Computational
Medicine

Research Interests

  • Computational Biology, Computational Medicine, Oncology, Antimicrobial resistance, COVID-19
  • Statistical data analysis, Artificial Intelligence, machine learning, deep learning

Current projects

  • Antimicrobial resistance: variational autoencoders to the rescue! We work out specialized deep generative models to produce synthetic antimicrobial peptides that can kill antibiotic-resistant bacteria.
    Methods: deep learning, generative models
  • Modeling tumor microenvironment What is the spatial organization of the tumor and its neighborhood? How do they interact? These interesting questions are solved in our lab by analyzing spatial transcriptomics, digitalized tumor imaging, or imaging mass spectrometry data. This work is in collaboration with colleagues from the Oncology Bioinformatics department at Merck, Germany, and with an international consortium called IMMUcan.
    Methods: probabilistic graphical models, deep learning, machine learning models
  • Drawing the genealogical trees of tumors. Which cancer mutations come first? How do metastases occur? How does drug resistance appear in cancer? Is tumor evloution neutral, or is it driven by selection? These and many more questions about the family history of tumor cells we find very exciting! Find out more on our CONTRA (Computational ONcology TRaining Alliance) website.
    Methods: probabilistic graphical models, mathematical models
  • Fighting cancer with its own weapons. We are analyzing the phenomenon of synthetic lethality between cancer genes. We can use synthetic lethality for cancer treatment. Once one gene is mutated, we can target its synthetic lethal target in order to kill cancer cells. Learn more on our project website.
    Methods: statistical tests, survival analysis methods
  • Deep Pathologist! Can deep learning algorithms scale the work of pathologists? We train a deep pathologist on colorectal and lung cancer histological images to recognize multiple tissue types.
    Methods: deep learning models
  • Modeling efficacy of drugs and drug combinations. Together with colleagues from the Oncology Bioinformatics department at Merck, Germany, we try to understand and predict how drugs work on cancer cell lines.
    Methods: deep learning, machine learning, statistical models, optimization algorithms
  • Modeling epidemic spread. We were involved in two projects modeling COVID-19 dynamics in Poland: SEIR-based COVID-19 model and microsimulation-based MOCOS (MOdeling COronavirus spread) model.

Organized seminars

Past organized conferences

>