Research topics
Our research aims at deepening the understanding of genome biology and advancing personalized medicine. Besides our own fields of interest we engage in collaborative research projects with the department of Human Genetics, the Excellence Cluster Immunosensation and with basically any lab on the campus that has challenging high dimensional data. In most of our projects we are using artificial intelligence in the analysis of big biomedical data sets and we are trying to understand what the machines are doing.
T-NAMSE + PEDIA
Prioritization of Exome Data by Image Analysis
GPI anchor deficiencies
Identification of pathogenic sequence variants
Radar
Study on possible DNA damage in descendants of radar technicians
FlowCat
Automated classification of B-cell neoplasms with AI
Fundus2Sex
A Computational Approach for Interpretable AI
Gestaltmatcher
GestaltMatch: breaking the limits of rare disease matching using facial phenotypic descriptors
GenRisk
GenRisk is a python package that processes genetic data to generate both gene-based burden scores and PRS for association tests and the development of prediction models
snpboost - Boosting Polygenic Risk Scores
To fit polygenic risk scores (PRS) directly on individual level genotype data, we developed the adapted statistical boosting framework snpboost which is implemented in R.