Navigating protein landscapes with a machine-learned transferable coarse-grained model

Machine Learning


  • Lindorff-Larsen, K., Piana, S., Dror, R. O. & Shaw, D. E. How fast-folding proteins fold. Science 334, 517–520 (2011).

    CAS 
    PubMed 

    Google Scholar 

  • Plattner, N., Doerr, S., De Fabritiis, G. & Noé, F. Complete protein–protein association kinetics in atomic detail revealed by molecular dynamics simulations and Markov modelling. Nat. Chem. 9, 1005–1011 (2017).

    CAS 
    PubMed 

    Google Scholar 

  • Voelz, V. A., Bowman, G. R., Beauchamp, K. & Pande, V. S. Molecular simulation of ab initio protein folding for a millisecond folder NTL9(1–39). J. Am. Chem. Soc. 132, 1526–1528 (2010).

  • Noé, F. & Clementi, C. Collective variables for the study of long-time kinetics from molecular trajectories: theory and methods. Curr. Opin. Struct. Biol. 43, 141–147 (2017).

    PubMed 

    Google Scholar 

  • Husic, B. E. & Pande, V. S. Markov state models: from an art to a science. J. Am. Chem. Soc. 140, 2386–2396 (2018).

    CAS 
    PubMed 

    Google Scholar 

  • Abramson, J. et al. Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature 630, 493–500 (2024).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Lewis, S. et al. Scalable emulation of protein equilibrium ensembles with generative deep learning. Preprint at bioRxiv https://www.biorxiv.org/content/10.1101/2024.12.05.626885v1 (2024).

  • Casasnovas, R., Limongelli, V., Tiwary, P., Carloni, P. & Parrinello, M. Unbinding kinetics of a p38 map kinase type II inhibitor from metadynamics simulations. J. Am. Chem. Soc. 139, 4780–4788 (2017).

    CAS 
    PubMed 

    Google Scholar 

  • Unke, O. T. et al. Biomolecular dynamics with machine-learned quantum-mechanical force fields trained on diverse chemical fragments. Sci. Adv. 10, eadn4397 (2024).

  • Kozinsky, B., Musaelian, A., Johansson, A. & Batzner, S. Scaling the leading accuracy of deep equivariant models to biomolecular simulations of realistic size. In Proc. International Conference for High Performance Computing, Networking, Storage and Analysis article no. 2, 1–12 (ACM, 2023).

  • Smith, J. S., Isayev, O. & Roitberg, A. E. ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost. Chem. Sci. 8, 3192–3203 (2017).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Rufa, D. A. et al. Towards chemical accuracy for alchemical free energy calculations with hybrid physics-based machine learning/molecular mechanics potentials. Preprint at bioRxiv https://doi.org/10.1101/2020.07.29.227959 (2020).

  • Onuchic, J. N., Luthey-Schulten, Z. & Wolynes, P. G. Theory of protein folding: the energy landscape perspective. Annu. Rev. Phys. Chem. 48, 545–600 (1997).

    CAS 
    PubMed 

    Google Scholar 

  • Clementi, C., Nymeyer, H. & Onuchic, J. N. Topological and energetic factors: what determines the structural details of the transition state ensemble and ‘en-route’ intermediates for protein folding? An investigation for small globular proteins. J. Mol. Biol. 298, 937–953 (2000).

    CAS 
    PubMed 

    Google Scholar 

  • Souza, P. C. T. et al. Martini 3: a general purpose force field for coarse-grained molecular dynamics. Nat. Methods 18, 382–388 (2021).

    CAS 
    PubMed 

    Google Scholar 

  • Liwo, A. et al. A general method for the derivation of the functional forms of the effective energy terms in coarse-grained energy functions of polymers. III. Determination of scale-consistent backbone-local and correlation potentials in the UNRES force field and force-field calibration and validation. J. Chem. Phys. 150, 155104 (2019).

