Theses and Student Projects
Theses
Below you can find an overview of previous theses and student projects at our chair. If you are interested in pursuing a thesis or project with us, please refer to the information provided on our Teaching page.
| Author | Titel | Submission Date | Degree |
| Nele Bringmann | Master | ||
| Lara Seif | Master | ||
| Levin Schmara | Master | ||
| Vladyslav Khabazniak | Master | ||
| Hauke Hornecker | Bachelor | ||
| Sofia Germer | Master | ||
| Alina Jäntsch | Master | ||
| Michael Hüppe | Predicting Protein Crystallization Conditions using Machine Learning | April 2026 | Master |
| Patrik Staak | Master | ||
| Dark Engel | Master | ||
| Louise Schop | A Neuro-Symbolic Tool to support Brain Disease Diagnosis | Feb. 2026 | Master |
| Berenike Rutz | Computational analysis of brain regional single-cell RNA-sequencing immune signatures in acute stroke | Oct. 2025 | Bachelor |
Tutor / HiWi
| Student | Student project |
| Nele Bringmann | Tutor for the lecture "Programmierung für Naturwissenschaften 3" in the summer semester 2026 |
| Patrik Staak | Tutor for the lecture "Deep Learning in Bioinformatics" in the winter semester 2025/26 |
Student Research Group
Duration: 10/2025 - 10/2026
Participating students (in alphabetical order): Danisch Khurshid, Mikko Kormann, Berenike Rutz, Viktor Zouboulis
Student research groups provide motivated students with the opportunity to work collaboratively and independently on current scientific challenges. They emphasize interdisciplinary collaboration, self-organized research, and the application of modern methods from computer science, bioinformatics, and life sciences. The projects are selected through a university-wide selection process and are supported by funding from the University of Hamburg.
Project: The Virtual Cell
This project aims to develop a data-driven model for simulating cellular processes (“virtual cell”). The goal is to predict the effects of genetic perturbations at single-cell level using modern machine learning approaches combined with biological domain knowledge. Methods include deep learning, graph-based models, and knowledge integration to capture complex cellular interactions.
The project is embedded in the international “Virtual Cell Challenge” and combines methodological development with experimental validation and interdisciplinary research.