ISCB Affiliated Group Logo

The Health Data Science Unit (HDSU, is a newly created unit of the BioQuant and medical Faculty of the University Heidelberg, which focuses on research topics related to digital health and the integration of clinical and genomic datasets.

The recently funded COMMITMENT project (COMorbidity Modeling via Integrative Transfer machine-learning in MENTal illness), in which HDSU is leading one work-package, will establish an interdisciplinary research consortium for the identification of molecular hallmarks of schizophrenia and comorbid somatic illnesses, such as diabetes or cardiovascular diseases. The identification of shared and distinct biological profiles will allow disentangling patient heterogeneity and provide the basis for objective tools for personalized clinical management of psychotic disorders.

The HDSU will lead the work-package on data integration, signature extraction and transfer learning over cohorts of

In this context, we are looking for a PhD student with a focus on the following points:

- Extension of existing matrix factorization (MF) approaches for the integration of heterogeneous datasets;
- Comparison of neural network models and MF methods for the definition of molecular signatures;
- Extraction of molecular signatures using transfer learning approaches


We are looking for a candidate with the following qualifications:

- A master degree in the field of computational biology or applied mathematics with a focus on statistical learning
- Good programming skills and first experiences in the field of machine-learning
- An interest in working in an interdisciplinary field involving clinicians, biologists, statisticians and computer scientists
- Good communication skills

We are offering

- An exciting, excellent and highly multi-disciplinary research environment on the campus of Heidelberg University, Germanys oldest university
- Payment according to German TV-L E13 (65%)
- A superb living environment in Heidelberg and surroundings.

Application letters and CVs (as pdfs), together with contact information of two referees should be sent by mail to This email address is being protected from spambots. You need JavaScript enabled to view it.


We use cookies on our website. Some of them are essential for the operation of the site, while others help us to improve this site and the user experience (tracking cookies). You can decide for yourself whether you want to allow cookies or not. Please note that if you reject them, you may not be able to use all the functionalities of the site.