMapGetter",
     "DictybaseGetter",
diff --git a/src/pyobo/sources/cordis/__init__.py b/src/pyobo/sources/cordis/__init__.py
index 8bcc08a5..95a442df 100644
--- a/src/pyobo/sources/cordis/__init__.py
+++ b/src/pyobo/sources/cordis/__init__.py
@@ -3,9 +3,11 @@
 from .cordis_basis import CordisBasisGetter
 from .cordis_organization import CordisOrganizationGetter
 from .cordis_project import CordisProjectGetter
+from .cordis_topic import CordisTopicGetter
 
 __all__ = [
     "CordisBasisGetter",
     "CordisOrganizationGetter",
     "CordisProjectGetter",
+    "CordisTopicGetter",
 ]
diff --git a/src/pyobo/sources/cordis/cordis_topic.py b/src/pyobo/sources/cordis/cordis_topic.py
new file mode 100644
index 00000000..2864e956
--- /dev/null
+++ b/src/pyobo/sources/cordis/cordis_topic.py
@@ -0,0 +1,33 @@
+"""Converter for CORDIS topics."""
+
+from collections.abc import Iterable
+
+from pyobo.sources.cordis.utils import TOPIC_PREFIX, clean_topic_id, open_cordis
+from pyobo.struct import Obo, Term
+
+__all__ = [
+    "CordisTopicGetter",
+]
+
+
+class CordisTopicGetter(Obo):
+    """An ontology representation of CORDIS topics."""
+
+    ontology = TOPIC_PREFIX
+    dynamic_version = True
+
+    def iter_terms(self, force: bool = False) -> Iterable[Term]:
+        """Iterate over terms in the ontology."""
+        return iter_terms()
+
+
+def iter_terms(version: str | None = None) -> Iterable[Term]:
+    """Iterate over CORDIS topic terms."""
+    with open_cordis("topics.csv", version=version) as reader:
+        unique = {row["topic"]: row["title"] for row in reader}
+        for identifier, name in sorted(unique.items()):
+            yield Term.from_triple(TOPIC_PREFIX, clean_topic_id(identifier), name)
+
+
+if __name__ == "__main__":
+    CordisTopicGetter.cli(["--obo"])
diff --git a/src/pyobo/sources/cordis/utils.py b/src/pyobo/sources/cordis/utils.py
index 7294527e..f1864f80 100644
--- a/src/pyobo/sources/cordis/utils.py
+++ b/src/pyobo/sources/cordis/utils.py
@@ -13,7 +13,9 @@
     "BASIS_PREFIX",
     "ORGANIZATION_PREFIX",
     "PROJECT_PREFIX",
+    "TOPIC_PREFIX",
     "URL",
+    "clean_topic_id",
     "get_cordis_path",
     "open_cordis",
 ]
@@ -24,6 +26,7 @@
 PROJECT_PREFIX = "cordis.project"
 ORGANIZATION_PREFIX = "cordis.organization"
 BASIS_PREFIX = "cordis.basis"
+TOPIC_PREFIX = "cordis.topic"
 
 
 def get_cordis_path(*, version: str | None = None) -> Path:
@@ -37,5 +40,11 @@ def open_cordis(
 ) -> Generator[csv.DictReader[str], None, None]:
     """Open a CORDIS CSV."""
     path = get_cordis_path(version=version)
-    with open_zip_dict_reader(path, inner_path, delimiter=";") as reader:
+    with open_zip_dict_reader(path, inner_path, delimiter=";", quoting=csv.QUOTE_MINIMAL) as reader:
         yield reader
+
+
+def clean_topic_id(topic_id: str) -> str:
+    """Fix CORDIS topic IDs that might have spaces in them."""
+    # identifier cleanup needed for `RISK FINANCE` and `SCIENCE WAF SOCIETY`
+    return topic_id.replace(" ", "%20")
diff --git a/src/pyobo/struct/struct_utils.py b/src/pyobo/struct/struct_utils.py
index b05463db..47ecb6be 100644
--- a/src/pyobo/struct/struct_utils.py
+++ b/src/pyobo/struct/struct_utils.py
@@ -976,7 +976,7 @@ def _iterate_obo_relations(
                     end = reference_escape(value, ontology_prefix=ontology_prefix)
                     name = value.name
                 case _:
-                    raise TypeError(f"got unexpected value: {values}")
+                    raise TypeError(f"got unexpected type {type(values)} with value: {values}")
             end += _get_obo_trailing_modifiers(
                 predicate, value, annotations, ontology_prefix=ontology_prefix
             )