    PubMed 

    Google Scholar 

  • Davtyan, A. et al. AWSEM-MD: protein structure prediction using coarse-grained physical potentials and bioinformatically based local structure biasing. J. Phys. Chem. B 116, 8494–8503 (2012).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Wang, J. et al. Multi-body effects in a coarse-grained protein force field. J. Chem. Phys. 154, 164113 (2021).

    CAS 
    PubMed 

    Google Scholar 

  • Zaporozhets, I. & Clementi, C. Multibody terms in protein coarse-grained models: a top-down perspective. J. Phys. Chem. B 127, 6920–6927 (2023).

    CAS 
    PubMed 

    Google Scholar 

  • Jin, J., Pak, A. J., Durumeric, A. E. P., Loose, T. D. & Voth, G. A. Bottom-up coarse-graining: principles and perspectives. J. Chem. Theory Comput. 18, 5759–5791 (2022).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Wang, J. et al. Machine learning of coarse-grained molecular dynamics force fields. ACS Cent. Sci. 5, 755–767 (2019).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Husic, B. E. et al. Coarse graining molecular dynamics with graph neural networks. J. Chem. Phys. 153, 194101 (2020).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Ding, X. & Zhang, B. Contrastive learning of coarse-grained force fields. J. Chem. Theory Comput. 18, 6334–6344 (2022).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Majewski, M. et al. Machine learning coarse-grained potentials of protein thermodynamics. Nat. Commun. 14, 5739 (2023).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Köhler, J., Chen, Y., Krämer, A., Clementi, C. & Noé, F. Flow-matching: efficient coarse-graining of molecular dynamics without forces. J. Chem. Theory Comput. 19, 942–952 (2023).

    PubMed 

    Google Scholar 

  • Chennakesavalu, S., Toomer, D. J. & Rotskoff, G. M. Ensuring thermodynamic consistency with invertible coarse-graining. J. Chem. Phys. 158, 124126 (2023).

  • Krämer, A. et al. Statistically optimal force aggregation for coarse-graining molecular dynamics. J. Phys. Chem. Lett. 14, 3970–3979 (2023).

    PubMed 

    Google Scholar 

  • Wellawatte, G. P., Hocky, G. M. & White, A. D. Neural potentials of proteins extrapolate beyond training data. J. Chem. Phys. 159, 085103 (2023).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Airas, J., Ding, X. & Zhang, B. Transferable implicit solvation via contrastive learning of graph neural networks. ACS Cent. Sci. 9, 2286–2297 (2023).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Marloes Arts, V. G. S. et al. Two for one: diffusion models and force fields for coarse-grained molecular dynamics. J. Chem. Theory Comput. 19, 6151–6159 (2023).

    PubMed 

    Google Scholar 

  • Izvekov, S. & Voth, G. A. A multiscale coarse-graining method for biomolecular systems. J. Phys. Chem. B 109, 2469–2473 (2005).

    CAS 
    PubMed 

    Google Scholar 

  • Noid, W. G. et al. The multiscale coarse-graining method. I. A rigorous bridge between atomistic and coarse-grained models. J. Chem. Phys. 128, 244114 (2008).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Chen, Y. et al. Machine learning implicit solvation for molecular dynamics. J. Chem. Phys. 155, 084101 (2021).

    CAS 
    PubMed 

    Google Scholar 

  • Durumeric, A. E. P. et al. Machine learned coarse-grained protein force-fields: are we there yet? Curr. Opin. Struct. Biol. 79, 102533 (2023).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Liwo, A., Czaplewski, C., Pillardy, J. & Scheraga, H. A. Cumulant-based expressions for the multibody terms for the correlation between local and electrostatic interactions in the united-residue force field. J. Chem. Phys. 115, 2323–2347 (2001).

