Meetings
BioHackSWAT4HCLS 2025
BioHackathon Europe 2025
4th BioHackathon Germany
DBCLS BioHackathon 2025
ELIXIR INTOXICOM
Recent preprints
-
BioHackEU24 report: Expanding FAIR database integration through elucidation and transformation of underlying graph schemas
The BioDataFuse (BDF) project aims to enhance the interoperability of biomedical data through modular integration of data from diverse life sciences resources into context-specific knowledge graphs. This paper discusses the efforts made during BioHackathon Europe 2024 to improve the FAIR (Findable, Accessible, Interoperable, and Reusable) data integration process by clarifying and transforming graph schemas. We explored tools such as VoID-generator, RDF-config, and sheXer for data schema extraction and the integration of RDF Portal data into the BDF framework. By leveraging these tools, we automated the generation of SPARQL queries, created GraphQL endpoints, and enhanced BDF’s ability to integrate new databases. Additionally, we explored the potential of large language models (LLMs) for automated reasoning and data interpretation within the BDF ecosystem. This work lays the foundation for building more efficient and standardized data models, contributing to the seamless integration of multiple biomedical databases. -
BioHackSWAT4HCLS25 report: Towards AI-Ready Datasets for the Life Sciences
At the SWAT4HCLS 2025 Hackathon, we continued our work on dataset interoperability and AI-readiness, extending our efforts from the 2024 Elixir Biohackathon. This report outlines the progress made in graph serialization, metadata embedding, and knowledge graph analysis, which further enhance machine learning workflows and data integration -
Reusable RDM Planning Environments for Trainings and Workshops: A BioHackathon Europe 2024 Report
This report provides an overview of our activities and accomplishments related to the creation of reusable RDM (Research Data Management) Planning Environments for trainings and workshops conducted during the ELIXIR BioHackathon Europe 2024. ELIXIR recognizes the critical role of effective data management planning in enabling sustainable and reproducible research outcomes. This effectiveness is achieved through the use of appropriate Data Management Planning tools, such as the Data Stewardship Wizard. The Data Stewardship Wizard is used to conduct various trainings which require instance with data which are different for each training. Goal of this project was to provide easy and effective way to prepare “recipes” for DSW Data Seeder -
Enhancing bio.tools by Semantic Literature Mining
Mining mentions of software tools in scientific literature is important for resource discovery and analysis in bioinformatics. Despite advancements in deep-learning-based natural language processing techniques, accurately identifying software mentions remains challenging due to naming ambiguities, inconsistent citation practices, and homonyms. In this study, we developed methods to enhance the bio.tools registry through integration with Europe PMC. We systematically explored three distinct article-tool relationships: direct associations, citations of associated articles, and textual mentions without explicit citations. A hybrid approach combining rule-based heuristics and machine learning was evaluated at a F1-score of 74.4% in contextual software mention disambiguation tasks. We further demonstrated the potential for mining software co-mentions and co-citations from EuropePMC, constructing interactive networks in Cytoscape to visualize relationships between tools. Leveraging bio.tools metadata significantly improved disambiguation accuracy, including for tools with generic names. In the future, we will expand annotated datasets, handle software synonyms, and make bio.tools software mentions retrievable through the Europe PMC Annotations API to enrich bio.tools with usage data, making software more findable, including for recommendation systems. -
BioHackEU24 report: Integrating Bioconductor packages with the ELIXIR Research Software Ecosystem using EDAM
This project seeks to enhance the ELIXIR Research Software Ecosystem (RSEc) by increasing the findability, accessibility, interoperability, and reusability (FAIR principles) of Bioconductor’s extensive collection of over 2,000 bioinformatics packages. By aligning Bioconductor metadata with the EDAM ontology and integrating detailed package descriptions into the bio.tools registry, we aim to improve the discoverability and usability of bioinformatics analysis tools. Short-term goals include mapping Bioconductor’s biocViews controlled vocabulary to EDAM concepts, developing a set of manually annotated “gold standard” packages, and evaluating tools for automated EDAM concept suggestions. Long-term, we intend to expand EDAM coverage across Bioconductor, phase out biocViews, and implement automated synchronisation with bio.tools. This initiative fosters collaboration between Bioconductor and ELIXIR, establishing a foundation for sustainable software management in European bioinformatics.Key results from the ELIXIR BioHackathon 2024 week include substantial progress in mapping the biocViews vocabulary to EDAM concepts, initiating the curation of a reference set of packages with manual annotations, integrating Bioconductor metadata into the ELIXIR Research Software Ecosystem (RSEc) with automated updates, and prototyping a tool for automated EDAM concept suggestions. Together, these achievements establish a strong foundation for further integration and refinement. -
Persistence, metadata collection and re-architecture of BioHackrXiv
In this paper, we present the work executed on re-architecting BioHackrXiv during the international ELIXIR BioHackathon Europe 2023 in Barcelona, Spain. BioHackrXiv is a scholarly publication service for biohackathons and codefests that target biology and the biomedical sciences in the spirit of pre-publishing platforms. -
An assessment of Croissant ML metadata descriptors for AI-ready datasets
To advance the use of machine learning to address humanity’s grand challenges such as the understanding of disease conditions and biodiversity loss in the anthropocene, it is important to promote FAIR AI-ready datasets, since data scientists and bioinformaticians spend 80% of their time in data finding and preparation. Metadata descriptors for datasets are pivotal for the creation of machine learning models as they facilitate the definition of strategies for data discovery, feature selection, data cleaning, and data pre-processing. ML-ready datasets, whether by design or after pre-processing, can be enriched with metadata so they become FAIRer, i.e., autonomously discoverable and processable by machines (machine-actionable). Croissant ML is an extension of schema.org to better describe ML-ready datasets, released early 2024 and already adopted by some ML-model platforms such as Hugging Face (see Croissant ML viewer documentation) and OpenML. However, as it commonly happens with metadata, there are some limitations to the amount of metadata that can be automatically extracted. How much Croissant metadata can be programmatically extracted from ML-ready datasets? And how could this automation be improved? In this project, we explored answers to these two questions.