Current Research

We work on computational methods to analyze genotype-phenotype and phenotype-environment relations. We work on methods to integrate phentype ontologies between different species and to build phenotype ontologies automatically or semi-automatically. We then use phenotype ontologies to integrate, mine, and predict phenotypes across species. Using machine learning approaches, we then build predictive models that can be used for prioritization of candidate genes of diseases, identification of drug targets, and prediction of protein functions.​
Building predictive models for protein functions and phenotypes​.
We work on novel neuro-symbolic methods for machine learning. ​​Symbolic methods and statistical connectionist methods are two main approaches to artificial intelligence. While symbolic methods are very widely used to represent knowledge in biology and biomedicine in the form of ontologies, only few methods have been developed that can utilize the information contained in these ontologies for building machine learning models. We work on methods that combine deductive inference and statistical models to improve knowledge representation and data analysis in biology.
We investigate methods for structuring knowledge, in particular in the biological and biomedical domain. Formal ontology is an area of research drawing on formal logic, computer science, linguistics, cognitive science and philosophy and investigates methods for structuring the content of knowledge bases or software applications. Main research questions we investigate are methods for representing qualities and measurements, functions of biological entities and artifacts, and how to formalize relations and roles.​