Deep Learning for understanding tumor evolution

Prof. Dr. Katharina Jahn 

December 12, 2024

 

The Biomedical Data Science group of Prof. Dr. Katharina Jahn develops computational and statistical methods for the analysis, integration and interpretation of biomedical omics data in particular single-cell data. One focus of the group is the study of clonal evolution of tumors to obtain a more comprehensive understanding of cancer biology, leading to improved diagnostic, prognostic, and therapeutic strategies for cancer patients.

We are looking for a highly motivated doctoral candidate with a strong computational background to develop advanced machine learning frameworks for reconstructing tumor mutation histories at the single-cell level. The goal of the project is to leverage deep learning techniques to analyze single-cell DNA sequencing data, integrating both single nucleotide variants (SNVs) and copy number alterations (CNAs). In this project, you will incorporate Bayesian optimization techniques to infer error rates in the sequencing data and implement a novel scoring metric to evaluate tree structures and prevent overfitting.

By combining these advanced techniques, our project aims to provide a more robust and accurate reconstruction of tumor evolutionary histories, ultimately contributing to improved cancer diagnostics and personalized treatment strategies.

For more information, visit the website of the Biomedical Data Science Group at the Free University Berlin.



Jahn

From Sollier, E., Kuipers, J., Takahashi, K. et al. COMPASS: joint copy number and mutation phylogeny reconstruction from amplicon single-cell sequencing data. Nat Commun 14, 4921 (2023). https://doi.org/10.1038/s41467-023-40378-8

Go to Editor View