What we do
We are interested in modern machine-learning techniques suitable for the analysis of problems that arise in medicine and biology.
In particular, we develop new learning techniques that are capable of dealing with large amounts of genomic data and medical data.
These techniques aim to provide accurate predictions on the phenomenon at hand and to comprehensively provide reasons for their prognoses, and thereby assist in gaining new biomedical insights.
Find out more about the Group’s activities
Main publications 2019
- Demircioğlu D et al.
A Pan-cancer Transcriptome Analysis Reveals Pervasive Regulation through Alternative Promoters
The Cell, https://doi.org/10.1016/j.cell.2019.08.018 - Locatello F et al.
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
arXiv, https://arxiv.org/pdf/1811.12359.pdf - Mustafa H et al.
Dynamic compression schemes for graph coloring
Bioinformatics, doi: 10.1093/bioinformatics/bty632
