On the basis of the characteristic aspects of a picture, certain computers can tell us what the picture is showing. They can learn this in the same way that young children are able to learn to recognize images. Further improving these techniques opens the way to a whole range of new applications. Biology and (bio) medical sciences offer numerous applications for computer science. We are pleased to work alongside biologists and medical scientists in identifying smart solutions for medical applications. Now and in the future, computers will be decisive in fighting a whole raft of diseases.

Imaging

The imaging group focuses on bio-imaging, image analysis and visualization. With their experience in high-throughput imaging, 3D reconstruction, cell tracking and pattern recognition, the group intends to find the relation between the information analyzed from image and other bio-molecular information resources. Furthermore, they develop new algorithms and techniques for producing images using the very latest equipment. These help create clearer three-dimensional pictures of organs and – on a scale of thousands of times smaller – body cells. These applications facilitate functional study, disease modeling and drug screening in the bio-medical field.

Life Science Semantics

The Life Science Semantics group does bioinformatics and data science research in knowledge discovery and integration. We have three main research lines

1 - FAIR data ecosystems; We were involved in creating and defining the FAIR principles and we develop methods and infrastructure to enable and exploit Findable, Accessible, Interoperable and Reusable data across the life sciences, specifically in bioimaging and systems biology.
2 - Reproducible research and provenance; Reproducibility and FAIR are intrinsically linked. If data is not reproducible, it should not be reused. We develop methods and models to improve reproducibility in omics data, using scientific workflows and ontologies. We are particularly interested in understanding evolving knowledge and the reproducibility and comparability effects of changes to ontologies and annotations.
3 - Semantic approaches to explainable AI (XAI); Semantically structuring data provides richer background information for models, improving model development and enabling a richer  interpretations of results, leading to better explainability. We apply these methods to drug repurposing challenges in rare disease research.
More information abou Life Science Semantics group.