Our research focuses on machine learning methodologies for the analysis of omics data, as well as digital and molecular pathology data.
Omics data generated by high-throughput sequencing technologies make it possible to investigate cellular systems at a genome-wide level and with increasing resolution. The bioinformatics analysis of this data has a key role in biomedical research and has gained increasing importance for precision medicine.
Our group works on the development of methodologies for the analysis of functional genomics data with the goal of dissecting transcriptional regulation in development and disease. We have developed novel approaches for clustering and reverse engineering of gene regulatory networks, as well as for pathway meta-analysis. In addition, within TRR 305 and TRR 374 we support experimental partners in the design of omics experiments and in the computational management and statistical analysis of the resulting data.
Thanks to the substantial technological improvements of the past few years in both hardware and software, a massive growth of AI applications in many different domains, from computer vision to bio-medicine took place. In pathology, the availability of high-resolution whole slide images opened the way to the development of deep-learning algorithms that have the potential to affect clinical decision-making by providing prognostic and/or predictive information.
Our group aims at developing machine-learning strategies that leverage digitalized histopathological images as well as molecular-level data in order to improve patients’ stratification and treatment in urothelial cancers.