This DC project will focus on developing computational methodology for the in silico antigen-specific profiling of immune receptor repertoires. Immune receptors are key actors in maintaining health responding with high specificity to antigens from infection and vaccination and may be causal agents in autoimmunity. Consequently, understanding the multidimensional antigen-specific immune repertoire in infectious and autoimmune diseases may foresee severe disease and select those eligible for more aggressive immune interventions in MS.
Since antigen-specific data is costly to generate, there is a need for an in silico prediction approach that assigns antigen binding information to non-antigen-labelled immune receptor data solely based on the immune receptor sequence. To address this problem, this DC project develops and applies machine learning methods that predict antigen specificity from the immune receptor sequence, with the aim to in silico antigen-annotate antigen-unlabeled public immune receptor-sequencing data from autoimmune and infection patients.
This project, hosted at UIO, will both yield new methods for antigen binding prediction as well as immunological insight in inter-individual variation of antigen-specific immune repertoire architecture.
Kamil Luczkiewicz
My PhD project focuses on applying advanced computational and machine learning methods to better understand antibody-antigen (Ab-Ag) interactions. This includes modelling and predicting Ab-Ag interactions based on protein sequences and structures, but also on analysing Adaptive Immune Receptor Repertoires (AIRR) in order to capture population-level diversity. The main question of this research is whether Ab-Ag binding affinities can be accurately predicted using in-silico methods, thereby accelerating new drugs and treatments discovery and development process.
My main motivation for joining this doctoral network was the opportunity to work on an interdisciplinary project with strong potential for translational impact. The international character of the network is also a great advantage, as it helps in knowledge exchange, enables collaboration with researchers across Europe, and broadens scientific and professional perspectives.
