Research Group

IML

Group leader: Morten Nielsen

Immunoinformatics and Machine Learning

The core research of the group deals with the development of novel and advanced data-driven prediction methods for pattern recognition in biological systems.

Immunoinformatics and Machine Learning

The main task of the immune system is to defend the host against pathogen infections. The immune system is in most cases highly effective, but if it fails, it can have dramatic implications both on individuals and society. Malaria, Tuberculosis, HIV, and cancer are some striking examples.

Understanding how the host immune system interacts with pathogens is essential to make sense of the successes and failures of the immune system, and can offer a crucial aid towards the development of therapeutic and prophylactic interventions against these diseases. A promising approach to address this complex problem has been to develop methods capable of predicting the behavior/function of key players of the immune system. The Immunoinformatics and Machine Learning group has played a central role in this field.

The core of the research within the Immunoinformatics and Machine Learning group deals with the development of novel and advanced data-driven prediction methods for pattern recognition in biological systems. The development of pattern recognition algorithms is pivotal for the construction of accurate prediction systems for receptor-ligand interactions in biological systems in general, and for our understanding of the response of the immune system to pathogens in particular.

The group has developed methods for the three main types of epitopes:

Cytotoxic T lymphocyte (CTL) epitopes, which are the targets of CD8 T cells and are used to directly detect and kill infected cells.
Helper T lymphocyte (HTL) epitopes, which interact with CD4 T cells to activate cells that have taken up foreign substances
B cell epitopes, which are the targets of antibodies and are used to recognize microorganisms outside cells 
and is current working on the development of methods to expand into the prediction of the interactions of T and B cell receptors with their cognate antigen target. 
 
Applying these methods, the Immunoinformatics and Machine Learning group is involved in a large number of collaborations focused on rational epitope and antigen discovery aiming at developing new vaccines and therapies for a wide range of diseases. They include diseases with major epidemiological significance such as HIV, Malaria and Tuberculosis, as well as cancer. 

Research Projects

The Immunoinformatics and Machine Learning group is involved in a large number of collaborations focused on rational epitope and antigen discovery aiming at developing new vaccines and therapies for a wide range of diseases. They include diseases with major epidemiological significance such as Cancer, HIV, Malaria and Tuberculosis.

  • Development of improved methods for predicting peptide binding to MHC Class I and Class II molecules

  • Prediction of CTL response

  • Prediction of pathogenicity

  • Prediction of T cell cross-reactivity and T cell tolerance

  • Improved proteasomal cleavage site predictions

  • Prediction of conformational and linear B cell epitopes

  • Development of methods for cancer neoepitope identification

  • Development of methods for prediction of T cell receptor targets

  • Development of high performance computing and Deep learning methods for pattern recognition in biological systems

Group Leader

Morten Nielsen

Morten Nielsen Groupleader, Professor Department of Health Technology Phone: +45 45252425

Link to Google scholar (New window)
List of PhD-projects (New window)