Breaking timescales with generative sampling of conformational transitions

Machine Learning


  • Dror, R. O., Dirks, R. M., Grossman, J. P., Xu, H. & Shaw, D. E. Biomolecular simulation: a computational microscope for molecular biology. Annu. Rev. Biophys. 41, 429–452 (2012).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Chipot, C. Free energy methods for the description of molecular processes. Annu. Rev. Biophys. 52, 113–138 (2023).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Kang, C. et al. Convergence is not correctness: context-dependent performance of enhanced-sampling methods across biological complexity. Nat. Commun. 17, 6245 (2026).

  • Ho, J., Jain, A. N. & Abbeel, P. Denoising diffusion probabilistic models. In Proc. Advances in Neural Information Processing Systems Vol. 33 (eds Larochelle, H. et al.) 6840–6851 (Curran Associates, 2020).

  • Roux, B. Transition rate theory, spectral analysis, and reactive paths. J. Chem. Phys. 156, 134111 (2022).

    Article 
    ADS 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

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

    Article 
    ADS 
    CAS 
    PubMed 

    Google Scholar 

  • Jung, H. et al. Machine-guided path sampling to discover mechanisms of molecular self-organization. Nat. Comput. Sci. 3, 334–345 (2023).

    Article 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Shaw, D. E. et al. Anton 3: twenty microseconds of molecular dynamics simulation before lunch. In Proc. International Conference for High Performance Computing, Networking, Storage and Analysis (eds de Supinski, B. R., Hall, M. W. & Gamblin, T.) 1:1–1:11 (Association for Computing Machinery, 2021).

  • Ren, W. & Vanden-Eijnden, E. Finite temperature string method for the study of rare events. J. Phys. Chem. B 109, 6688–6693 (2005).

    Article 
    PubMed 

    Google Scholar 

  • Pan, A. C., Sezer, D. & Roux, B. Finding transition pathways using the string method with swarms of trajectories. J. Phys. Chem. B 112, 3432–3440 (2008).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Miao, M. et al. Avoiding non-equilibrium effects in adaptive biasing force calculations. Mol. Simul. 47, 390–394 (2021).

    Article 
    CAS 

    Google Scholar 

  • Vanden-Eijnden, E. & Tal, F. A. Transition state theory: variational formulation, dynamical corrections, and error estimates. J. Chem. Phys. 123, 184103 (2005).

    Article 
    ADS 
    PubMed 

    Google Scholar 

  • He, Z., Chipot, C. & Roux, B. Committor-consistent variational string method. J. Phys. Chem. Lett. 13, 9263–9271 (2022).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Horvath, F. et al. STIM1 transmembrane helix dimerization captured by AI-guided transition path sampling. Proc. Natl Acad. Sci. USA 122, e2506516122 (2025).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Chen, H., Roux, B. & Chipot, C. Discovering reaction pathways, slow variables, and committor probabilities with machine learning. J. Chem. Theory Comput. 19, 4414–4426 (2023).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Megías, A. et al. Iterative variational learning of committor-consistent transition pathways using artificial neural networks. Nat. Comput. Sci. 5, 592–602 (2025).

    Article 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Giuseppe Chen, C. et al. Following the committor flow: a data-driven discovery of transition pathways. J. Chem. Theory Comput. 22, 1258–1265 (2026).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Contreras Arredondo, S. et al. Learning the committor without collective variables. Nat. Comput. Sci. 6, 350–357 (2026).

    Article 
    PubMed 

    Google Scholar 

  • Noé, F., Olsson, S., Köhler, J. & Wu, H. Boltzmann generators: sampling equilibrium states of many-body systems with deep learning. Science 365, eaaw1147 (2019).

    Article 
    ADS 
    PubMed 

    Google Scholar 

  • Jing, B., Stärk, H., Jaakkola, T. & Berger, B. Generative modeling of molecular dynamics trajectories. In Proc. Advances in Neural Information Processing Systems Vol. 37 (eds Globerson, A. et al.) 40534–40564 (Curran Associates, 2024).

