@article{CharronMusilGuljasetal., author = {Charron, Nicholas and Musil, F{\´e}lix and Guljas, Andrea and Chen, Yaoyi and Bonneau, Klara and Pasos-Trejo, Aldo and Jacopo, Venturin and Daria, Gusew and Zaporozhets, Iryna and Kr{\"a}mer, Andreas and Templeton, Clark and Atharva, Kelkar and Durumeric, Aleksander and Olsson, Simon and P{\´e}rez, Adri{\`a} and Majewski, Maciej and Husic, Brooke and Patel, Ankit and De Fabritiis, Gianni and No{\´e}, Frank and Clementi, Cecilia}, title = {Navigating protein landscapes with a machine-learned transferable coarse-grained model}, series = {Arxiv}, journal = {Arxiv}, doi = {https://doi.org/10.48550/arXiv.2310.18278}, abstract = {The most popular and universally predictive protein simulation models employ all-atom molecular dynamics (MD), but they come at extreme computational cost. The development of a universal, computationally efficient coarse-grained (CG) model with similar prediction performance has been a long-standing challenge. By combining recent deep learning methods with a large and diverse training set of all-atom protein simulations, we here develop a bottom-up CG force field with chemical transferability, which can be used for extrapolative molecular dynamics on new sequences not used during model parametrization. We demonstrate that the model successfully predicts folded structures, intermediates, metastable folded and unfolded basins, and the fluctuations of intrinsically disordered proteins while it is several orders of magnitude faster than an all-atom model. This showcases the feasibility of a universal and computationally efficient machine-learned CG model for proteins.}, language = {en} } @article{MajewskiPerezThoelkeetal., author = {Majewski, Maciej and P{\´e}rez, Adri{\`a} and Th{\"o}lke, Philipp and Doerr, Stefan and Charron, Nicholas and Giorgino, Toni and Husic, Brooke and Clementi, Cecilia and No{\´e}, Frank and De Fabritiis, Gianni}, title = {Machine learning coarse-grained potentials of protein thermodynamics}, series = {Nature Communications}, volume = {14}, journal = {Nature Communications}, doi = {10.1038/s41467-023-41343-1}, abstract = {A generalized understanding of protein dynamics is an unsolved scientific problem, the solution of which is critical to the interpretation of the structure-function relationships that govern essential biological processes. Here, we approach this problem by constructing coarse-grained molecular potentials based on artificial neural networks and grounded in statistical mechanics. For training, we build a unique dataset of unbiased all-atom molecular dynamics simulations of approximately 9 ms for twelve different proteins with multiple secondary structure arrangements. The coarse-grained models are capable of accelerating the dynamics by more than three orders of magnitude while preserving the thermodynamics of the systems. Coarse-grained simulations identify relevant structural states in the ensemble with comparable energetics to the all-atom systems. Furthermore, we show that a single coarse-grained potential can integrate all twelve proteins and can capture experimental structural features of mutated proteins. These results indicate that machine learning coarse-grained potentials could provide a feasible approach to simulate and understand protein dynamics.}, language = {en} } @article{DurumericCharronTempletonetal., author = {Durumeric, Aleksander and Charron, Nicholas and Templeton, Clark and Musil, F{\´e}lix and Bonneau, Klara and Pasos-Trejo, Aldo and Chen, Yaoyi and Kelkar, Atharva and No{\´e}, Frank and Clementi, Cecilia}, title = {Machine learned coarse-grained protein force-fields: Are we there yet?}, series = {Current Opinion in Structural Biology}, volume = {79}, journal = {Current Opinion in Structural Biology}, doi = {10.1016/j.sbi.2023.102533}, abstract = {The successful recent application of machine learning methods to scientific problems includes the learning of flexible and accurate atomic-level force-fields for materials and biomolecules from quantum chemical data. In parallel, the machine learning of force-fields at coarser resolutions is rapidly gaining relevance as an efficient way to represent the higher-body interactions needed in coarse-grained force-fields to compensate for the omitted degrees of freedom. Coarse-grained models are important for the study of systems at time and length scales exceeding those of atomistic simulations. However, the development of transferable coarse-grained models via machine learning still presents significant challenges. Here, we discuss recent developments in this field and current efforts to address the remaining challenges.}, language = {en} } @article{KraemerDurumericCharronetal., author = {Kr{\"a}mer, Andreas and Durumeric, Aleksander and Charron, Nicholas and Chen, Yaoyi and Clementi, Cecilia and No{\´e}, Frank}, title = {Statistically optimal force aggregation for coarse-graining molecular dynamics}, series = {The Journal of Physical Chemistry Letters}, volume = {14}, journal = {The Journal of Physical Chemistry Letters}, number = {17}, doi = {10.1021/acs.jpclett.3c00444}, pages = {3970 -- 3979}, abstract = {Machine-learned coarse-grained (CG) models have the potential for simulating large molecular complexes beyond what is possible with atomistic molecular dynamics. However, training accurate CG models remains a challenge. A widely used methodology for learning bottom-up CG force fields maps forces from all-atom molecular dynamics to the CG representation and matches them with a CG force field on average. We show that there is flexibility in how to map all-atom forces to the CG representation and that the most commonly used mapping methods are statistically inefficient and potentially even incorrect in the presence of constraints in the all-atom simulation. We define an optimization statement for force mappings and demonstrate that substantially improved CG force fields can be learned from the same simulation data when using optimized force maps. The method is demonstrated on the miniproteins chignolin and tryptophan cage and published as open-source code.}, language = {en} } @article{KlusNueskePeitzetal., author = {Klus, Stefan and N{\"u}ske, Feliks and Peitz, Sebastian and Niemann, Jan-Hendrik and Clementi, Cecilia and Sch{\"u}tte, Christof}, title = {Data-driven approximation of the Koopman generator: Model reduction, system identification, and control}, series = {Physica D: Nonlinear Phenomena}, volume = {406}, journal = {Physica D: Nonlinear Phenomena}, doi = {10.1016/j.physd.2020.132416}, language = {en} }