AI semantics for biomedical data integration
- 1EMBL-EBI, Hinxton, UK
Abstract
Researchers increasingly need to explore hypotheses that span multimodal data across different scales, organisms, and domains. In practice, this requires connecting knowledge across fragmented databases with incompatible APIs and heterogeneous annotation practices. Large language model (LLM) agents can automate this data integration process, but grounding LLM agent outputs in scientifically correct sources of truth remains a significant challenge. Here we describe our deployment of a novel AI semantics workflow using LLM agents to enable scalable data integration, grounded in biological knowledge in the form of ontologies. Our workflow comprises (1) a multi-agent system curating scientific knowledge across ontologies using the Ontology Lookup Service (OLS) as grounding; (2) an LLM embedding service to enable interoperability between scientific databases by mapping ontology terms; and (3) GrEBI, a knowledge graph and Model Context Protocol (MCP) server enabling LLM agents to conduct cross-cutting, multi-omic biomedical queries.
Related
- Total Integration – reviving the Biomedical Platform as an analytical tool
- A population code for semantics in human hippocampus
- NeuroLens: Learning Latent Embeddings of Neural Semantics from Chronic Recordings
- Digital twins in agriculture: A systematic literature review on modeling, semantics, and interoperability
- Active Visual Semantics: A large-scale MEG and eye-tracking dataset for understanding visual intelligence in action
BibTeX
@misc{mclaughlin2026semantics,
title = {{AI semantics for biomedical data integration}},
author = {J. McLaughlin and A. Puig-Barbe and A. Ibrahim and D. Pava and Z. M. Pendlington and N. Matentzoglu and E. Sollis and A. Foreman and R. Wilson and F. Lopez Gomez and L. Harris and Y. Adeleye and S. Kaur and B. Meldal and D. Smedley and H. Parkinson},
howpublished = {bioRxiv},
year = {2026},
month = aug,
doi = {10.64898/2026.08.03.742514},
url = {https://www.biorxiv.org/content/10.64898/2026.08.03.742514v2},
note = {CC BY},
}
RIS
TY - UNPB
TI - AI semantics for biomedical data integration
AU - J. McLaughlin
AU - A. Puig-Barbe
AU - A. Ibrahim
AU - D. Pava
AU - Z. M. Pendlington
AU - N. Matentzoglu
AU - E. Sollis
AU - A. Foreman
AU - R. Wilson
AU - F. Lopez Gomez
AU - L. Harris
AU - Y. Adeleye
AU - S. Kaur
AU - B. Meldal
AU - D. Smedley
AU - H. Parkinson
PY - 2026
DA - 2026/08/03
PB - bioRxiv
DO - 10.64898/2026.08.03.742514
UR - https://www.biorxiv.org/content/10.64898/2026.08.03.742514v2
AB - Researchers increasingly need to explore hypotheses that span multimodal data across different scales, organisms, and domains. In practice, this requires connecting knowledge across fragmented databases with incompatible APIs and heterogeneous annotation practices. Large language model (LLM) agents can automate this data integration process, but grounding LLM agent outputs in scientifically correct sources of truth remains a significant challenge. Here we describe our deployment of a novel AI semantics workflow using LLM agents to enable scalable data integration, grounded in biological knowledge in the form of ontologies. Our workflow comprises (1) a multi-agent system curating scientific knowledge across ontologies using the Ontology Lookup Service (OLS) as grounding; (2) an LLM embedding service to enable interoperability between scientific databases by mapping ontology terms; and (3) GrEBI, a knowledge graph and Model Context Protocol (MCP) server enabling LLM agents to conduct cross-cutting, multi-omic biomedical queries.
ER -