Biomedical ontology alignment as typed link prediction
Systems receive a source concept and a fixed set of target candidates, then rank candidate–relation pairs for equivalence or directional subsumption — one familiar interface for graph, text, and neuro-symbolic methods.
Source and target denote the same disease. Under the preferred typed metric this is the only fully relevant prediction — entity and relation both match the reference — so a strong system ranks it first.
Illustrative example (NCIT → DOID). The live site renders from the public release; hidden test data is never shown.
One graph, three tasks, one primary metric
BioKG-Align runs two tracks — the main track, summarised here, and a complex track on OWL class-expression generation (more in the FAQ).
- 5 track ontologies
- NCIT, DOID, ORDO, SNOMED, FMA — projected into one knowledge graph.
- 3 task pairs
NCIT-DOID,SNOMED-FMA,SNOMED-NCIT.- Metrics
- Primary: Macro Preferred Typed (Relation-Aware) MRR. Secondary: Hierarchy-Aware Typed nDCG@10.
- Candidate sets
- 50 target candidates × 3 relations = 150 scored rows per query.
- Three methodological entry points
- Triples → + node properties → + Datalog rules — graph, text, and neuro-symbolic methods.
The unified graph spans multiple projected ontologies with three task pairs.
- Input
- A source entity and a fixed candidate set, per query.
- Output
- A ranked list of (candidate, relation) pairs.
- Correctness
- A hit needs both the target entity and the relation to match the hidden reference.
Current competition status
Status: In preparation
Latest (kit v0.3.2):
the entity set is now classes only — the 137 SNOMED concepts that function as
properties in SNOMED's own OWL (but that RF2 lists as ordinary concepts) are
excluded from entities and queries, keeping their role as relation types. The released Datalog facts remain
curated so the shipped theory cannot contradict the reference alignment; canary coherence checks are also sound with respect to candidate
mappings.
Datalog facts ship as Soufflé .input TSVs runnable at release scale.
- Starting Kit Release
- TBA Provisional
- Dataset Publication
- TBA Provisional
- Competition Proposal Acceptance Decision
- TBA Provisional
- Competition Starts, Leaderboard Opens
- TBA Provisional
- Competition Ends
- TBA Provisional