Cecilia Clementi

Cecilia Clementi

Auto-generated profile, based on publicly available information

Cecilia Clementi

Department of Physics, Freie Universität Berlin, Berlin, Germany

Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 April 2020 in Annual Review of Physical Chemistry
Verified
Journal Article
Open access
FNFrank Noé
Frank Noé
ATAlexandre Tkatchenko
Alexandre Tkatchenko
KMKlaus-Robert Müller
Klaus-Robert Müller
CCCecilia Clementi
Cecilia Clementi
Machine learning (ML) is transforming all areas of science. The complex and time-consuming calculations in molecular simulations are particularly suitable for an ML revolution and have already been profoundly affected by the application of existing ML methods. Here we review recent ML methods for molecular simulation, with particular focus on (deep) neural networks for the prediction of quantum-mechanical energies and forces, on coarse-grained molecular dynamics, on the extraction of free energy surfaces and kinetics, and on generative network approaches to sample molecular equilibrium structures and compute thermodynamics. To explain these methods and illustrate open methodological problems, we review some important principles of molecular physics and describe how they can be incorporated into ML structures. Finally, we identify and describe a list of open challenges for the interface between ML and molecular simulation.

15 April 2019 in ACS Central Science
Verified
Journal Article
Open access
JWJiang Wang
Jiang Wang
SOSimon Olsson
Simon Olsson
CWChristoph Wehmeyer
Christoph Wehmeyer
APAdrià Pérez
Adrià Pérez
NCNicholas E. Charron
Nicholas E. Charron
CCCecilia Clementi
Cecilia Clementi
Atomistic or ab initio molecular dynamics simulations are widely used to predict thermodynamics and kinetics and relate them to molecular structure. A common approach to go beyond the time- and length-scales accessible with such computationally expensive simulations is the definition of coarse-grained molecular models. Existing coarse-graining approaches define an effective interaction potential to match defined properties of high-resolution models or experimental data. In this paper, we reformulate coarse-graining as a supervised machine learning problem. We use statistical learning theory to decompose the coarse-graining error and cross-validation to select and compare the performance of different models. We introduce CGnets, a deep learning approach, that learns coarse-grained free energy functions and can be trained by a force-matching scheme. CGnets maintain all physically relevant invariances and allow one to incorporate prior physics knowledge to avoid sampling of unphysical structures. We show that CGnets can capture all-atom explicit-solvent free energy surfaces with models using only a few coarse-grained beads and no solvent, while classical coarse-graining methods fail to capture crucial features of the free energy surface. Thus, CGnets are able to capture multibody terms that emerge from the dimensionality reduction.

4 May 2021 in Chemical Reviews
Verified
Journal Article
Open access
AGAldo Glielmo
Aldo Glielmo
BHBrooke E. Husic
Brooke E. Husic
ARAlex Rodriguez
Alex Rodriguez
CCCecilia Clementi
Cecilia Clementi
FNFrank Noé
Frank Noé
ALAlessandro Laio
Alessandro Laio
Unsupervised learning is becoming an essential tool to analyze the increasingly large amounts of data produced by atomistic and molecular simulations, in material science, solid state physics, biophysics, and biochemistry. In this Review, we provide a comprehensive overview of the methods of unsupervised learning that have been most commonly used to investigate simulation data and indicate likely directions for further developments in the field. In particular, we discuss feature representation of molecular systems and present state-of-the-art algorithms of dimensionality reduction, density estimation, and clustering, and kinetic models. We divide our discussion into self-contained sections, each discussing a specific method. In each section, we briefly touch upon the mathematical and algorithmic foundations of the method, highlight its strengths and limitations, and describe the specific ways in which it has been used-or can be used-to analyze molecular simulation data.

14 August 2025 in Science
Verified
Journal Article
Closed access
SLSarah Lewis
Sarah Lewis
THTim Hempel
Tim Hempel
JJJosé Jiménez-Luna
José Jiménez-Luna
MGMichael Gastegger
Michael Gastegger
YXYu Xie
Yu Xie
FNFrank Noé
Frank Noé
Following the sequence and structure revolutions, predicting functionally relevant protein structure changes at scale remains an outstanding challenge. We introduce BioEmu, a deep learning system that emulates protein equilibrium ensembles by generating thousands of statistically independent structures per hour on a single graphics processing unit (GPU). BioEmu integrates more than 200 milliseconds of molecular dynamics (MD) simulations, static structures, and experimental protein stabilities using new training algorithms. It captures diverse functional motions—including cryptic pocket formation, local unfolding, and domain rearrangements—and predicts relative free energies with 1 kilocalorie per mole accuracy compared with millisecond-scale MD and experimental data. BioEmu provides mechanistic insights by jointly modeling structural ensembles and thermodynamic properties. This approach amortizes the cost of MD and experimental data generation, demonstrating a scalable path toward understanding and designing protein function.

27 June 2006 in Proceedings of the National Academy of Sciences
Verified
Journal Article
Closed access
PDPayel Das
Payel Das
MMMark Moll
Mark Moll
HSHernán Stamati
Hernán Stamati
LKLydia Kavraki
Lydia Kavraki
CCCecilia Clementi
Cecilia Clementi
The definition of reaction coordinates for the characterization of a protein-folding reaction has long been a controversial issue, even for the “simple” case in which one single free-energy barrier separates the folded and unfolded ensemble. We propose a general approach to this problem to obtain a few collective coordinates by using nonlinear dimensionality reduction. We validate the usefulness of this method by characterizing the folding landscape associated with a coarse-grained protein model of src homology 3 as sampled by molecular dynamics simulations. The folding free-energy landscape projected on the few relevant coordinates emerging from the dimensionality reduction can correctly identify the transition-state ensemble of the reaction. The first embedding dimension efficiently captures the evolution of the folding process along the main folding route. These results clearly show that the proposed method can efficiently find a low-dimensional representation of a complex process such as protein folding.

17 March 2021 in Journal of Chemical Theory and Computation
Verified
Journal Article
Open access
SDStefan Doerr
Stefan Doerr
MMMaciej Majewski
Maciej Majewski
APAdrià Pérez
Adrià Pérez
AKAndreas Krämer
Andreas Krämer
CCCecilia Clementi
Cecilia Clementi
GFGianni De Fabritiis
Gianni De Fabritiis
Molecular dynamics simulations provide a mechanistic description of molecules by relying on empirical potentials. The quality and transferability of such potentials can be improved leveraging data-driven models derived with machine learning approaches. Here, we present TorchMD, a framework for molecular simulations with mixed classical and machine learning potentials. All force computations including bond, angle, dihedral, Lennard-Jones, and Coulomb interactions are expressed as PyTorch arrays and operations. Moreover, TorchMD enables learning and simulating neural network potentials. We validate it using standard Amber all-atom simulations, learning an ab initio potential, performing an end-to-end training, and finally learning and simulating a coarse-grained model for protein folding. We believe that TorchMD provides a useful tool set to support molecular simulations of machine learning potentials. Code and data are freely available at github.com/torchmd.