The Italian EOSC Node, operated by the Italian Research Center on High Performance Computing, Big Data and Quantum Computing (ICSC), federates resources from over 50 members, including national research infrastructures, ERICs, service providers, and e-Infrastructures.
Supported by the Italian government, the Node provides federated cloud and HPC infrastructure, national research product catalogues, repositories, AAI, and training services. With ISO27001-certified cloud regions and national HPC centres (Cineca, INFN), the Italian EOSC Node integrates compute, storage, and data analysis services into EOSC. It will contribute to the EOSC Federation with federated services and cross-node use cases.
Key objective: To enrich the EOSC Federation with state-of-the-art federated HPC, cloud, and data services, enabling cross-node workflows, secure sensitive data analysis, and support for AI and quantum technologies.
Science areas: HPC, cloud and quantum computing, astrophysics, life sciences, physics, environment, and AI/ML applications.
FAIR data
The Italian EOSC Node provides access to repositories with Open Access publications and datasets, as well as other resource repositories. FAIR compliance is ensured via metadata registries, catalogues, and semantic interoperability policies.
Scientific use cases
Federating CERN’s REANA pipelines
The REANA science case focuses on enabling near-data computation—sending computational workflows to where large scientific datasets are stored, rather than transferring massive volumes of data to the researcher.
The use case demonstrates this concept through particle physics—a field that generates enormous data volumes—but it is applicable to many other domains, including astronomy and life sciences. The project aims to show how researchers can execute their analyses directly at the data source, using REANA—CERN’s Reproducible research data analysis platform—to manage containerized workflows across federated computing resources.
Multi-centric validation of AI models for prostate-cancer screening
Advances in digital pathology are transforming cancer diagnosis by enabling high-resolution imaging of tissue samples and the application of artificial intelligence (AI) for clinical decision support.
Prostate cancer, one of the most prevalent malignancies among men worldwide, represents a critical case for early and accurate diagnosis, as survival rates are strongly tied to timely detection and treatment. The objective of the multi-centric validation of AI models for prostate-cancer screening (MCVAL) use case, coordinated by the BBMRI-ERIC EOSC Node, is to create a secure environment in which AI models for prostate cancer screening can be validated using data from different hospitals. Rather than building new diagnostic systems from scratch, the project focuses on testing an existing model trained on whole-slide images and assessing how well it performs when applied to data processed elsewhere.
Other use cases
- Italian Indico instance for federated agenda services, backup, and disaster recovery for EU Node Indico
- Federated sensitive data analysis using interactive notebooks, HPC-enabled distributed resources, ISO-certified cloud regions
