Knowledge bases: Although recent progress in biomedicine has made it possible to obtain quantitative information for thousands to tens of thousand entities in a few hours we are still far from understanding disease. So how come that the knowledge that we are accumulating with lightning speed is not sufficient to understand what goes wrong in a human body?
We strongly believe that data integration and re-use is what is currently limiting our understanding, which is why we build intelligent ‘knowledge-bases’. We build automated software systems to extract, transform, normalize, and analyze ‘big’ biological data. This means that we can compare hundreds of diseases at the same time; across genomic, epigenetic, transcriptomic, and protein levels; considering age, gender, and medication.
Machine Learning: To strip our knowledge-bases of their secrets we use statistical inference and machine learning approaches. On the one hand, we use classical machine learning as well as deep learning approaches to stratify and predict disease. On the other hand, we use them to understand how diseases come about and extract detailed mechanisms of human pathology. Especially for the latter task we develop and apply state-of-the-art deep learning algorithms to learn and extract disease-relevant features that can later be used to reproduce and cure pathology. Ultimately, our insights will fuel medical researchers and pharmaceutical engineers to understand and combat human malady.