On October 2, 2025, Prague hosted the annual High-Performance Computing Seminar MetaCentrum 2025, where Czech researchers, infrastructure experts, and technology specialists gathered to explore the role of HPC computing in advancing science. As part of the e-INFRA CZ national research infrastructure, MetaCentrum provides the backbone of distributed computing for academia, enabling thousands of scientists to tackle projects that would otherwise be impossible.
This year’s seminar highlighted the Czech Republic's national distributed computing environment, MetaCentrum, which provides HPC, cloud services, and specialized tools (including AI support) for scientific research. The seminar featured presentations on new infrastructure developments, user-centric services, and technological trends. The event underlined MetaCentrum’s central role in Czech science and its growing integration into the European Open Science Cloud (EOSC).
Building the Future of Czech Research Infrastructure
The opening keynote, delivered by Miroslav Ruda, set the stage by presenting MetaCentrum’s extensive infrastructure upgrades for 2025, featuring new hardware, including specialized GPU servers (NVIDIA H100 and DGX systems) optimized for AI. Storage has expanded with multi-petabyte BeeGFS and Ceph systems, ensuring sufficient capacity for data-intensive projects.
Equally important are the services built on top of this hardware. Through a single sign-on system, users gain seamless access to interactive environments like Jupyter, RStudio, and commercial software such as MATLAB and Ansys. Platforms like Galaxy, Kubernetes, and OnDemand have been tightly integrated, giving scientists the ability to run reproducible workflows, orchestrate containerized jobs, and scale their experiments efficiently.
MetaCentrum now supports over 3,500 active users and manages more than 53,000 CPU cores, 500+ GPUs, and 20 petabytes of storage. By aligning with European standards and connecting to EOSC services, it ensures Czech researchers can operate on a global level while still receiving specialised national support.
Preserving Scientific Data: The National Repository Platform
The challenge of long-term data preservation was addressed by David Antoš, who introduced the National Repository Platform (NRP). Unlike short-term storage systems, the NRP is designed as a permanent, certifiable home for research datasets. By adhering to FAIR principles—Findable, Accessible, Interoperable, and Reusable—the platform guarantees that scientific data remains accessible and transparent for decades.
Through services like the National Metadata Catalogue (nma.eosc.cz), researchers can search across repositories, while specialized interfaces allow them to upload, annotate, and share their datasets. Pilot repositories are already live, and further domain-specific repositories will be launched in the coming year. This initiative addresses a critical gap in Czech science, ensuring valuable data does not disappear into “dark storage” but instead contributes to open, reusable knowledge.
From Genomics to Ecology: Research Enabled by HPC
The heart of the seminar lay in the user presentations, which illustrated the transformative role of MetaCentrum’s services in cutting-edge science.
Tomáš Pavlík from Masaryk University described their genomic research, which involves assembling complex genomes and annotating DNA sequences to support advances in personalized medicine. Their projects require hundreds of years of CPU time and tens of terabytes of storage—resources unattainable outside a national HPC environment. While acknowledging challenges for newcomers, especially students unfamiliar with Linux, Pavlík stressed the importance of interactive tutorials and tailored onboarding to help young research groups thrive.
Jan Filip of Charles University presented a remarkable ecological project funded by a GAČR Junior Star grant. His team is using AI models trained on MetaCentrum’s GPU nodes to process billions of video frames from long-term field monitoring. The goal: to detect and quantify interactions between insects and plants, including nocturnal pollination previously overlooked by traditional methods. By leveraging parallel computing and containerized workflows, the project has already processed hundreds of thousands of videos—turning what would have been decades of manual work into actionable ecological data within months. This pioneering work offers an unprecedented view into biodiversity at a global scale.
Aleš Křenek and Adrian Rošinec introduced MDDash, a virtual research environment for molecular dynamics simulations. As the number of simulations grows, so does the need for specialized repositories that allow scientists to find and reuse molecular data. With tools like MetaDump for metadata extraction and BioID for automatic protein identification, MDDash brings structure to what has long been considered “dark data.” The establishment of a national MD repository, integrated into EOSC, will provide petabytes of storage and ensure Czech contributions are visible and reusable in global computational biology.
Afternoon Focus: Security, Platforms, and Cloud
The seminar’s second half shifted to technological trends and user-facing services.
Dan Kouřil emphasized that MetaCentrum’s openness does not come at the expense of security. Using a real-world example from September 2025, he demonstrated how a compromised account was detected and resolved swiftly through a coordinated response. The case exemplifies MetaCentrum’s balance of flexibility and safety—an essential feature for infrastructure used by thousands of researchers.
Aleš Křenek dispelled myths about the Galaxy platform, which is often thought of as limited to genomics or teaching. In fact, Galaxy now supports workflows in areas as diverse as natural language processing, climatology, and astronomy. With usegalaxy.cz integrated into MetaCentrum, Czech researchers benefit from additional computational quotas, GPU access, and direct links to national data repositories. Galaxy’s open architecture and reproducibility features make it an indispensable tool for modern science.
Anežka Melounová demonstrated the accessibility and flexibility of the Jupyter environment in MetaCentrum, which caters to a range of needs, from teaching to demanding HPC and machine learning workloads. Users can choose between OnDemand-based notebooks for immediate tasks and Kubernetes-based setups for long-term projects, supported by modern tools such as AI assistants, GPU acceleration, and integrated storage.
Lukáš Hejtmánek presented progress in deploying Kubernetes for scalable workloads, including AI model provisioning in ISO-certified environments. By combining container orchestration with GPU acceleration, researchers can now experiment with advanced machine learning pipelines in a secure, reproducible setting.
Klára Moravcová introduced MetaCentrum Cloud, a flexible self-service environment that enables researchers to spin up virtual machines, configure networking, or deploy Kubernetes clusters in OnDemand. With options ranging from personal sandbox projects to large group allocations, the cloud extends HPC capabilities into a versatile and user-friendly platform. Upcoming innovations include FastStack instances with next-generation networking and NVMe storage, promising even faster performance.
Listening to the Community: Survey Insights
The seminar concluded with Jiří Vorel, who provided valuable insights into MetaCentrum's core mission, user satisfaction survey results, and immediate actions to enhance user experience. The seminar closed with an analysis of the 2024/25 user satisfaction survey, which gathered nearly 300 responses. While researchers praised the scale and impact of MetaCentrum, they also identified gaps in documentation, difficulties in accessing GPU resources, and challenges for beginners. In response, MetaCentrum is overhauling its tutorials, introducing clearer GPU overviews, and launching an Ambassador Program to provide localized user support.
A Vision for Czech Science
The MetaCentrum 2025 Seminar demonstrated how national HPC infrastructure is not only a technical resource but also a catalyst for scientific excellence and collaboration. From genomics to ecology, from molecular biology to artificial intelligence, the presentations highlighted how computational capacity translates into real-world discovery.
By expanding hardware, introducing flexible cloud services, and supporting open-science principles, MetaCentrum is ensuring that Czech researchers have the tools they need to compete internationally. As part of e-INFRA CZ, MetaCentrum continues to bridge the gap between technology and research, making the Czech Republic a strong contributor to European science.