  • Lewis, S. et al. Scalable emulation of protein equilibrium ensembles with generative deep learning. Science 389, eadv9817 (2025).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Thiemann, F. L. et al. Force-free molecular dynamics through autoregressive equivariant networks. Nat. Mach. Intell. 8, 764–776 (2026).

    Article 

    Google Scholar 

  • Seong, K., Park, S., Kim, S., Kim, W. Y. & Ahn, S. Transition path sampling with improved off-policy training of diffusion path samplers. In Proc. International Conference on Learning Representations Vol. 2025 (eds Yue, Y. et al.) 93040–93062 (ICLR, 2025).

  • Raja, S. et al. Action-minimization meets generative modeling: efficient transition path sampling with the Onsager–Machlup functional. In Proc. 42nd International Conference on Machine Learning Vol. 267 (eds Singh, A. et al.) 50972–51008 (PMLR, 2025).

  • Kania, S., Webber, R. J., Simpson, G., Aristoff, D. & Zuckerman, D. M. Randomized Iterative trajectory reweighting for steady-state distributions without discretization error. Proc. Natl Acad. Sci. USA 123, e2529246123 (2026).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Bolhuis, P. G., Dellago, C., Geissler, P. L. & Chandler, D. Transition path sampling: throwing ropes over mountains in the dark. J. Phys. Condens. Matter 12, A147–A152 (2000).

    Article 
    ADS 
    CAS 

    Google Scholar 

  • Juraszek, J. & Bolhuis, P. G. Sampling the multiple folding mechanisms of Trp-cage in explicit solvent. Proc. Natl Acad. Sci. USA 103, 15859–15864 (2006).

    Article 
    ADS 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Chen, H. & Chipot, C. Chasing collective variables using temporal data-driven strategies. QRB Discov. 4, e2 (2023).

    Article 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Chen, H. et al. A companion guide to the string method with swarms of trajectories: characterization, performance, and pitfalls. J. Chem. Theory Comput. 18, 1406–1422 (2022).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Roh, S.-H. et al. Cryo-EM and MD infer water-mediated proton transport and autoinhibition mechanisms of the Vo complex. Sci. Adv. 6, eabb9605 (2020).

    Article 
    ADS 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Blanc, F. E. C. & Hummer, G. Mechanism of proton-powered c-ring rotation in a mitochondrial ATP synthase. Proc. Natl Acad. Sci. USA 121, e2314199121 (2024).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Zhou, R. Trp-cage: folding free energy landscape in explicit water. Proc. Natl Acad. Sci. USA 100, 13280–13285 (2003).

    Article 
    ADS 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Marinelli, F., Pietrucci, F., Laio, A. & Piana, S. A kinetic model of Trp-cage folding from multiple biased molecular dynamics simulations. PLoS Comput. Biol. 5, e1000452 (2009).

    Article 
    ADS 
    MathSciNet 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Sidky, H., Chen, W. & Ferguson, A. L. High-resolution Markov state models for the dynamics of Trp-cage miniprotein constructed over slow folding modes identified by state-free reversible VAMPnets. J. Phys. Chem. B 123, 7999–8009 (2019).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Klingenberg, M. The ADP and ATP transport in mitochondria and its carrier. Biochim. Biophys. Acta Biomembr. 1778, 1978–2021 (2008).

    Article 
    CAS 

    Google Scholar 

  • Kunji, E. R. & Ruprecht, J. J. The mitochondrial ADP/ATP carrier exists and functions as a monomer. Biochem. Soc. Trans. 48, 1419–1432 (2020).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Tamura, K. & Hayashi, S. Atomistic modeling of alternating access of a mitochondrial ADP/ATP membrane transporter with molecular simulations. PLoS One 12, 1–21 (2017).