    CAS 

    Google Scholar 

  • Bryson, J. W., Desjarlais, J. R., Handel, T. M. & Degrado, W. F. From coiled coils to small globular proteins: design of a native-like three-helix bundle. Protein Sci. 7, 1404–1414 (1998).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Periole, X., Cavalli, M., Marrink, S.-J. & Ceruso, M. A. Combining an elastic network with a coarse-grained molecular force field: structure, dynamics and intermolecular recognition. J. Chem. Theory Comput. 5, 2531–2543 (2009).

    CAS 
    PubMed 

    Google Scholar 

  • Poma, A. B., Cieplak, M. & Theodorakis, P. E. Combining the MARTINI and structure-based coarse-grained approaches for the molecular dynamics studies of conformational transitions in proteins. J. Chem. Theory Comput. 13, 1366–1374 (2017).

    CAS 
    PubMed 

    Google Scholar 

  • Pérez-Hernández, G., Paul, F., Giorgino, T., De Fabritiis, G. & Noé, F. Identification of slow molecular order parameters for Markov model construction. J. Chem. Phys. 139, 015102 (2013).

    PubMed 

    Google Scholar 

  • Rogers, J. M. et al. Interplay between partner and ligand facilitates the folding and binding of an intrinsically disordered protein. Proc. Natl Acad. Sci. USA 111, 15420–15425 (2014).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Went, H. M. & Jackson, S. E. Ubiquitin folds through a highly polarized transition state. Protein Eng Des. Sel. 18, 229–237 (2005).

    CAS 
    PubMed 

    Google Scholar 

  • Zhang, Z. et al. Predicting folding free energy changes upon single point mutations. Bioinformatics 28, 664–671 (2012).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Gapsys, V., Michielssens, S., Seeliger, D. & Groot, B. L. Accurate and rigorous prediction of the changes in protein free energies in a large scale mutation scan. Angew. Chem. Int. Ed. 55, 7364–7368 (2016).

    CAS 

    Google Scholar 

  • Vendruscolo, M. & Domany, E. Pairwise contact potentials are unsuitable for protein folding. J. Chem. Phys. 109, 11101–11108 (1998).

    CAS 

    Google Scholar 

  • Ejtehadi, M., Avall, S. & Plotkin, S. Three-body interactions improve the prediction of rate and mechanism in protein folding models. Proc. Natl Acad. Sci. USA 101, 15088–15093 (2004).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Scherer, C. & Andrienko, D. Understanding three-body contributions to coarse-grained force fields. Phys. Chem. Chem. Phys. 20, 22387–22394 (2018).

    CAS 
    PubMed 

    Google Scholar 

  • Kar, P. & Feig, M. Recent advances in transferable coarse-grained modeling of proteins. Adv. Protein Chem. Struct. Biol. 96, 143–180 (2014).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Hills Jr, R. D., Lu, L. & Voth, G. A. Multiscale coarse-graining of the protein energy landscape. PLoS Comput. Biol. 6, 1000827 (2010).

    Google Scholar 

  • Schütt, K. T., Sauceda, H. E., Kindermans, P.-J., Tkatchenko, A. & Müller, K.-R. SchNet: a deep learning architecture for molecules and materials. J. Chem. Phys. 148, 241722 (2018).

    PubMed 

    Google Scholar 

  • Sheinerman, F. B. & Honig, B. On the role of electrostatic interactions in the design of protein–protein interfaces. J. Mol. Biol. 318, 161–177 (2002).

    CAS 
    PubMed 

    Google Scholar 

  • Zhang, Z., Witham, S. & Alexov, E. On the role of electrostatics in protein–protein interactions. Phys. Biol. 8, 035001 (2011).

