Scalable emulation of protein equilibrium ensembles with generative deep learning

Editor’s summary

Proteins can typically adopt a range of conformations in solution. Molecular dynamics simulations have been used to generate ensembles with realistic probabilities, but the required computational resources are large even for simple problems. Lewis et al. developed a generative deep learning protein dynamics emulator called BioEmu that is trained on extensive molecular dynamics results, protein structures, and experimental data. Using a tiny fraction of the power used in traditional simulations, BioEmu generates accurate conformational ensembles for medium-sized soluble proteins. The ability to quickly, cheaply, and accurate generate such data will enable researchers to generate and test many more hypotheses and shift computational resources to validation and investigation of more difficult problems. —Michael A. Funk

Structured Abstract

INTRODUCTION

Proteins constitute the functional building blocks of life and are central to drug discovery and biotechnology. We now have technologies to determine protein sequence and predict protein structure at the genomic scale, but this is not the case for protein function. Protein function relies on dynamical mechanisms, particularly the transitions between long-lived protein structures (conformational states) and the association with and dissociation from other proteins and ligands (compositional states). The coupling between conformational and compositional state changes, and the probability of these states under a given set of conditions (temperature, solvation, concentration), determine “how proteins work” on a molecular scale. Although biophysical experiments and molecular dynamics (MD) simulations can reveal such structure-dynamics relationships with high accuracy, these methods suffer from low throughput.

RATIONALE

As a step toward solving this throughput challenge, we developed a biomolecular emulator (BioEmu) that samples the approximate equilibrium distribution of structures of single protein chains. BioEmu is a generative deep-learning system that can generate thousands of statistically independent structure samples per hour on a single graphics processing unit (GPU). BioEmu leverages AlphaFold to encode the protein sequence into a rich sequence-structure representation, which inputs into a diffusion model that efficiently samples three-dimensional structures. BioEmu was trained in three stages: It was pretrained on a processed version of the AlphaFold database (AFDB) in such a way as to incentivize the model to associate each protein sequence with a diverse set of structures. Training was continued on a vast dataset of MD simulations of thousands of proteins and more than 200 ms of aggregate simulation time. And finally, BioEmu was fine-tuned on more than 500,000 experimental protein stabilities using a technology developed here, property-prediction fine-tuning (PPFT).

RESULTS

We tested BioEmu on a variety of protein systems that are dissimilar from training proteins and benchmarked its performance on three tasks: (i) Predicting known conformational changes including large domain motions, local unfolding transitions, and the formation of cryptic binding pockets while achieving success rates of sampling the known references of between 55 and 90%. (ii) Emulating equilibrium distributions of both protein folding and native-state conformational transitions that can be generated by high-throughput MD simulation, demonstrating errors in free-energy differences below 1 kcal/mol and speedups of four to five orders of magnitude. (iii) Predicting experimentally measured stabilities of folded states of small proteins by directly generating equilibrium ensembles and explaining structure-stability relationships of mutants, achieving errors below 1 kcal/mol and correlation coefficients greater than 0.6 for both absolute folding free energies and folding free-energy changes of mutants.

CONCLUSION

BioEmu has various practical use cases, including complementing present MD simulation workflows, interpreting protein experiments in terms of structural mechanisms, identifying binding pockets and allosteric mechanisms in drug discovery, and generating ensembles for dynamical protein design. Our demonstration that the large upfront costs of MD simulation and experimental data generation can be amortized and that the prediction error decreases with an increasing amount of diverse training data indicates a path forward for predicting biomolecular function at the genomic scale.

Illustration of the BioEmu model and workflow.
BioEmu generates equilibrium protein structure ensembles by combining AlphaFold’s sequence representation with a diffusion model trained on vast simulation and experimental data. These ensembles enable rapid computation of properties such as protein stability, achieving speeds that are orders of magnitude faster than MD simulation. [Emu illustration by F.N.]

Abstract

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.

Register and access this article for free

As a service to the community, this article is available for free.

Access the full article

View all access options to continue reading this article.

