GUI Development for Sequence Design

Design a user application enabling Bayesian optimization based biological sequence design.

Biological sequences like DNA, RNA or Proteins define information and functionality of cells. Engineering these sequences allows to design new functionality or to improve existing mechanisms. Historically, the engineering was driven by rational insights, while model-driven approaches promise to advance this into a new dimension. To this end, we are developing a Bayesian optimization based method for biological sequence design. This method integrates tightly the results of the experimental characterization into the predictions leading to proposing new candidates. To improve the accessibility of our framework, this project focuses on the development of a graphical user interface (GIO). This GUI should allow to define the search space of the design as well as load and process the data generated via experiments to make it available to the pipeline. In addition, informative visualizations and appealing presentation of the data is appreciated. For the development of the GUI, we want to use Python and the GUI framework Flet, which is based on Flutter and allows for cross platform development. To provide you an example of how a biology related application created with Flet looks like, I attached a link to the GitHub of CellSepi in the recommended literature section. CellSePi was developed as a student project in our lab and allows the batch processing of microscopy images. The project can be done as a group project.

Background in electrical engineering, computer science, bioinformatics, (computational) biology, or related fields Proficiency in Python Prior experience with deep learning frameworks (PyTorch) is helpful but not required Strong interest in interdisciplinary research combining computational methods with biological applications Motivation to interpret results from a biological perspective Knowledge in biology is beneficial but not mandatory (guidance will be provided)

NAND Hybrid Riboswitch Design by Deep Batch Bayesian Optimization: https://www.biorxiv.org/content/10.1101/2025.03.28.645907v1

Flet: https://flet.dev/

CellSePi: https://github.com/PraiseTheDarkFlo/CellSePi

Additional Information

Supervisor
Contact at Department
Prof. Dr. Heinz Koeppl
Erik Kubaczka
Availability Spring, Summer 2026
Capacity 5 Students
Credits 18 ECTS
Remote Option yes