Lab notebooks and extracted metadata, supporting the Msc thesis: Metadata Extraction from Scientific Lab notebooks
What's in it
Abstract: High-quality, interpretable metadata is essential for enabling data reuse and reproducibility in the life sciences. Frameworks such as the Investigation–Study–Assay (ISA) model provide a structured way to describe experimental workflows, yet in practice metadata remains incomplete, inconsistent, and costly to produce. Lab notebooks, which record experimental procedures, offer a promising source for automating metadata creation, but their unstructured and heterogeneous nature makes extraction challenging. This thesis investigates the feasibility of extracting ISA-compliant metadata from lab notebooks using a multi-agent system. It also addresses the lack of suitable evaluation methodologies for such tasks, given the inherent flexibility of the ISA framework. To this end, a prototyping methodology is adopted to develop two artefacts: (1) a prototype multi-agent system that decomposes the extraction task into specialized components, and (2) a rubric-based evaluation framework capable of assessing extraction performance beyond binary correctness. A feasibility study is conducted on a set of real-world lab notebooks to evaluate the proposed system. The results show that …
Files and services
- DataCite REST API (JSON)api.datacite.orgOpen