Multi-omic Machine Learning in Metabolism and Disease
Use and develop hybrid deep learning models suitable to understand complex biological networks and study human disease. We believe this will help us to infer comorbid molecular components across complex metabolic diseases such as type-2 diabetes and obesity.
Identification of regulatory networks mediating adaptations to metabolic challenges (i.e. obesity, diabetes and exercise)
Systemic genomic integration using multi-omic deep learning inference of regulatory networks governing metabolic adaptations. We are currently focusing our integrative approches on immunometabolism.
Geometric Deep Learning in Biological Networks
Geometric deep learning is on the rise. Its application to relational graphs is outstanding. Among the latter, complex biological networks represent one of the fields that could profit the most from this emerging techinque
We are developing methods to integrate our systemic network approach into a single platform. To this end, we are using concepts from the field of geometric deep learning. Briefly, in order to achieve combinatorial generalization of biological systems, we aim to systematically learn structured representations such as networks using relational collective behavior with deep learning. These methods support relational reasoning and generalization, which will help us understanding structured relations such as those observed in complex biological networks. We believe our systematic combination of several principles of machine learning and network science will uncover unseen relations useful for drug-development and biomarker discovery.