Supplementary Materials

The PDF file includes:

Materials and Methods

Figs. S1 to S12

Tables S1 to S4

Algorithms 1 and 2

References (63–126)

Download
24.34 MB

Other Supplementary Material for this manuscript includes the following:

MDAR Reproducibility Checklist

Download
166.06 KB

References and Notes

J. Jumper, R. Evans, A. Pritzel, T. Green, M. Figurnov, O. Ronneberger, K. Tunyasuvunakool, R. Bates, A. Žídek, A. Potapenko, A. Bridgland, C. Meyer, S. A. A. Kohl, A. J. Ballard, A. Cowie, B. Romera-Paredes, S. Nikolov, R. Jain, J. Adler, T. Back, S. Petersen, D. Reiman, E. Clancy, M. Zielinski, M. Steinegger, M. Pacholska, T. Berghammer, S. Bodenstein, D. Silver, O. Vinyals, A. W. Senior, K. Kavukcuoglu, P. Kohli, D. Hassabis, Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589 (2021).

J. Abramson, J. Adler, J. Dunger, R. Evans, T. Green, A. Pritzel, O. Ronneberger, L. Willmore, A. J. Ballard, J. Bambrick, S. W. Bodenstein, D. A. Evans, C.-C. Hung, M. O’Neill, D. Reiman, K. Tunyasuvunakool, Z. Wu, A. Žemgulytė, E. Arvaniti, C. Beattie, O. Bertolli, A. Bridgland, A. Cherepanov, M. Congreve, A. I. Cowen-Rivers, A. Cowie, M. Figurnov, F. B. Fuchs, H. Gladman, R. Jain, Y. A. Khan, C. M. R. Low, K. Perlin, A. Potapenko, P. Savy, S. Singh, A. Stecula, A. Thillaisundaram, C. Tong, S. Yakneen, E. D. Zhong, M. Zielinski, A. Žídek, V. Bapst, P. Kohli, M. Jaderberg, D. Hassabis, J. M. Jumper, Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature 630, 493–500 (2024).

M. Baek, F. DiMaio, I. Anishchenko, J. Dauparas, S. Ovchinnikov, G. R. Lee, J. Wang, Q. Cong, L. N. Kinch, R. D. Schaeffer, C. Millán, H. Park, C. Adams, C. R. Glassman, A. DeGiovanni, J. H. Pereira, A. V. Rodrigues, A. A. van Dijk, A. C. Ebrecht, D. J. Opperman, T. Sagmeister, C. Buhlheller, T. Pavkov-Keller, M. K. Rathinaswamy, U. Dalwadi, C. K. Yip, J. E. Burke, K. C. Garcia, N. V. Grishin, P. D. Adams, R. J. Read, D. Baker, Accurate prediction of protein structures and interactions using a three-track neural network. Science 373, 871–876 (2021).

R. Krishna, J. Wang, W. Ahern, P. Sturmfels, P. Venkatesh, I. Kalvet, G. R. Lee, F. S. Morey-Burrows, I. Anishchenko, I. R. Humphreys, R. McHugh, D. Vafeados, X. Li, G. A. Sutherland, A. Hitchcock, C. N. Hunter, A. Kang, E. Brackenbrough, A. K. Bera, M. Baek, F. DiMaio, D. Baker, Generalized biomolecular modeling and design with RoseTTAFold All-Atom. Science 384, eadl2528 (2024).

F. Ritort, Single-molecule experiments in biological physics: Methods and applications. J. Phys. Condens. Matter 18, R531–R583 (2006).

X.-C. Bai, G. McMullan, S. H. Scheres, How cryo-EM is revolutionizing structural biology. Trends Biochem. Sci. 40, 49–57 (2015).

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

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

J. Wang, S. Olsson, C. Wehmeyer, A. Pérez, N. E. Charron, G. de Fabritiis, F. Noé, C. Clementi, Machine learning of coarse-grained molecular dynamics force fields. ACS Cent. Sci. 5, 755–767 (2019).

N. E. Charron, K. Bonneau, A. S. Pasos-Trejo, A. Guljas, Y. Chen, F. Musil, J. Venturin, D. Gusew, I. Zaporozhets, A. Krämer, C. Templeton, A. Kelkar, A. E. P. Durumeric, S. Olsson, A. Pérez, M. Majewski, B. E. Husic, A. Patel, G. De Fabritiis, F. Noé, C. Clementi, Navigating protein landscapes with a machine-learned transferable coarse-grained model. Nat. Chem. 17, 1284–1292 (2025).