From 0b1fae54f32ff34d7c55db15e7a1a925deae841e Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Mon, 18 May 2026 14:08:29 +0200
Subject: [PATCH 12/18] Add test for quotes in string literals

---
 .../test_struct/test_obo/test_struct_term.py  | 20 +++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/tests/test_struct/test_obo/test_struct_term.py b/tests/test_struct/test_obo/test_struct_term.py
index b8ed9a58..90ce971a 100644
--- a/tests/test_struct/test_obo/test_struct_term.py
+++ b/tests/test_struct/test_obo/test_struct_term.py
@@ -711,6 +711,26 @@ def test_12_property_string_with_language(self) -> None:
             """,
         )
 
+    def test_12_property_string_with_quote(self) -> None:
+        """Test emitting a string property literal with a quote in it."""
+        term = Term(reference=LYSINE_DEHYDROGENASE_ACT)
+        term.annotate_string(RO_DUMMY, "\"value\" added")
+        self.assert_obo_stanza(
+            term,
+            obo="""\
+                [Term]
+                id: GO:0050069
+                name: lysine dehydrogenase activity
+                property_value: RO:1234567 "\\"value\\" added" xsd:string
+            """,
+            typedefs={RO_DUMMY.pair: RO_DUMMY},
+            ofn="""\
+                Declaration(Class(GO:0050069))
+                AnnotationAssertion(rdfs:label GO:0050069 "lysine dehydrogenase activity")
+                AnnotationAssertion(RO:1234567 GO:0050069 "\\"value\\" added"@en)
+            """,
+        )
+
     def test_12_property_integer(self) -> None:
         """Test emitting property literals that were annotated as a boolean."""
         term = Term(reference=LYSINE_DEHYDROGENASE_ACT)

From 57eb34842bf4e876d8eb57ded90f559b1aaa122b Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Mon, 18 May 2026 14:08:32 +0200
Subject: [PATCH 13/18] Update struct_utils.py

---
 src/pyobo/struct/struct_utils.py | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/src/pyobo/struct/struct_utils.py b/src/pyobo/struct/struct_utils.py
index 47ecb6be..29507562 100644
--- a/src/pyobo/struct/struct_utils.py
+++ b/src/pyobo/struct/struct_utils.py
@@ -501,6 +501,16 @@ def annotate_datetime(
         """Append a datetime annotation."""
         return self.annotate_literal(prop, OBOLiteral.datetime(value), annotations=annotations)
 
+    def annotate_date(
+        self,
+        prop: ReferenceHint,
+        value: datetime.datetime | datetime.date | str,
+        *,
+        annotations: Iterable[Annotation] | None = None,
+    ) -> Self:
+        """Append a date annotation."""
+        return self.annotate_literal(prop, OBOLiteral.date(value), annotations=annotations)
+
     def _iterate_obo_properties(
         self,
         *,

From 1e03a97608d69432a51525e5ab20daa1bfafc9ea Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Mon, 18 May 2026 14:08:38 +0200
Subject: [PATCH 14/18] Update reference.py

---
 src/pyobo/struct/reference.py | 34 ++++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/src/pyobo/struct/reference.py b/src/pyobo/struct/reference.py
index 10802986..599384ad 100644
--- a/src/pyobo/struct/reference.py
+++ b/src/pyobo/struct/reference.py
@@ -6,6 +6,8 @@
 import logging
 from collections import Counter
 from collections.abc import Iterable, Sequence
+from datetime import date as date_cls
+from datetime import datetime as datetime_cls
 from typing import Any, NamedTuple
 
 import bioregistry
@@ -14,6 +16,7 @@
 import pytz
 from bioregistry import NormalizedNamableReference as Reference
 from curies import ReferenceTuple
+from curies import vocabulary as v
 from curies.preprocessing import BlocklistError
 
 from ..identifier_utils import (
@@ -304,9 +307,7 @@ def _parse_reference_or_uri_literal(
             return None
 
