Clinical applications of computational cytometry

01 October 2021 → 30 September 2024
Regional and community funding: Special Research Fund
Research disciplines
  • Natural sciences
    • Data mining
    • Machine learning and decision making
  • Medical and health sciences
    • Single-cell data analysis
  • Engineering and technology
    • Bio-informatics
    • Data visualisation and imaging
Cytometry Machine Learning Disease diagnostics
Project description

Flow cytometry is an essential technique in the fields of immunology and oncology, allowing insights at the individual cell level at relatively low cost, complementary to genetics and other clinical parameters. Due to recent technological advancements, this field is moving towards more automated analysis approaches. In this research proposal, I will work on two methods to aid researchers using flow cytometry. First, I will develop an algorithm for panel design, an optimization problem of combining fluorochromes with markers of interest, which becomes manually infeasible for large panels. Second, I will focus on the characterization of batch effects, one of the main challenges in clinical studies, as data is often recorded over longer time spans. While some normalization methods have been recently proposed, guidelines clarifying which ones to use in which situations are still lacking. Additionally, I will continue two collaborations with the Ghent University Hospital, developing analysis pipelines for specific clinical contexts. The first setting is Primary Immune Deficiency (PID), a disease causing recurrent infections, malignancies and autoimmunity. I work on a data-driven stratification of the patients, which will lead to improved diagnosis. The second setting is Acute Myeloid Leukemia (AML), a heterogeneous bone marrow cancer. Here, I focus on improving prognosis of the patients, in particular by a better characterization of rare leukemic stem cells present in the samples