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

S. Zheng, J. He, C. Liu, Y. Shi, Z. Lu, W. Feng, F. Ju, J. Wang, J. Zhu, Y. Min, H. Zhang, S. Tang, H. Hao, P. Jin, C. Chen, F. Noé, H. Liu, T.-Y. Liu, Predicting equilibrium distributions for molecular systems with deep learning. Nat. Mach. Intell. 6, 558–567 (2024).

J. Jing, B. Berger, T. Jaakkola, “AlphaFold meets flow matching for generating protein ensembles” in Proceedings of the 41st International Conference on Machine Learning (JMLR, 2024), pp. 22277–22303.

Z. Qiao, W. Nie, A. Vahdat, T. F. Miller III, A. Anandkumar, State-specific protein–ligand complex structure prediction with a multiscale deep generative model. Nat. Mach. Intell. 6, 195–208 (2024).

H. K. Wayment-Steele, A. Ojoawo, R. Otten, J. M. Apitz, W. Pitsawong, M. Hömberger, S. Ovchinnikov, L. Colwell, D. Kern, Predicting multiple conformations via sequence clustering and AlphaFold2. Nature 625, 832–839 (2024).

P. Bryant, F. Noé, Structure prediction of alternative protein conformations. Nat. Commun. 15, 7328 (2024).

B. P. Vani, A. Aranganathan, D. Wang, P. Tiwary, AlphaFold2-RAVE: From sequence to Boltzmann ranking. J. Chem. Theory Comput. 19, 4351–4354 (2023).

A. Aranganathan, X. Gu, D. Wang, B. Vani, P. Tiwary, Modeling Boltzmann-eighted structural ensembles of proteins using artificial intelligence–based methods. Curr. Opin. Struct. Biol. 91, 103000 (2025).

R. E. Amaro, J. Åqvist, I. Bahar, F. Battistini, A. Bellaiche, D. Beltran, P. C. Biggin, M. Bonomi, G. R. Bowman, R. A. Bryce, G. Bussi, P. Carloni, D. A. Case, A. Cavalli, C. A. Chang, T. E. Cheatham III, M. S. Cheung, C. Chipot, L. T. Chong, P. Choudhary, G. A. Cisneros, C. Clementi, R. Collepardo-Guevara, P. Coveney, R. Covino, T. D. Crawford, M. Dal Peraro, B. L. de Groot, L. Delemotte, M. De Vivo, J. W. Essex, F. Fraternali, J. Gao, J. L. Gelpí, F. L. Gervasio, F. D. González-Nilo, H. Grubmüller, M. G. Guenza, H. V. Guzman, S. Harris, T. Head-Gordon, R. Hernandez, A. Hospital, N. Huang, X. Huang, G. Hummer, J. Iglesias-Fernández, J. H. Jensen, S. Jha, W. Jiao, W. L. Jorgensen, S. C. L. Kamerlin, S. Khalid, C. Laughton, M. Levitt, V. Limongelli, E. Lindahl, K. Lindorff-Larsen, S. Loverde, M. Lundborg, Y. L. Luo, F. J. Luque, C. I. Lynch, A. D. MacKerell Jr., A. Magistrato, S. J. Marrink, H. Martin, J. A. McCammon, K. Merz, V. Moliner, A. J. Mulholland, S. Murad, A. N. Naganathan, S. Nangia, F. Noe, A. Noy, J. Oláh, M. L. O’Mara, M. J. Ondrechen, J. N. Onuchic, A. Onufriev, S. Osuna, G. Palermo, A. R. Panchenko, S. Pantano, C. Parish, M. Parrinello, A. Perez, T. Perez-Acle, J. R. Perilla, B. M. Pettitt, A. Pietropaolo, J.-P. Piquemal, A. B. Poma, M. Praprotnik, M. J. Ramos, P. Ren, N. Reuter, A. Roitberg, E. Rosta, C. Rovira, B. Roux, U. Rothlisberger, K. Y. Sanbonmatsu, T. Schlick, A. K. Shaytan, C. Simmerling, J. C. Smith, Y. Sugita, K. Świderek, M. Taiji, P. Tao, D. P. Tieleman, I. G. Tikhonova, J. Tirado-Rives, I. Tuñón, M. W. van der Kamp, D. van der Spoel, S. Velankar, G. A. Voth, R. Wade, A. Warshel, V. V. Welborn, S. D. Wetmore, T. J. Wheeler, C. F. Wong, L.-W. Yang, M. Zacharias, M. Orozco, The need to implement FAIR principles in biomolecular simulations. Nat. Methods 22, 641–645 (2025).

