Agenda

ECLT Fellow Cecilia Clementi awarded an ERC Advanced Grant for the ProDyGe Project

Professor Cecilia Clementi (Freie Universität Berlin), Fellow of the European Center for Living Technology (ECLT) and Professor of Theoretical and Computational Biophysics at Freie Universität Berlin, has been awarded a prestigious ERC Advanced Grant from the European Research Council (ERC). The grant will support the project ProDyGe – Protein Dynamics with Generalized machine-learned potentials.

The ERC Advanced Grant supports outstanding researchers with an established track record who wish to pursue ambitious and groundbreaking projects in emerging areas of research.

The ProDyGe project aims to develop a universal machine learning-based model for the efficient and accurate simulation of biomolecular dynamics. Its goal is to make biomolecular processes that have so far been difficult or nearly impossible to simulate predictable, regardless of system size and across longer timescales. This will enable a deeper understanding of complex biological mechanisms, including protein folding, drug binding, and the functioning of large molecular complexes, opening new opportunities for biomedical research.

"Our goal with ProDyGe is to make biomolecular processes that were previously difficult or nearly impossible to simulate predictable, regardless of size and across longer timescales. If we succeed, we will be much better equipped to understand complex biological mechanisms and open up new methods of investigating the effects of different medications or how large molecular machines function. The ERC Advanced Grant gives us the opportunity to pursue a totally novel approach that lies at the intersection of physics, biology, and artificial intelligence," says Cecilia Clementi.

Cecilia Clementi's research combines methods from statistical physics, computational biophysics, and machine learning to gain a deeper understanding of complex biological processes at the molecular level. Through ProDyGe, her research team will develop a new physics-based machine learning approach that integrates information from high-resolution simulations with experimental data. The resulting model will be transferable across different biomolecular systems and capable of predicting structural changes, free energy landscapes, and binding affinities between biological molecules.

Read the full press release