Mining the cellular, adaptive immune system

Research group
Adrem Data Lab
  • Biology / Biochemistry / Biomedical sciences
    Master thesis, internship or bachelor thesis


Bioinformatics techniques, MHC-epitope prediction models, (un)supervised machine learning (may change depending on the scope of the research project)


The adaptive immune system is tasked with the major challenge of distinguishing self from nonself molecules. The major histocompatibility complex (MHC) is responsible for the first step in the activation of the adaptive immune system by presenting both self and nonself peptides derived from intracellular or extracellular proteins to circulating T cells. MHC molecules are encoded by the highly polymorphic and polygenic human leukocyte antigen (HLA) alleles and each MHC molecule possesses specific peptide binding capacities. As the number of possible pathogens the immune system can face is huge, the HLA alleles are accordingly diverse. At the other side of the complex, the MHC-presented peptides need to be recognized by the T cell receptors (TCRs) of circulating T cells before they can trigger an immune response. T cell receptors are generated through a process of semi-random recombination events resulting in a diversity that it still several orders of magnitudes higher than the observed MHC diversity. Integrating and understanding these different data types thus possess a considerable challenge and presents itself as a prime opportunity for the application of data mining and machine learning methods to generate new knowledge about this system. Therefore, we will study the adaptive immune system by applying state-of-the-art computational techniques.

Necessary background

This proposal is open to Biology, biochemistry, biomedicine, … students who have some knowledge on cellular or immunological processes and have a keen interest in bioinformatics and computational techniques.