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, allow for very accurate predictions on the phenomenon at hand and are able to comprehensibly provide reasons for their prognoses, and thereby assist in gaining new biomedical insights.

Highlights 2017

We are pleased to report that we were part of three successful grant submissions to the first coordinated calls of the “SFA Personalized Health and Related Technologies (PHRT)” and “Swiss Personalized Health Network (SPHN)”. We will contribute and co-lead the Swiss Molecular Pathology and Tumour Immunology Breakthrough Platform​ ​(​SOCIBP​), together with Prof. Dr. Marc Rubin (University of Bern and Inselspital). We will be part of the Personalized Swiss Sepsis Study (PSSS), which is led by Prof. Dr. Adrian Egli (University Hospital Basel (USB) and University of Basel). Finally, in the MIDATA Platform for Ethical and Fair Citizen/Patient Participation in Personalized Health Research, which is led by Prof. Dr. Ernst Hafen, we will work towards expanding MIDATA’s current scope and capabilities. Furthermore, our SNF Grant Proposal “Novel Machine Learning Approaches for Data from the Intensive Care Unit” together with Inselspital Bern was accepted.

Find out more about the Group’s activities

Main publications 2017

  • Locatello F. et al., Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees, NIPS 2017. arXiv:1705.11041
  • Hyland S L et al. Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs. arXiv:1706.02633
  • Zhong Y. et al. RiboDiff: detecting changes of mRNA translation efficiency from ribosome footprints. Bioinformatics 2017; 33:1


eth zurich

Gunnar Rätsch
Biomedical Informatics
ETH Zurich
Group Webpage

Twitter button

Domains of activity:

  • Text mining and machine learning
  • Comparative genomics
  • Deep sequencing data
  • Electronic health record
  • Genome structure
  • Machine learning
  • Metagenomics
  • Next generation sequencing
  • Oncology
  • Software engineering
  • Structural biology
  • Text mining
  • Transcriptomics

Domains of application:

  • Medicine and health
  • Cancer Genomics and Transcriptomics