Jonas Ebner, Research Assistant and Master’s student at the Hasso Plattner Institute, is using AIR·MS to investigate two complex and still poorly understood conditions: Fragile X premutation and Post-COVID syndrome (Long COVID).
Both research areas present significant scientific challenges. Fragile X premutation carriers can remain asymptomatic for long periods, which makes it difficult to identify and study affected populations. Long COVID, on the other hand, affects an estimated 10% of people after a COVID infection, yet the biological mechanisms behind the condition remain largely unclear.
Jonas is exploring how large-scale electronic health record (EHR) data can help uncover patterns and potential indicators for the Fragile-X permutation as Research Assistant and for the Post-COVID syndrome as part of his master’s thesis.
“AIR·MS gives us access to a large amount of well-structured population health data,” he explains. “This is crucial for studying diseases that are rare, heterogeneous, or remain asymptomatic for long periods.”
Using Python, Jupyter Notebooks, and the OMOP data model, Jonas applies machine learning approaches to analyze EHR data and clinical notes. These methods require substantial computational resources, which AIR·MS provides through its high-performance computing infrastructure.
“Through AIR·MS, I’m able not only to query the data but also to run demanding statistical and machine learning analyses efficiently,” he says.
For Jonas, the combination of rapid data access, standardized datasets, and scalable compute resources opens the door to research questions that would otherwise be extremely difficult to investigate.
Looking ahead, he also sees opportunities to strengthen collaboration within the AIR·MS community.
“It would be great to have an overview of researchers working with AIR·MS and their research topics. That could help people connect and collaborate when they are working on related problems.”
Jonas’ work highlights how AIR·MS enables researchers to explore complex biomedical questions using large-scale health data and advanced computational methods.