J.-H. Prinz, H. Wu, M. Sarich, B. Keller, M. Senne, M. Held, J. D. Chodera, C. Schütte, F. Noé, Markov models of molecular kinetics: Generation and validation. J. Chem. Phys. 134, 174105 (2011).

K. Tsuboyama, J. Dauparas, J. Chen, E. Laine, Y. Mohseni Behbahani, J. J. Weinstein, N. M. Mangan, S. Ovchinnikov, G. J. Rocklin, Mega-scale experimental analysis of protein folding stability in biology and design. Nature 620, 434–444 (2023).

D. del Alamo, D. Sala, H. S. Mchaourab, J. Meiler, Sampling alternative conformational states of transporters and receptors with AlphaFold2. eLife 11, e75751 (2022).

H. Y. Aviram, M. Pirchi, H. Mazal, Y. Barak, I. Riven, G. Haran, Direct observation of ultrafast large-scale dynamics of an enzyme under turnover conditions. Proc. Natl. Acad. Sci. U.S.A. 115, 3243–3248 (2018).

F. B. Fromowitz, M. V. Viola, S. Chao, S. Oravez, Y. Mishriki, G. Finkel, R. Grimson, J. Lundy, ras p21 expression in the progression of breast cancer. Hum. Pathol. 18, 1268–1275 (1987).

J. B. Greisman, L. Willmore, C. Y. Yeh, F. Giordanetto, S. Shahamadtar, H. Nisonoff, P. Maragakis, D. E. Shaw, Discovery and validation of the binding poses of allosteric fragment hits to protein tyrosine phosphatase 1b: From molecular dynamics simulations to x-ray crystallography. J. Chem. Inf. Model. 63, 2644–2650 (2023).

M. I. Zimmerman, J. R. Porter, M. D. Ward, S. Singh, N. Vithani, A. Meller, U. L. Mallimadugula, C. E. Kuhn, J. H. Borowsky, R. P. Wiewiora, M. F. D. Hurley, A. M. Harbison, C. A. Fogarty, J. E. Coffland, E. Fadda, V. A. Voelz, J. D. Chodera, G. R. Bowman, SARS-CoV-2 simulations go exascale to predict dramatic spike opening and cryptic pockets across the proteome. Nat. Chem. 13, 651–659 (2021).

T. J. Lane, D. Shukla, K. A. Beauchamp, V. S. Pande, To milliseconds and beyond: Challenges in the simulation of protein folding. Curr. Opin. Struct. Biol. 23, 58–65 (2013).

D. E. Shaw, P. Maragakis, K. Lindorff-Larsen, S. Piana, R. O. Dror, M. P. Eastwood, J. A. Bank, J. M. Jumper, J. K. Salmon, Y. Shan, W. Wriggers, Atomic-level characterization of the structural dynamics of proteins. Science 330, 341–346 (2010).

J. D. Chodera, F. Noé, Markov state models of biomolecular conformational dynamics. Curr. Opin. Struct. Biol. 25, 135–144 (2014).

R. B. Best, J. Mittal, Free-energy landscape of the GB1 hairpin in all-atom explicit solvent simulations with different force fields: Similarities and differences. Proteins 79, 1318–1328 (2011).

D. F. Hahn, V. Gapsys, B. L. de Groot, D. L. Mobley, G. Tresadern, Current state of open source force fields in protein-ligand binding affinity predictions. J. Chem. Inf. Model. 64, 5063–5076 (2024).

