Uniklinik RWTH Aachen uses Azure to help innovate genome research

Uniklinik RWTH Aachen was working with large, complex datasets as they sought to understand genomic function. Connecting multiple biological layers to interpret how they relate to biological processes and molecular functions.

The team used Microsoft Azure to support large-scale model training, flexible storage, and development across the full MLOps lifecycle—enabling development of Genolator, an AI system for natural‑language genomic exploration.

Azure enabled researchers to build Genolator, making genomic data more accessible and helping scientists explore functional relationships, accelerate discovery, and lay the groundwork for future genetic disease research.

“This is the next era in genomics.”

Ingo Kurth, Professor of Human Genetics, Uniklinik RWTH Aachen

How can we better understand the vast complexity of the human genome? At Uniklinik RWTH Aachen, a multidisciplinary team is exploring new ways for scientists to interact with genomic data using AI and cloud computing on Microsoft Azure.

Ingo Kurth, Director of the Center for Human Genetics and Genomic Medicine, is working on the project alongside data scientist and machine learning engineer Martin Danner and physician and principal investigator Jeremias Krause.

Together, they’re shaping an ambitious new research vision to accelerate genomic discovery.

Translating the language of life

Understanding genomic function requires working with datasets of enormous scale and complexity. Researchers must connect multiple biological layers from DNA sequences to amino acid chains and three‑dimensional protein structures to interpret how they relate to biological processes and molecular functions.

To address this challenge, the team developed Genolator—a multimodal AI system designed to bridge genetic code and human understanding.

By integrating genomic sequence representations, protein structure information, and natural language models, Genolator allows researchers to query coding sequences in natural language and explore potential biological processes, molecular functions, and cellular roles associated with a sequence.

This ability to connect diverse biological layers through natural language queries creates a new interface for exploring genomic data, helping researchers uncover functional relationships and generate new insights into the genome.

From infrastructure to innovation

While the research team’s on-premises systems are dedicated to clinical workloads, Genolator requires additional storage and significant compute capacity for large-scale model training.

Azure provides the flexibility to build and scale without disruption—enabling the creation of extensive training datasets and supporting development across the full MLOps lifecycle.

Guided by patient needs

Kurth states: “This is the next era in genomics. The result is a practical tool that makes genomic data more accessible and meaningful, freeing researchers to focus on discovery. But the ultimate goal goes beyond data.”

“While Genolator currently focuses on coding regions, the framework provides a foundation for future research into less well‑understood parts of the genome – work that may ultimately deepen our understanding of genetic disease,” Krause reflects.

Danner adds: “We see many patients with genetic disorders, but in too many cases we do not yet understand which genetic change caused the condition.”

The team’s search for answers continues to drive the work forward.

Discover more about Uniklinik RWTH Aachen.