    Article 

    Google Scholar 

  • Pietropaolo, A., Pierri, C. L., Palmieri, F. & Klingenberg, M. The switching mechanism of the mitochondrial ADP/ATP carrier explored by free-energy landscapes. Biochim. Biophys. Acta Bioenerg. 1857, 772–781 (2016).

    Article 
    CAS 

    Google Scholar 

  • Yao, S. et al. Mechanistic insights into multiple-step transport of mitochondrial ADP/ATP carrier. Comput. Struct. Biotechnol. J. 20, 1829–1840 (2022).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Yi, Q. et al. Molecular dynamics simulations on apo ADP/ATP carrier shed new lights on the featured motif of the mitochondrial carriers. Mitochondrion 47, 94–102 (2019).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Springett, R., King, M. S., Crichton, P. G. & Kunji, E. R. Modelling the free energy profile of the mitochondrial ADP/ATP carrier. Biochim. Biophys. Acta Bioenerg. 1858, 906–914 (2017).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Okazaki, K.-I. et al. Mechanism of the electroneutral sodium/proton antiporter PaNhaP from transition-path shooting. Nat. Commun. 10, 1742 (2019).

    Article 
    ADS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Thompson, M. J. et al. Asynchronous subunit transitions prime acetylcholine receptor activation. Science 391, eadw1264 (2025).

    Article 

    Google Scholar 

  • Lev, B. et al. String method solution of the gating pathways for a pentameric ligand-gated ion channel. Proc. Natl Acad. Sci. USA 114, E4158–E4167 (2017).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Bergh, C., Heusser, S. A., Howard, R. & Lindahl, E. Markov state models of proton- and pore-dependent activation in a pentameric ligand-gated ion channel. eLife 10, e68369 (2021).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Ajaz, A. et al. Concerted vs stepwise mechanisms in dehydro-Diels-Alder reactions. J. Org. Chem. 76, 9320–9328 (2011).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Biroli, G. & Kurchan, J. Metastable states in glassy systems. Phys. Rev. E 64, 016101 (2001).

    Article 
    ADS 
    CAS 

    Google Scholar 

  • Yang, S., Banavali, N. K. & Roux, B. Mapping the conformational transition in Src activation by cumulating the information from multiple molecular dynamics trajectories. Proc. Natl Acad. Sci. USA 106, 3776–3781 (2009).

    Article 
    ADS 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Moradi, M. & Tajkhorshid, E. Mechanistic picture for conformational transition of a membrane transporter at atomic resolution. Proc. Natl Acad. Sci. USA 110, 18916–18921 (2013).

    Article 
    ADS 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Shaw, D. E. et al. Anton, a special-purpose machine for molecular dynamics simulation. Commun. ACM 51, 91–97 (2008).

    Article 

    Google Scholar 

  • Sipka, M., Dietschreit, J. C. B., Grajciar, L. & Gomez-Bombarelli, R. Differentiable simulations for enhanced sampling of rare events. In Proc. 40th International Conference on Machine Learning Vol. 202 (eds Krause, A. et al.) 31990–32007 (PMLR, 2023).

  • Swenson, D. W. H., Prinz, J.-H., Noé, F., Chodera, J. D. & Bolhuis, P. G. OpenPathSampling: a Python framework for path sampling simulations. 1. Basics. J. Chem. Theory Comput. 15, 813–836 (2019).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Belkacemi, Z., Gkeka, P., Lelièvre, T. & Stoltz, G. Chasing collective variables using autoencoders and biased trajectories. J. Chem. Theory Comput. 18, 59–78 (2022).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Frassek, M., Arjun, A. & Bolhuis, P. G. An extended autoencoder model for reaction coordinate discovery in rare event molecular dynamics datasets. J. Chem. Phys. 155, 064103 (2021).