A. Laio, M. Parrinello, Escaping free-energy minima. Proc. Natl. Acad. Sci. U.S.A. 99, 12562–12566 (2002).

P. Robustelli, S. Piana, D. E. Shaw, Developing a molecular dynamics force field for both folded and disordered protein states. Proc. Natl. Acad. Sci. U.S.A. 115, E4758–E4766 (2018).

I. Sillitoe, N. Bordin, N. Dawson, V. P. Waman, P. Ashford, H. M. Scholes, C. S. M. Pang, L. Woodridge, C. Rauer, N. Sen, M. Abbasian, S. Le Cornu, S. D. Lam, K. Berka, I. H. Varekova, R. Svobodova, J. Lees, C. A. Orengo, CATH: Increased structural coverage of functional space. Nucleic Acids Res. 49, D266–D273 (2021).

J. Malsam, S. Bärfuss, T. Trimbuch, F. Zarebidaki, A. F.-P. Sonnen, K. Wild, A. Scheutzow, L. Rohland, M. P. Mayer, I. Sinning, J. A. G. Briggs, C. Rosenmund, T. H. Söllner, Complexin suppresses spontaneous exocytosis by capturing the membrane-proximal regions of VAMP2 and SNAP25. Cell Rep. 32, 107926 (2020).

Q. Zhou, P. Zhou, A. L. Wang, D. Wu, M. Zhao, T. C. Südhof, A. T. Brunger, The primed SNARE-complexin-synaptotagmin complex for neuronal exocytosis. Nature 548, 420–425 (2017).

R. Umeda, Y. Satouh, M. Takemoto, Y. Nakada-Nakura, K. Liu, T. Yokoyama, M. Shirouzu, S. Iwata, N. Nomura, K. Sato, M. Ikawa, T. Nishizawa, O. Nureki, Structural insights into tetraspanin CD9 function. Nat. Commun. 11, 1606 (2020).

R. Nikam, A. Kulandaisamy, K. Harini, D. Sharma, M. M. Gromiha, ProThermDB: Thermodynamic database for proteins and mutants revisited after 15 years. Nucleic Acids Res. 49, D420–D424 (2021).

G. Tesei, A. I. Trolle, N. Jonsson, J. Betz, F. E. Knudsen, F. Pesce, K. E. Johansson, K. Lindorff-Larsen, Conformational ensembles of the human intrinsically disordered proteome. Nature 626, 897–904 (2024).

G. Tesei, K. Lindorff-Larsen, Improved predictions of phase behaviour of intrinsically disordered proteins by tuning the interaction range. Open Res. Eur. 2, 94 (2023).

J. Zhu, Z. Li, B. Zhang, Z. Zheng, B. Zhong, J. Bai, T. Wang, T. Wei, J. Yang, H.-F. Chen, Precise generation of conformational ensembles for intrinsically disordered proteins via fine-tuned diffusion models. bioRxiv 2024.05.05.592611 [Preprint] (2024); https://doi.org/10.1101/2024.05.05.592611.

J. Ouyang-Zhang, D. Diaz, A. Klivans, P. Krähenbühl, Predicting a protein’s stability under a million mutations. Adv. Neural Inf. Process. Syst. 36, 76229–76247 (2023).

M. Cagiada, S. Ovchinnikov, K. Lindorff-Larsen, Predicting absolute protein folding stability using generative models. Protein Sci. 34, e5233 (2025).

P. Notin, A. W. Kollasch, D. Ritter, L. van Niekerk, S. Paul, H. Spinner, N. Rollins, A. Shaw, R. Weitzman, J. Frazer, M. Dias, D. Franceschi, R. Orenbuch, Y. Gal, D. S. Marks, ProteinGym: Large-scale benchmarks for protein fitness prediction and design. Adv. Neural Inf. Process. Syst. 36, 64331–64379 (2023).

T. Widatalla, R. Rafailov, B. Hie, Aligning protein generative models with experimental fitness via Direct Preference Optimization. bioRxiv 2024.05.20.595026 [Preprint] (2024); https://doi.org/10.1101/2024.05.20.595026.

Y. Lipman, R. T. Q. Chen, H. Ben-Hamu, M. Nickel, M. Le, Flow matching for generative modeling. arXiv:2210.02747 [cs.LG] (2022).