 
-unspecified_matching = Reference(
-    prefix="semapv", identifier="UnspecifiedMatching", name="unspecified matching process"
-)
+unspecified_matching = Reference.from_reference(v.unspecified_matching_process)
 
 
 class OBOLiteral(NamedTuple):
@@ -319,44 +320,53 @@ class OBOLiteral(NamedTuple):
     @classmethod
     def string(cls, value: str, *, language: str | None = None) -> OBOLiteral:
         """Get a string literal."""
-        return cls(value, curies.Reference(prefix="xsd", identifier="string"), language)
+        return cls(value, v.xsd_string, language)
 
     @classmethod
     def boolean(cls, value: bool) -> OBOLiteral:
         """Get a boolean literal."""
-        return cls(str(value).lower(), curies.Reference(prefix="xsd", identifier="boolean"), None)
+        return cls(str(value).lower(), v.xsd_boolean, None)
 
     @classmethod
     def decimal(cls, value: float) -> OBOLiteral:
         """Get a decimal literal."""
-        return cls(str(value), curies.Reference(prefix="xsd", identifier="decimal"), None)
+        return cls(str(value), v.xsd_decimal, None)
 
     @classmethod
     def float(cls, value: float) -> OBOLiteral:
         """Get a float literal."""
-        return cls(str(value), curies.Reference(prefix="xsd", identifier="float"), None)
+        return cls(str(value), v.xsd_float, None)
 
     @classmethod
     def integer(cls, value: int | str) -> OBOLiteral:
         """Get a integer literal."""
-        return cls(str(int(value)), curies.Reference(prefix="xsd", identifier="integer"), None)
+        return cls(str(int(value)), v.xsd_integer, None)
 
     @classmethod
     def year(cls, value: int | str) -> OBOLiteral:
         """Get a year (gYear) literal."""
-        return cls(str(int(value)), curies.Reference(prefix="xsd", identifier="gYear"), None)
+        return cls(str(int(value)), v.xsd_year, None)
 
     @classmethod
     def uri(cls, uri: str) -> OBOLiteral:
         """Get a string literal for a URI."""
-        return cls(uri, curies.Reference(prefix="xsd", identifier="anyURI"), None)
+        return cls(uri, v.xsd_uri, None)
+
+    @classmethod
+    def datetime(cls, dt: datetime_cls | str) -> OBOLiteral:
+        """Get a datetime literal."""
+        if isinstance(dt, str):
+            dt = _parse_datetime(dt)
+        return cls(dt.isoformat(), v.xsd_datetime, None)
 
     @classmethod
-    def datetime(cls, dt: datetime.datetime | str) -> OBOLiteral:
+    def date(cls, dt: datetime_cls | date_cls | str) -> OBOLiteral:
         """Get a datetime literal."""
         if isinstance(dt, str):
             dt = _parse_datetime(dt)
-        return cls(dt.isoformat(), curies.Reference(prefix="xsd", identifier="dateTime"), None)
+        if isinstance(dt, datetime.datetime):
+            dt = dt.date()
+        return cls(dt.isoformat(), v.xsd_date, None)
 
 
 def _parse_datetime(dd: str) -> datetime.datetime:

From 920958d79120c1738a67b234da14752c5977b76e Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Mon, 18 May 2026 14:08:39 +0200
Subject: [PATCH 15/18] Update cordis_project.py

---
 src/pyobo/sources/cordis/cordis_project.py | 97 +++++++++++++++++++++-
 1 file changed, 93 insertions(+), 4 deletions(-)

diff --git a/src/pyobo/sources/cordis/cordis_project.py b/src/pyobo/sources/cordis/cordis_project.py
index ad0d6030..0694228c 100644
--- a/src/pyobo/sources/cordis/cordis_project.py
+++ b/src/pyobo/sources/cordis/cordis_project.py
@@ -1,8 +1,10 @@
 """Converter for CORDIS projects."""
 
+from collections import Counter
 from collections.abc import Iterable
 
 from curies import vocabulary as v
+from tabulate import tabulate
 from tqdm import tqdm
 
 from pyobo import Obo, Reference, Term, TypeDef, default_reference
@@ -10,6 +12,8 @@
     BASIS_PREFIX,
     ORGANIZATION_PREFIX,
     PROJECT_PREFIX,
+    TOPIC_PREFIX,
+    clean_topic_id,
     open_cordis,
 )
 from pyobo.struct.typedef import has_participant
@@ -20,7 +24,45 @@
 
