From 777b8905188af5fe1b63cad304eedac9f6c61a5c Mon Sep 17 00:00:00 2001 From: Phil Reed Date: Tue, 9 Dec 2025 09:41:40 +0000 Subject: [PATCH] Create 2025-12-09-BHEUPreprint.md --- pages/_news/2025-12-09-BHEUPreprint.md | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) create mode 100644 pages/_news/2025-12-09-BHEUPreprint.md diff --git a/pages/_news/2025-12-09-BHEUPreprint.md b/pages/_news/2025-12-09-BHEUPreprint.md new file mode 100644 index 00000000..71e5ac16 --- /dev/null +++ b/pages/_news/2025-12-09-BHEUPreprint.md @@ -0,0 +1,24 @@ +--- +layout: post +title: "BioHackEU25 report: Mining the potential of knowledge graphs for metadata on training" +tags: +- BHEU2025 +- Preprint +- BioHackrXiv +--- + +We are pleased to announce another [BioHackrXiv](https://biohackrxiv.org) preprint from 2025. It reports on the work done during the past [BioHackathon Europe 2025](https://biohackathon-europe.org/) by the group [Mining the potential of knowledge graphs for metadata on training](https://github.com/elixir-europe/biohackathon-projects-2025/blob/main/18.md). + +Abstract: + +> Training metadata in the life‑science community is increasingly standardized through Bioschemas, yet remains fragmented and under‑utilized. +> In this work we harvested training records from ELIXR’s TeSS platform and the Galaxy Training Network, converting them into a unified knowledge graph. +> A dedicated pipeline parses RDF/Turtle dumps, deduplicates entries, and builds rich indexes (keyword, provider, location, date, topic) that power a Model Context Protocol (MCP) server. +> The MCP offers live and offline search tools—including keyword, provider, location, date, topic, and SPARQL queries—enabling natural‑language access to training resources via LLM‑driven clients. +> User‑story driven evaluations demonstrate the system’s ability to generate custom learning paths, assemble trainer profiles, and link training data to external repositories. +> Findings highlight gaps in persistent identifiers (ORCID, ROR) and location granularity, informing recommendations for metadata providers. +> The project showcases how knowledge‑graph‑backed metadata can enhance discoverability, interoperability, and AI‑assisted exploration of scientific training materials. + +Citation and link: + +D. Panouris, H. Gupta, V. Emonet, J. Miranda, J. Bolleman, P. Reed, F. Bacall, G. van Geest, Mining the potential of knowledge graphs for metadata on training, (2025). [doi:10.37044/osf.io/gv2ac_v1](https://doi.org/10.37044/osf.io/gv2ac_v1).