J. Yim, A. Campbell, A. Y. K. Foong, M. Gastegger, J. Jiménez-Luna, S. Lewis, V. Garcia Satorras, B. S. Veeling, R. Barzilay, T. Jaakkola, F. Noé, Fast protein backbone generation with SE(3) flow matching. arXiv:2310.05297 [q-bio.QM] (2023).

W. G. Noid, J.-W. Chu, G. S. Ayton, V. Krishna, S. Izvekov, G. A. Voth, A. Das, H. C. Andersen, The multiscale coarse-graining method. I. A rigorous bridge between atomistic and coarse-grained models. J. Chem. Phys. 128, 244114 (2008).

L. Klein, A. Y. K. Foong, T. E. Fjelde, B. Mlodozeniec, M. Brockschmidt, S. Nowozin, F. Noé, R. Tomioka, Timewarp: Transferable acceleration of molecular dynamics by learning time-coarsened dynamics. Adv. Neural Inf. Process. Syst. 36, 52863–52883 (2023).

M. Schreiner, O. Winther, S. Olsson, Implicit transfer operator learning: Multiple time-resolution models for molecular dynamics. Adv. Neural Inf. Process. Syst. 36, 36449–36462 (2023).

T. Fröhlking, M. Bernetti, N. Calonaci, G. Bussi, Toward empirical force fields that match experimental observables. J. Chem. Phys. 152, 230902 (2020).

J. Gawlikowski, C. R. N. Tassi, M. Ali, J. Lee, M. Humt, J. Feng, A. Kruspe, R. Triebel, P. Jung, R. Roscher, M. Shahzad, W. Yang, R. Bamler, X. X. Zhu, A survey of uncertainty in deep neural networks. Artif. Intell. Rev. 56, 1513–1589 (2023).

H. Sidky, W. Chen, A. L. Ferguson, Machine learning for collective variable discovery and enhanced sampling in biomolecular simulation. Mol. Phys. 118, e1737742 (2020).

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

H. Hofmann, A. Soranno, A. Borgia, K. Gast, D. Nettels, B. Schuler, Polymer scaling laws of unfolded and intrinsically disordered proteins quantified with single-molecule spectroscopy. Proc. Natl. Acad. Sci. U.S.A. 109, 16155–16160 (2012).

S. Lewis, T. Hempel, J. Jiménez-Luna, M. Gastegger, Y. Xie, A. Y. K. Foong, V. G. Satorras, O. Abdin, B. S. Veeling, I. Zaporozhets, Y. Chen, S. Yang, A. E. Foster, A. Schneuing, J. Nigam, F. Barbero, V. Stimper, A. Campbell, J. Yim, M. Lienen, Y. Shi, S. Zheng, H. Schulz, U. Munir, R. Sordillo, R. Tomioka, C. Clementi, F. Noé, Molecular dynamics dataset for “scalable emulation of protein equilibrium ensembles with generative deep learning”: Octapeptides. Zenodo (2025); https://doi.org/10.5281/zenodo.15641199.

S. Lewis, T. Hempel, J. Jiménez-Luna, M. Gastegger, Y. Xie, A. Y. K. Foong, V. G. Satorras, O. Abdin, B. S. Veeling, I. Zaporozhets, Y. Chen, S. Yang, A. E. Foster, A. Schneuing, J. Nigam, F. Barbero, V. Stimper, A. Campbell, J. Yim, M. Lienen, Y. Shi, S. Zheng, H. Schulz, U. Munir, R. Sordillo, R. Tomioka, C. Clementi, F. Noé, Molecular dynamics dataset for “scalable emulation of protein equilibrium ensembles with generative deep learning”: CATH domains. Zenodo (2025); https://doi.org/10.5281/zenodo.15629740.

S. Lewis, T. Hempel, J. Jiménez-Luna, M. Gastegger, Y. Xie, A. Y. K. Foong, V. G. Satorras, O. Abdin, B. S. Veeling, I. Zaporozhets, Y. Chen, S. Yang, A. E. Foster, A. Schneuing, J. Nigam, F. Barbero, V. Stimper, A. Campbell, J. Yim, M. Lienen, Y. Shi, S. Zheng, H. Schulz, U. Munir, R. Sordillo, R. Tomioka, C. Clementi, F. Noé, Molecular dynamics dataset for “scalable emulation of protein equilibrium ensembles with generative deep learning”: MegaSim. Zenodo (2025); https://doi.org/10.5281/zenodo.15641184.