 # see euscivoc, which is in skosxl format
 
-HAS_LEGAL_BASIS = TypeDef(reference=default_reference(PROJECT_PREFIX, "hasLegalBasis"))
+PROJECT = Term.from_triple("foaf", "Project", "project")
+STATUS = Term(reference=default_reference(PROJECT_PREFIX, "status"))
+KEY_TO_STATUS = {
+    "CLOSED": Term(reference=default_reference(PROJECT_PREFIX, "closed")).append_parent(STATUS),
+    "SIGNED": Term(reference=default_reference(PROJECT_PREFIX, "signed")).append_parent(STATUS),
+    "TERMINATED": Term(reference=default_reference(PROJECT_PREFIX, "terminated")).append_parent(
+        STATUS
+    ),
+}
+
+HAS_LEGAL_BASIS = TypeDef(
+    reference=default_reference(PROJECT_PREFIX, "hasLegalBasis"), domain=PROJECT.reference
+)
+HAS_TOPIC = TypeDef(
+    reference=default_reference(PROJECT_PREFIX, "hasTopic"), domain=PROJECT.reference
+)
+HAS_FUNDING_SCHEME = TypeDef(
+    reference=default_reference(PROJECT_PREFIX, "hasFundingScheme"),
+    domain=PROJECT.reference,
+    range=Reference.from_reference(v.xsd_string),
+)
+HAS_KEYWORD = TypeDef(  # TODO replace with SDO
+    reference=default_reference(PROJECT_PREFIX, "hasKeyword"),
+    range=Reference.from_reference(v.xsd_string),
+    domain=PROJECT.reference,
+)
+HAS_STATUS = TypeDef(
+    reference=default_reference(PROJECT_PREFIX, "hasStatus"), domain=PROJECT.reference
+)
+HAS_START = TypeDef(
+    reference=default_reference(PROJECT_PREFIX, "hasStart"),
+    domain=PROJECT.reference,
+    range=Reference.from_reference(v.xsd_date),
+)
+HAS_END = TypeDef(
+    reference=default_reference(PROJECT_PREFIX, "hasEnd"),
+    domain=PROJECT.reference,
+    range=Reference.from_reference(v.xsd_date),
+)
 ACRONYM = Reference.from_reference(v.acronym)
 
 
@@ -28,8 +70,17 @@ class CordisProjectGetter(Obo):
     """An ontology representation of cordis projects."""
 
     ontology = PROJECT_PREFIX
-    typedefs = [HAS_LEGAL_BASIS]
+    typedefs = [
+        HAS_LEGAL_BASIS,
+        HAS_TOPIC,
+        HAS_FUNDING_SCHEME,
+        HAS_KEYWORD,
+        HAS_STATUS,
+        HAS_START,
+        HAS_END,
+    ]
     dynamic_version = True
+    root_terms = [STATUS.reference, PROJECT.reference]
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
         """Iterate over terms in the ontology."""
@@ -39,6 +90,7 @@ def iter_terms(self, force: bool = False) -> Iterable[Term]:
 def iter_terms(*, version: str | None = None) -> Iterable[Term]:
     """Iterate over CORDIS project terms."""
     terms: dict[str, Term] = {}
+    scheme_counter: Counter[str] = Counter()
     with open_cordis("project.csv", version=version) as reader:
         for row in reader:
             term = Term(
@@ -46,7 +98,7 @@ def iter_terms(*, version: str | None = None) -> Iterable[Term]:
                     prefix="cordis.project", identifier=row["id"], name=row["title"]
                 ),
                 # definition=row['objective'],
-            )
+            ).append_parent(PROJECT)
             term.append_synonym(row["acronym"], type=ACRONYM)
             term.annotate_object(
                 HAS_LEGAL_BASIS, Reference(prefix=BASIS_PREFIX, identifier=row["legalBasis"])
@@ -57,22 +109,59 @@ def iter_terms(*, version: str | None = None) -> Iterable[Term]:
                 doi_reference = Reference(prefix="doi", identifier=doi)
             except ValueError:
                 tqdm.write(f"[{term.curie}] problem with DOI: {doi}")
+                continue
             else:
                 term.append_exact_match(doi_reference)
+
+            try:
+                rcn_id = Reference(prefix="eu.rcn", identifier=row["rcn"])
+            except ValueError:
+                pass  # this is probably the same offset issue as above
+                # tqdm.write(f"[{term.curie}] problem with RCN: {doi}")
+            else:
+                term.append_exact_match(rcn_id)
+
+            for topic in row["topics"].split(","):
+                term.annotate_object(
+                    HAS_TOPIC, Reference(prefix=TOPIC_PREFIX, identifier=clean_topic_id(topic))
+                )
+
+            for keyword in row["keywords"].split(","):
+                if keyword_stripped := keyword.strip().strip('"').strip():
+                    term.annotate_string(HAS_KEYWORD, keyword_stripped)
+
+            if funding_scheme := row["fundingScheme"]:
+                scheme_counter[row["fundingScheme"]] += 1
+                term.annotate_string(HAS_FUNDING_SCHEME, funding_scheme)
+
+            if start_date := row["startDate"]:
+                term.annotate_date(HAS_START, start_date)
+            if end_date := row["endDate"]:
+                term.annotate_date(HAS_END, end_date)
+
+            term.annotate_object(HAS_STATUS, KEY_TO_STATUS[row["status"]])
+
             terms[term.identifier] = term
 
