Main content

Area of research

Picture of Prof. Dr. Karsten Borgwardt
Prof. Dr. Karsten Borgwardt

Big Data Analysis and Biomedical Research meet in our lab: We develop novel Data Mining Algorithms to detect patterns and statistical dependencies in large datasets from Biology and Medicine.

We try to reach two grand goals: To enable the automatic generation of new knowledge from Big Data through Machine Learning, and to gain an understanding of the relationship between the function of Biological Systems and their molecular properties. This understanding is of fundamental importance for Personalized Medicine, which tailors medical treatment to the molecular properties of each patient.

Our lab receives significant external funding from the European Union through a Marie Curie Initial Training Network (2013-2016), from the Krupp Foundation through the Alfried-Krupp Award (2013-2018), and from the Swiss National Science Foundation through a Starting Grant from the ERC backup scheme (2015-2020).   



The source code and data sets of our research projects can be downloaded from our GitHub repository. More information on the individual projects can be found here.


easyGWAS Our online platform for computing, storing, sharing, analyzing and comparing the results of genome-wide association studies.

MLCB news


"Medicine is awash in data"

Karsten explains how he extracts relevant information from health data and the potential benefits for personalised medicine in ETH magazine "Globe". Read more 


MLCB research featured in Swiss Research Magazine SNSF "Horizons"

"Data discoveries" is the topic of the latest edition of the SNSF research magazine "Horizons". Read more 


Karsten appointed as full professor at ETH

At its meeting of 8/9 March 2017, the ETH Board promoted Karsten Borgwardt to the rank of Full Professor. Read more 


New group member

Caroline Weis joins our group. Read more 


New publication: Genome-wide genetic heterogeneity discovery with categorical covariates

Felipe, Laetitia, Dean, Damian and Karsten have developed an alternative to burden tests for genetic heterogeneity discovery, which searches the entire genome rather than preselected genomic regions. Read more 

Show more news items 
Page URL:
© 2017 Eidgenössische Technische Hochschule Zürich