OAEI Bio-ML is a ML-friendly biomedical track for equivalence and subsumption matching over three whole biomedical ontologies — NCIT–DOID, SNOMED–FMA and SNOMED–NCIT. Systems are scored across two CodaBench competitions.
The tasks
Track 1 measures whole-ontology equivalence matching two ways — globally (a full alignment) and locally (ranked candidates).
Submit one full alignment per pair (full OWL IRIs). Public
refs_equiv/train.tsv and refs_equiv/valid.tsv per pair
(repaired basis); the test reference is hidden and scored
organiser-side. Headline is the repaired, coherence-aware P/R/F1,
with a reasoner-checked Global Coherence score.
For each source entity, rank a fixed candidate pool best-first. The public
*.test.cands.tsv are gold-stripped. Scored with
MRR and Hits@{1,5,10}, macro-averaged over the
three pairs.
Data
The 2026 task data is distributed on the Hugging Face Hub as
OAEI-ML/bio-ml (edition tag
2026). It is publicly available
and downloads without gating (entity IRIs only); the download now also bundles the
NCIT, DOID and FMA ontology files. The self-contained
scoring_kit/ ships separately with the track repository. The only
source not included is SNOMED CT (for the two SNOMED pairs), obtained
separately under an Affiliate Licence or by contacting us for a research-only copy.
git clone https://github.com/liseda-lab/OAEI-Bio-MLhf download OAEI-ML/bio-ml --repo-type dataset --revision 2026 --local-dir ./bio-ml
The Hugging Face download holds the per-pair task files and the NCIT, DOID and FMA ontology
files; the self-contained scoring_kit/ (validators and self-scorers)
comes from the track repository, cloned above. SNOMED CT is the only source
you obtain yourself — see the ontologies page for the
licence and how, and the quickstart for the full
walk-through. Track repository: liseda-lab/OAEI-Bio-ML.
Submit
Each scored subtrack has its own CodaBench competition. Validate and (where possible) self-score locally with the scoring kit, then submit. Both portals are open as of 12 July 2026. As with every OAEI track, your system must be registered with the OAEI 2026 campaign (via its registration form) before you submit; a CodaBench account alone is not OAEI registration.
| Competition | Submission portal |
|---|---|
| Track 1 · Subtrack 1 — Global equivalence alignment | Open on CodaBench |
| Track 1 · Subtrack 2 — Local equivalence ranking | Open on CodaBench |
Organiser-run baselines are published on the baselines page; participant standings appear on results now that the window is open.
__MACOSX files the scorer can read instead of your file, and filenames
without the hyphenated pair slug are never matched. See
submission support for the fix.
Timeline
The vocabularies
NCIT, DOID, SNOMED CT and FMA are matched across the three pairs; MONDO and the UMLS Metathesaurus underlie the reference construction. NCIT, DOID and FMA ship with the download; only SNOMED CT is obtained separately — see ontologies for licences and how.
Part of the OAEI
OAEI Bio-ML runs under the Ontology Alignment Evaluation Initiative — the long-running campaign that benchmarks ontology-matching systems. It continues the machine-learning-friendly Bio-ML datasets, which superseded the LargeBio track in 2022.
Bio-ML is one of the OAEI's biomedical tracks; its results feed the annual OAEI campaign. The earlier LargeBio track was retired when Bio-ML launched in 2022.
The OAEI-ML 2026 evaluation tracks are OAEI Bio-ML (this track) and DISO-OAEI. A proud member of the OAEI.
Citation
A citation for the 2026 edition is pending and will be published here once minted. The benchmark design follows the original machine-learning-friendly Bio-ML datasets (He et al.). Until the edition DOI is available, cite the dataset release:
OAEI Bio-ML 2026 [Data set]. Hugging Face. huggingface.co/datasets/OAEI-ML/bio-ml (edition tag 2026).
People
Jon Dilworth, Pedro Cotovio, Ernesto Jiménez-Ruiz, and Catia Pesquita.
Questions or corrections: open an issue on the track repository or email contact@oaei-ml.org.
Part of the Ontology Alignment Evaluation Initiative.