G. M. Visani, W. Galvin, M. Pun, A. Nourmohammad, “H-Packer: Holographic rotationally equivariant convolutional neural network for protein side-chain packing” in Proceedings of the 18th Machine Learning in Computational Biology Meeting, vol. 240 of Proc. Mach. Learn. Res., D. A. Knowles, S. Mostafavi, Eds. (PMLR, 2024), pp. 230–249.

P. Eastman, J. Swails, J. D. Chodera, R. T. McGibbon, Y. Zhao, K. A. Beauchamp, L.-P. Wang, A. C. Simmonett, M. P. Harrigan, C. D. Stern, R. P. Wiewiora, B. R. Brooks, V. S. Pande, OpenMM 7: Rapid development of high performance algorithms for molecular dynamics. PLOS Comput. Biol. 13, e1005659 (2017).

S. Lewis, T. Hempel, J. Jiménez-Luna, M. Gastegger, Y. Xie, A. Y. K. Foong, V. G. Satorras, O. Abdin, B. S. Veeling, I. Zaporozhets, Y. Chen, S. Yang, A. E. Foster, A. Schneuing, J. Nigam, F. Barbero, V. Stimper, A. Campbell, J. Yim, M. Lienen, Y. Shi, S. Zheng, H. Schulz, U. Munir, R. Sordillo, R. Tomioka, C. Clementi, F. Noé, Supplementary data for “scalable emulation of protein equilibrium ensembles with generative deep learning”. Zenodo (2025); https://doi.org/10.5281/zenodo.15672282.

M. Steinegger, J. Söding, MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nat. Biotechnol. 35, 1026–1028 (2017).

M. van Kempen, S. S. Kim, C. Tumescheit, M. Mirdita, J. Lee, C. L. M. Gilchrist, J. Söding, M. Steinegger, Fast and accurate protein structure search with Foldseek. Nat. Biotechnol. 42, 243–246 (2024).

G. Huguet, J. Vuckovic, K. Fatras, E. Thibodeau-Laufer, P. Lemos, R. Islam, C.-H. Liu, J. Rector-Brooks, T. Akhound-Sadegh, M. Bronstein, A. Tong, A. J. Bose, Sequence-augmented SE(3)-flow matching for conditional protein backbone generation. arXiv:2405.20313 [cs.LG] (2024).

M. J. Abraham, T. Murtola, R. Schulz, S. Páll, J. C. Smith, B. Hess, E. Lindahl, GROMACS: High performance molecular simulations through multi-level parallelism from laptops to supercomputers. SoftwareX 1–2, 19–25 (2015).

W. L. Jorgensen, J. Chandrasekhar, J. D. Madura, R. W. Impey, M. L. Klein, Comparison of simple potential functions for simulating liquid water. J. Chem. Phys. 79, 926–935 (1983).

C. W. Hopkins, S. Le Grand, R. C. Walker, A. E. Roitberg, Long-time-step molecular dynamics through hydrogen mass repartitioning. J. Chem. Theory Comput. 11, 1864–1874 (2015).

K. Lindorff-Larsen, S. Piana, K. Palmo, P. Maragakis, J. L. Klepeis, R. O. Dror, D. E. Shaw, Improved side-chain torsion potentials for the Amber ff99SB protein force field. Proteins 78, 1950–1958 (2010).

E. Hruska, J. R. Abella, F. Nüske, L. E. Kavraki, C. Clementi, Quantitative comparison of adaptive sampling methods for protein dynamics. J. Chem. Phys. 149, 244119 (2018).

M. K. Scherer, B. Trendelkamp-Schroer, F. Paul, G. Pérez-Hernández, M. Hoffmann, N. Plattner, C. Wehmeyer, J.-H. Prinz, F. Noé, PyEMMA 2: A software package for estimation, validation, and analysis of Markov models. J. Chem. Theory Comput. 11, 5525–5542 (2015).