    Article 
    ADS 
    CAS 
    PubMed 

    Google Scholar 

  • Zou, Z., Wang, D. & Tiwary, P. A graph neural network-state predictive information bottleneck (GNN-SPIB) approach for learning molecular thermodynamics and kinetics. Digit. Discov. 4, 211–221 (2025).

    Article 
    CAS 

    Google Scholar 

  • Strahan, J., Finkel, J., Dinner, A. R. & Weare, J. Predicting rare events using neural networks and short-trajectory data. J. Comput. Phys. 488, 112152 (2023).

    Article 
    MathSciNet 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Kang, P., Trizio, E. & Parrinello, M. Computing the committor with the committor to study the transition state ensemble. Nat. Comput. Sci. 4, 451–460 (2024).

    Article 
    PubMed 

    Google Scholar 

  • Costa, A. d. S., Ponnapati, M., Rubin, D., Smidt, T. & Jacobson, J. Accelerating protein molecular dynamics simulation with DeepJump. Preprint at https://doi.org/10.48550/arXiv.2509.13294 (2025).

  • Song, J., Meng, C. & Ermon, S. Denoising diffusion implicit models. In Proc. International Conference on Learning Representations (ICLR) (eds Oh, A., Murray, N. & Titov, I.) 1–20 (ICLR, 2021).

  • Schlitter, J., Engels, M. & Krüger, P. Targeted molecular dynamics: a new approach for searching pathways of conformational transitions. J. Mol. Graph. 12, 84–89 (1994).

    Article 
    CAS 
    PubMed 

    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).

  • Vaswani, A. et al. Attention is all you need. In Proc. Advances in Neural Information Processing Systems Vol. 30 (eds Guyon, I. et al.) 5998–6008 (Curran Associates, 2017).

  • Post, M. & Hummer, G. AI-guided transition path sampling of lipid flip-flop and membrane nanoporation. Nat. Commun. 17, 224 (2026).

    Article 
    ADS 
    CAS 

    Google Scholar 

  • Breebaart, R. S., Lazzeri, G., Covino, R. & Bolhuis, P. G. Understanding mechanisms of molecular rare events from start to finish. Phys. Rev. Lett. 136, 168001 (2026).

  • Clevert, D.-A., Unterthiner, T. & Hochreiter, S. Fast and accurate deep network learning by exponential linear units (ELUs). In Proc. 4th International Conference on Learning Representations (ICLR) (eds Bengio, Y. & LeCun, Y.) 1–14 (ICLR, 2016).

  • Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. In Proc. 3rd International Conference on Learning Representations (ICLR) (eds Bengio, Y. & LeCun, Y.) 1–15 (ICLR, 2015).

  • Phillips, J. C. et al. Scalable molecular dynamics on CPU and GPU architectures with NAMD. J. Chem. Phys. 153, 044130 (2020).

    Article 
    ADS 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Huang, J. et al. CHARMM36m: an improved force field for folded and intrinsically disordered proteins. Nat. Methods 14, 71–73 (2017).

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Pebay-Peyroula, E. et al. Structure of mitochondrial ADP/ATP carrier in complex with carboxyatractyloside. Nature 426, 39–44 (2003).

    Article 
    ADS 
    CAS 
    PubMed 

    Google Scholar 

  • Webb, B. & Sali, A. Comparative protein structure modeling using MODELLER. Curr. Protoc. Bioinformatics 54, 5–6 (2016).

    Article 

    Google Scholar 

  • Ruprecht, J. J. et al. The molecular mechanism of transport by the mitochondrial ADP/ATP carrier. Cell 176, 435–447 (2019).

    Article 
    CAS 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Smart, O. S., Neduvelil, J. G., Wang, X., Wallace, B. A. & Sansom, M. S. P. HOLE: a program for the analysis of the pore dimensions of ion channel structural models. J. Mol. Graph. 14, 354–360 (1996).

    Article 
    CAS 
    PubMed 

    Google Scholar 



  • Source link