Our research focus

We develop algorithms and machine learning approaches to address the following questions:

1. Determine the role of epigenetic remodeling in oncogenic transformation
2. Investigate the consequences of somatic genomic alterations on the epigenetic landscape and chromatin folding in cancer
3. Adjust methodology for studying genetic and epigenetic plasticity in cancer.

Our methods and techniques for analyzing cancer genomes, transcriptomes, and epigenomes can be applied to most cancer types. Currently, we are interested in understanding the oncogenic processes related to several cancer types: esophageal adenocarcinoma, mesothelioma, lung cancer, neuroblastoma, adrenocortical carcinoma, Ewing sarcoma, and lymphoma. But we are open to collaborations with research groups studying other types of cancer.

Recent projects and highlights:

• Modelling effects of non-coding genomic variants on chromatin accessibility and the strength of enhancer-promoter interactions [ASAP preprint, UniversalEPI preprint]
• Building single cell transcriptomics foundation model for cancer cells [CancerFoundation preprint]
• Evaluating computational strategies for the discovery of shared transcriptional states in cancer cells [CanSig preprint]
• Discovery and spatial characterization of transcriptional states of malignant cells in esophageal adenocarcinoma [Cell Reports Medicine, 2025]
• Discovery that malignant cells expressing high amounts of MT RNA in single-cell RNA-seq data are rarely artifacts of cell dissociation-induced stress [Genome Biology, 2025]
• Discovering DNA-methylation changes in healthy tissue surrounding adenomatous polyps [JNCI, 2024]
• Fitting sparse survival models via knowledge distillation [Bioinformatics, 2024]
• Revealing a widespread lack of noise resistance of multi-omics survival models [Cell Reports Methods, 2023]

We offer several projects to bachelor's and master's students. Please check this page for more information!