Academic Research

We develop pharmacological digital twins that describe how drugs are absorbed, distributed, metabolized, and eliminated in the human body. A particular focus is on the liver and kidneys and their role in drug detoxification. Using physiologically based pharmacokinetic (PBPK) models, we combine physiological knowledge, drug properties, and clinical data to simulate drug behavior in different patients. These models can help study drug–drug interactions, organ impairment, aging, and other sources of variability.
In 2027, we will increasingly use agentic AI workflows to support literature analysis, data extraction, scientific programming, model development, testing, and documentation. The intern will learn how to combine AI-assisted workflows with critical scientific reasoning. The aim is to build transparent, reproducible models that can support personalized medicine and model-informed drug development.

The intern will develop a PBPK model for a selected drug. Typical tasks include literature research, extraction and curation of pharmacokinetic data, model implementation in Python, parameter estimation, validation against clinical data, and simulation of relevant scenarios such as drug interactions or organ impairment.

A central part of the project will be the use of agentic AI for scientific programming and model development. The intern will learn how to use, supervise, and critically evaluate AI-supported workflows for coding, testing, documentation, and analysis.

No previous experience with AI, large language models, or agentic programming is required. These skills will be taught during the internship.

Students should refresh basic Python skills and familiarize themselves with introductory pharmacokinetics.

Recommended preparation:

No prior preparation in AI or agentic programming is required.