+    tqdm.write(tabulate(scheme_counter.most_common()))
+
     with open_cordis("organization.csv", version=version) as reader:
         for row in reader:
             project_id = row["projectID"]
             organization_id = row["organisationID"]
+            if project_id not in terms:
+                continue
             terms[project_id].annotate_object(
                 has_participant,
                 Reference(prefix=ORGANIZATION_PREFIX, identifier=organization_id),
                 # TODO can add all sorts of annotations from this file, like the cost, role, ordinal
             )
 
+    yield PROJECT
+    yield STATUS
+    yield from KEY_TO_STATUS.values()
     yield from terms.values()
 
 
 if __name__ == "__main__":
-    CordisProjectGetter.cli()
+    CordisProjectGetter.cli(["--obo"])

From f6b2f57b374c8875eb4a715474226e9604b625c7 Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Mon, 18 May 2026 14:08:45 +0200
Subject: [PATCH 16/18] Update test_struct_term.py

---
 tests/test_struct/test_obo/test_struct_term.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/test_struct/test_obo/test_struct_term.py b/tests/test_struct/test_obo/test_struct_term.py
index 90ce971a..1e36d3b3 100644
--- a/tests/test_struct/test_obo/test_struct_term.py
+++ b/tests/test_struct/test_obo/test_struct_term.py
@@ -714,7 +714,7 @@ def test_12_property_string_with_language(self) -> None:
     def test_12_property_string_with_quote(self) -> None:
         """Test emitting a string property literal with a quote in it."""
         term = Term(reference=LYSINE_DEHYDROGENASE_ACT)
-        term.annotate_string(RO_DUMMY, "\"value\" added")
+        term.annotate_string(RO_DUMMY, '"value" added')
         self.assert_obo_stanza(
             term,
             obo="""\

From d87910531352e65b1ee30d9394dee0015b814100 Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Mon, 18 May 2026 14:28:23 +0200
Subject: [PATCH 17/18] Up

---
 src/pyobo/sources/cordis/cordis_basis.py        | 2 ++
 src/pyobo/sources/cordis/cordis_organization.py | 2 ++
 src/pyobo/sources/cordis/cordis_project.py      | 2 ++
 src/pyobo/sources/cordis/cordis_topic.py        | 2 ++
 src/pyobo/sources/cordis/utils.py               | 2 ++
 5 files changed, 10 insertions(+)

diff --git a/src/pyobo/sources/cordis/cordis_basis.py b/src/pyobo/sources/cordis/cordis_basis.py
index c5c8fc8a..c722af52 100644
--- a/src/pyobo/sources/cordis/cordis_basis.py
+++ b/src/pyobo/sources/cordis/cordis_basis.py
@@ -1,5 +1,7 @@
 """Converter for CORDIS legal bases."""
 
+from __future__ import annotations
+
 from collections.abc import Iterable
 
 from pyobo.sources.cordis.utils import BASIS_PREFIX, open_cordis
diff --git a/src/pyobo/sources/cordis/cordis_organization.py b/src/pyobo/sources/cordis/cordis_organization.py
index 41125a03..d754f6f1 100644
--- a/src/pyobo/sources/cordis/cordis_organization.py
+++ b/src/pyobo/sources/cordis/cordis_organization.py
@@ -1,5 +1,7 @@
 """Converter for CORDIS organizations."""
 
