<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>9292</id>
    <completedYear/>
    <publishedYear>2025</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>1284</pageFirst>
    <pageLast>1292</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume>17</volume>
    <type>article</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2025-07-18</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Navigating protein landscapes with a machine-learned transferable coarse-grained model</title>
    <abstract language="eng">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.</abstract>
    <parentTitle language="eng">Nature Chemistry</parentTitle>
    <identifier type="doi">10.1038/s41557-025-01874-0</identifier>
    <identifier type="arxiv">2310.18278</identifier>
    <enrichment key="PeerReviewed">yes</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <author>Nicholas Charron</author>
    <submitter>Nicholas Charron</submitter>
    <author>Félix Musil</author>
    <author>Andrea Guljas</author>
    <author>Yaoyi Chen</author>
    <author>Klara Bonneau</author>
    <author>Aldo Pasos-Trejo</author>
    <author>Venturin Jacopo</author>
    <author>Gusew Daria</author>
    <author>Iryna Zaporozhets</author>
    <author>Andreas Krämer</author>
    <author>Clark Templeton</author>
    <author>Kelkar Atharva</author>
    <author>Aleksander Durumeric</author>
    <author>Simon Olsson</author>
    <author>Adrià Pérez</author>
    <author>Maciej Majewski</author>
    <author>Brooke Husic</author>
    <author>Ankit Patel</author>
    <author>Gianni De Fabritiis</author>
    <author>Frank Noé</author>
    <author>Cecilia Clementi</author>
    <collection role="institutes" number="vas">Distributed Algorithms and Supercomputing</collection>
    <collection role="projects" number="no-project">no-project</collection>
    <collection role="persons" number="charron">Charron, Nicholas</collection>
  </doc>
  <doc>
    <id>9348</id>
    <completedYear/>
    <publishedYear>2023</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume>14</volume>
    <type>article</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Machine learning coarse-grained potentials of protein thermodynamics</title>
    <abstract language="eng">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.</abstract>
    <parentTitle language="eng">Nature Communications</parentTitle>
    <identifier type="doi">10.1038/s41467-023-41343-1</identifier>
    <enrichment key="PeerReviewed">yes</enrichment>
    <enrichment key="AcceptedDate">29 August 2023</enrichment>
    <enrichment key="opus.source">publish</enrichment>
    <author>Maciej Majewski</author>
    <submitter>Nicholas Charron</submitter>
    <author>Adrià Pérez</author>
    <author>Philipp Thölke</author>
    <author>Stefan Doerr</author>
    <author>Nicholas Charron</author>
    <author>Toni Giorgino</author>
    <author>Brooke Husic</author>
    <author>Cecilia Clementi</author>
    <author>Frank Noé</author>
    <author>Gianni De Fabritiis</author>
    <collection role="institutes" number="vas">Distributed Algorithms and Supercomputing</collection>
    <collection role="projects" number="no-project">no-project</collection>
    <collection role="persons" number="charron">Charron, Nicholas</collection>
  </doc>
</export-example>
