Seminar: Machine learning and network biology for big data integration
Prof. Dr. Dr. Fabian J. Theis, Director of the Institute of Computational Biology, Helmholtz Zentrum München
Prof. Dr. Dr. Fabian J. Theis. Photo: TUM Technische Universität München
In modern high-throughput biomedicine, huge and complex data sets are being generated, in particular from the 'omics and imaging fields. The analysis and integration of these data sets is daunting but crucial not only for research but also for envisioned clinical use e.g. for precision medicine. Big data is a challenge both for infrastructure as well as for analysis. In this talk I will focus on the latter, showing first how to use machine learning for the statistical integration of omics data, with applications to single cell transcriptomics and to genetic disease signatures. Then I will focus on network biology as a tool for multi-omics data integration. Networks consist of nodes typically representing certain molecules and edges describing interactions of those, such as regulation, coexpression or complex formation. I will describe how to use networks to integrate data in population cohorts from multiple omics-level, in particular a graphical model for metabolomics and genetics data, and will finish with outlook how towards modeling including mechanistic prior knowledge.