HIGHLIGHTS
A collaborative constrained graph diffusion model for the generation of realistic synthetic molecules
Nat. Mach. Intell. - May 4, 2026
Developing new molecular compounds is crucial to address pressing challenges, from health to environmental sustainability. However, exploring the molecular space to discover new molecules is difficult owing to the vastness of the space. Here we introduce CoCoGraph, a collaborative and constrained graph diffusion model capable of generating molecules that are...
Bayesian symbolic regression: automated equation discovery from a physicist’s perspective
Philos. Trans. A Math. Phys. Eng. Sci. - April 9, 2026
Symbolic regression automates the process of learning closed-form mathematical models from data. Standard approaches to symbolic regression, as well as newer deep learning approaches, rely on heuristic model selection criteria, heuristic regularization and heuristic exploration of model space. Here, we discuss the probabilistic approach to symbolic regression, an alternative to...
ChemEmbed: a deep learning framework for metabolite identification using enhanced MS/MS data and multidimensional molecular embeddings
Brief. Bioinf. - Feb. 13, 2026
Machine learning offers a promising path to annotating the large number of unidentified MS/MS spectra in metabolomics, addressing the limited coverage of current reference spectral libraries. However, existing methods often struggle with the high dimensionality and sparsity of MS/MS spectra and metabolite structures. ChemEmbed tackles these challenges by integrating multidimensional,...
OUR RESEARCH
Complex Systems
Cells, ecosystems and economies are examples of complex systems. In complex systems, individual components interact with each other, usually in nonlinear ways, giving rise to complex networks of interactions that are neither totally regular nor totally random. Partly because of the interactions themselves and partly because of the interaction's topology, complex systems cannot be properly understood by just analyzing their constituent parts.
Data Science
Humans generate information at an unprecedented pace, with some estimates suggesting that, in a year, we now produce on the order of 10^21 bytes of data, millions of times the amount of information in all the books ever written. Processing this "data deluge", as some have called it, requires new tools and new approaches at the interface of statistics, statistical and machine learning, network theory and statistical physics.
Multidisciplinarity
Our goal is to push forward the boundaries of science. We are interested in addressing fundamental questions in all areas of science including natural, social and economic sciences. We put a special emphasis in the development of tools that aid scientific discovery through understanding and quantification of a specific phenomenon. To this end we have assembled a multidisciplinary team and have established solid collaborations with experts in biology, social sciences, ecology and economics.