    PubMed 
    PubMed Central 

    Google Scholar 

  • Ko, T. W., Finkler, J. A., Goedecker, S. & Behler, J. A fourth-generation high-dimensional neural network potential with accurate electrostatics including non-local charge transfer. Nat. Commun. 12, 398 (2021).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Unke, O. T. et al. SpookyNet: learning force fields with electronic degrees of freedom and nonlocal effects. Nat. Commun. 12, 7273 (2021).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Kosmala, A., Gasteiger, J., Gao, N. & Günnemann, S. Ewald-based long-range message passing for molecular graphs. In Proc. International Conference on Machine Learning (PMLR, 2023)

  • Caruso, A. et al. Extending the RANGE of graph neural networks: relaying attention nodes for global encoding. Preprint at https://arxiv.org/abs/2502.13797 (2025).

  • Thölke, P. & Fabritiis, G. D. Equivariant transformers for neural network based molecular potentials. In 10th International Conference on Learning Representations (Curran Associates, 2022).

  • Kidder, K. M., Szukalo, R. J. & Noid, W. Energetic and entropic considerations for coarse-graining. Eur. Phys. J. B 94, 153 (2021).

    CAS 

    Google Scholar 

  • Krishna, V., Noid, W. G. & Voth, G. A. The multiscale coarse-graining method. IV. Transferring coarse-grained potentials between temperatures. J. Chem. Phys. 131, 024103 (2009).

    PubMed 
    PubMed Central 

    Google Scholar 

  • Pretti, E. & Shell, M. S. A microcanonical approach to temperature-transferable coarse-grained models using the relative entropy. J. Chem. Phys. 155, 094102 (2021).

    CAS 
    PubMed 

    Google Scholar 

  • Wang, W. & Gómez-Bombarelli, R. Coarse-graining auto-encoders for molecular dynamics. npj Comput. Mater. 5, 125 (2019).

    Google Scholar 

  • Shirts, M. R. & Chodera, J. D. Statistically optimal analysis of samples from multiple equilibrium states. J. Chem. Phys. 129, 124105 (2008).

    PubMed 
    PubMed Central 

    Google Scholar 

  • Sillitoe, I. et al. CATH: comprehensive structural and functional annotations for genome sequences. Nucleic Acids Res. 43, 376–381 (2015).

    Google Scholar 

  • Paszke, A. et al. PyTorch: an imperative style, high-performance deep learning library. In Proc. Neural Information Processing Systems Vol. 32 (eds Wallach, H. et al.) article no. 721, 8026–8037 (Curran Associates, 2019).

  • Fey, M. & Lenssen, J. E. Fast graph representation learning with PyTorch Geometric. In Proc. ICLR Workshop on Representation Learning on Graphs and Manifolds (Curran Associates, 2019).

  • Batzner, S. et al. E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials. Nat. Commun. 13, 2453 (2022).

    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Batatia, I., Kovacs, D. P., Simm, G., Ortner, C. & Csányi, G. MACE: higher order equivariant message passing neural networks for fast and accurate force fields. In Proc. Advances in Neural Information Processing Systems Vol. 35 (eds Koyejo, S. et al.) 11423–11436 (Curran Associates, 2022).

  • Matysiak, S. & Clementi, C. Optimal combination of theory and experiment for the characterization of the protein folding landscape of S6: how far can a minimalist model go? J. Mol. Biol. 343, 235–248 (2004).

    CAS 
    PubMed 

    Google Scholar 

  • Matysiak, S. & Clementi, C. Minimalist protein model as a diagnostic tool for misfolding and aggregation. J. Mol. Biol. 363, 297–308 (2006).

    CAS 
    PubMed 

    Google Scholar 

  • Charron, N., Bonneau, K., Pasos-Trejo, A. & Guljas, A. Navigating protein landscapes with a machine-learned transferable coarse-grained model (data and codes). Zenodo https://doi.org/10.5281/zenodo.15465782 (2025).

  • Charron, N. et al. ClementiGroup/mlcg: 0.0.3. Zenodo https://doi.org/10.5281/zenodo.15482457 (2025).



  • Source link

    Leave a Reply

    Your email address will not be published. Required fields are marked *