Researchers at Leipzig University have put a brain-inspired supercomputer into operation. The infrastructure, which is funded with around four million euros, offers high computing power with low energy consumption and opens up possibilities for personalized medicine.

The system is based on neural networks and is used for AI-supported drug search. It is designed to predict protein structures and identify new drug candidates, with potential accelerations by a factor of 10,000 after adjusting the algorithms. Humboldt Professor Jens Meiler, head of the Institute for Drug Development, has raised the funds from the Free State of Saxony.

The platform consumes 18 times less power than conventional supercomputers and enables real-time AI, adaptive systems, and neuromorphic signal processing. It will be integrated into the emerging AI data center and strengthen Europe’s sovereignty in AI and supercomputing.

In the start-up phase, groups from medicine, including the Cluster of Excellence LeiCeM, computer science and physics will use the system, as will the Max Planck Institute for Human Cognitive and Brain Sciences. Applications include drug discovery for metabolic diseases, algorithms for environmental and climate models, knowledge graphs, AI-supported decision support in cancer research, and optimization of wireless communication for biomedical purposes.

The supercomputer is part of the AI Competence Center ScaDS.AI Dresden/Leipzig and was financed by the European Regional Development Fund and the Free State of Saxony.

Editor: X-Press Journalistenbüro GbR

Gender Notice. The personal designations used in this text always refer equally to female, male and diverse persons. Double/triple naming and gendered designations are used for better readability. ected.