Supervision: Pengkang Guo

Project type: Semester project (master) Master thesis


Background: Machine learning has seen increasing applications in natural sciences, particularly biology. The powerful contributions of machine learning to the field are exemplified by leading models like AlphaFold2 and ProteinMPNN, which have fostered further innovation in various aspects of biological sciences.

Project: This semester project will focus on protein sequence design. It involves the creation of specialized protein sequences to perform specific functions, a process crucial in several sectors, including drug development and bioengineering. The project will incorporate the use of advanced Graph Neural Networks (GNN) for enhancing protein sequence design methodologies.

Required Skills: Candidates should ideally be from a Computer Science, Data Science, or related field. A basic understanding of machine learning is necessary. Experience with the PyTorch or JAX framework, familiarity with GNN, and a background or interest in computational biology would be beneficial.

Supervisor: Pengkang Guo, a PhD student in GNN and its applications in biology, and Casper Goverde, a PhD student in protein design. For any inquiries about the project, you may reach us at or