Biomedical Data Science
(formerly: Algorithmic Bioinformatics)
Research focus

The work of our group falls within the intersection of data sciences / data analytics and life sciences. Big data plays an increasing role in modern biomedical and biopharmaceutical research. Examples include -omics data (genomics, transcriptomics, methylomics, proteomics, ...) reflecting biological phenomena at the intracellular level, data from clinical and electronic medical records (EMR), bioimages, data from mobile devices and video recordings. A key questions is, how to utilize these data in order to generate value for patients, for example by better understanding of disease mechanisms, identifying novel drug targets and stratification of patients according to their expected treatment success, disease prognosis and early disease onset. The latter approach is also called precision medicine. In order to address these questions suitable data mining and Artificial Intelligence (AI, specifically machine learning) are playing a very important role. In that context one has to take the specific aspects of the employed data (e.g. high noise level, high dimensionality, large heterogeneity) into account. Furthermore, a critical factor for success and acceptance by medical and life scientists is typically the appropriate consideration and integration of background domain knowledge.

The research of our team has a methodological as well as an application oriented component, where method development is typically driven by specific questions arising in applications. Currently these applications largely cover:

  • precision medicine (the right drug for the right patient):
    • AI based modeling of disease risk, disease progression and disease subtypes
    • AI based simulation of synthetic patient data as a mechanism for privacy preserving data sharing
  • early drug discovery (better drug targets):
    • AI based drug target prioritization
    • AI methods for adverse event prediction

In addition, we have a long standing experience with applications of AI in system medicine (reverse engineering and simulation of biological networks).

To address the highly complex questions arising in our different applications a broad range of different AI and data science techniques is needed (covering neural networks, Bayesian learning, Bayesian Networks, kernel methods, boosting and others). At the same time, off-the-shelf solutions rarely provide satisfactory results. Hence, a significant proportion of our work goes into the adaptation, development and design of AI and data science techniques that are tailored to solve a particular application problem. During the last years our method developments have specifically covered

  • "Hybrid" AI: combination and integration of knowledge (e.g. in form of graphs) into machine learning models
  • (Generative) modeling of multivariate time series, including approaches to deal with missing values
  • Models that deal with multiple data modalities and biological scales.

We have historically a long standing experience with various types of -omics data, but during the last years other data types (e.g. clinical, real world evidence, bioimaging derived features) have become more and more important.

Starting from 12/2019 the group is also part of Fraunhofer SCAI.