+from __future__ import annotations
+
 from collections.abc import Iterable
 
 from curies import vocabulary as v
diff --git a/src/pyobo/sources/cordis/cordis_project.py b/src/pyobo/sources/cordis/cordis_project.py
index 0694228c..71186e8b 100644
--- a/src/pyobo/sources/cordis/cordis_project.py
+++ b/src/pyobo/sources/cordis/cordis_project.py
@@ -1,5 +1,7 @@
 """Converter for CORDIS projects."""
 
+from __future__ import annotations
+
 from collections import Counter
 from collections.abc import Iterable
 
diff --git a/src/pyobo/sources/cordis/cordis_topic.py b/src/pyobo/sources/cordis/cordis_topic.py
index 2864e956..12b57566 100644
--- a/src/pyobo/sources/cordis/cordis_topic.py
+++ b/src/pyobo/sources/cordis/cordis_topic.py
@@ -1,5 +1,7 @@
 """Converter for CORDIS topics."""
 
+from __future__ import annotations
+
 from collections.abc import Iterable
 
 from pyobo.sources.cordis.utils import TOPIC_PREFIX, clean_topic_id, open_cordis
diff --git a/src/pyobo/sources/cordis/utils.py b/src/pyobo/sources/cordis/utils.py
index f1864f80..d24ec9a8 100644
--- a/src/pyobo/sources/cordis/utils.py
+++ b/src/pyobo/sources/cordis/utils.py
@@ -1,5 +1,7 @@
 """Utilities for CORDIS resources."""
 
+from __future__ import annotations
+
 import csv
 from collections.abc import Generator
 from contextlib import contextmanager

From f8ec630f93820139363663f50d101b9464754475 Mon Sep 17 00:00:00 2001
From: Charles Tapley Hoyt <cthoyt@gmail.com>
Date: Mon, 18 May 2026 15:00:44 +0200
Subject: [PATCH 18/18] Finish

---
 src/pyobo/sources/cordis/cordis_project.py | 11 ++++++-----
 src/pyobo/sources/cordis/cordis_topic.py   |  2 +-
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/src/pyobo/sources/cordis/cordis_project.py b/src/pyobo/sources/cordis/cordis_project.py
index 71186e8b..ef16ff5c 100644
--- a/src/pyobo/sources/cordis/cordis_project.py
+++ b/src/pyobo/sources/cordis/cordis_project.py
@@ -58,12 +58,12 @@
 HAS_START = TypeDef(
     reference=default_reference(PROJECT_PREFIX, "hasStart"),
     domain=PROJECT.reference,
-    range=Reference.from_reference(v.xsd_date),
+    range=Reference.from_reference(v.xsd_datetime),
 )
 HAS_END = TypeDef(
     reference=default_reference(PROJECT_PREFIX, "hasEnd"),
     domain=PROJECT.reference,
-    range=Reference.from_reference(v.xsd_date),
+    range=Reference.from_reference(v.xsd_datetime),
 )
 ACRONYM = Reference.from_reference(v.acronym)
 
@@ -136,10 +136,11 @@ def iter_terms(*, version: str | None = None) -> Iterable[Term]:
                 scheme_counter[row["fundingScheme"]] += 1
                 term.annotate_string(HAS_FUNDING_SCHEME, funding_scheme)
 
+            # switch to date after https://github.com/protegeproject/protege/issues/1343
             if start_date := row["startDate"]:
-                term.annotate_date(HAS_START, start_date)
+                term.annotate_datetime(HAS_START, start_date)
             if end_date := row["endDate"]:
-                term.annotate_date(HAS_END, end_date)
+                term.annotate_datetime(HAS_END, end_date)
 
             term.annotate_object(HAS_STATUS, KEY_TO_STATUS[row["status"]])
 
@@ -166,4 +167,4 @@ def iter_terms(*, version: str | None = None) -> Iterable[Term]:
 
 
 if __name__ == "__main__":
-    CordisProjectGetter.cli(["--obo"])
+    CordisProjectGetter.cli()
diff --git a/src/pyobo/sources/cordis/cordis_topic.py b/src/pyobo/sources/cordis/cordis_topic.py
index 12b57566..5baf298c 100644
--- a/src/pyobo/sources/cordis/cordis_topic.py
+++ b/src/pyobo/sources/cordis/cordis_topic.py
@@ -32,4 +32,4 @@ def iter_terms(version: str | None = None) -> Iterable[Term]:
 
 
 if __name__ == "__main__":
-    CordisTopicGetter.cli(["--obo"])
+    CordisTopicGetter.cli()