J. A. Maier, C. Martinez, K. Kasavajhala, L. Wickstrom, K. E. Hauser, C. Simmerling, ff14SB: Improving the accuracy of protein side chain and backbone parameters from ff99SB. J. Chem. Theory Comput. 11, 3696–3713 (2015).

S. Piana, K. Lindorff-Larsen, D. E. Shaw, How robust are protein folding simulations with respect to force field parameterization? Biophys. J. 100, L47–L49 (2011).

S. M. Hanson, G. Georghiou, M. K. Thakur, W. T. Miller, J. S. Rest, J. D. Chodera, M. A. Seeliger, What makes a kinase promiscuous for inhibitors? Cell Chem. Biol. 26, 390–399.e5 (2019).

S. Chen, R. P. Wiewiora, F. Meng, N. Babault, A. Ma, W. Yu, K. Qian, H. Hu, H. Zou, J. Wang, S. Fan, G. Blum, F. Pittella-Silva, K. A. Beauchamp, W. Tempel, H. Jiang, K. Chen, R. J. Skene, Y. G. Zheng, P. J. Brown, J. Jin, C. Luo, J. D. Chodera, M. Luo, The dynamic conformational landscape of the protein methyltransferase SETD8. eLife 8, e45403 (2019).

Y. Duan, C. Wu, S. Chowdhury, M. C. Lee, G. Xiong, W. Zhang, R. Yang, P. Cieplak, R. Luo, T. Lee, J. Caldwell, J. Wang, P. Kollman, A point-charge force field for molecular mechanics simulations of proteins based on condensed-phase quantum mechanical calculations. J. Comput. Chem. 24, 1999–2012 (2003).

E. C. Thomson, L. E. Rosen, J. G. Shepherd, R. Spreafico, A. da Silva Filipe, J. A. Wojcechowskyj, C. Davis, L. Piccoli, D. J. Pascall, J. Dillen, S. Lytras, N. Czudnochowski, R. Shah, M. Meury, N. Jesudason, A. De Marco, K. Li, J. Bassi, A. O’Toole, D. Pinto, R. M. Colquhoun, K. Culap, B. Jackson, F. Zatta, A. Rambaut, S. Jaconi, V. B. Sreenu, J. Nix, I. Zhang, R. F. Jarrett, W. G. Glass, M. Beltramello, K. Nomikou, M. Pizzuto, L. Tong, E. Cameroni, T. I. Croll, N. Johnson, J. Di Iulio, A. Wickenhagen, A. Ceschi, A. M. Harbison, D. Mair, P. Ferrari, K. Smollett, F. Sallusto, S. Carmichael, C. Garzoni, J. Nichols, M. Galli, J. Hughes, A. Riva, A. Ho, M. Schiuma, M. G. Semple, P. J. M. Openshaw, E. Fadda, J. K. Baillie, J. D. Chodera, S. J. Rihn, S. J. Lycett, H. W. Virgin, A. Telenti, D. Corti, D. L. Robertson, G. Snell; ISARIC4C Investigators; COVID-19 Genomics UK (COG-UK) Consortium, Circulating SARS-CoV-2 spike N439K variants maintain fitness while evading antibody-mediated immunity. Cell 184, 1171–1187.e20 (2021).

E. T. Abualrous, S. Stolzenberg, J. Sticht, M. Wieczorek, Y. Roske, M. Günther, S. Dähn, B. B. Boesen, M. M. Calvo, C. Biese, F. Kuppler, Á. Medina-García, M. Álvaro-Benito, T. Höfer, F. Noé, C. Freund, MHC-II dynamics are maintained in HLA-DR allotypes to ensure catalyzed peptide exchange. Nat. Chem. Biol. 19, 1196–1204 (2023).

V. Hornak, R. Abel, A. Okur, B. Strockbine, A. Roitberg, C. Simmerling, Comparison of multiple Amber force fields and development of improved protein backbone parameters. Proteins 65, 712–725 (2006).

M. Mirdita, K. Schütze, Y. Moriwaki, L. Heo, S. Ovchinnikov, M. Steinegger, ColabFold: Making protein folding accessible to all. Nat. Methods 19, 679–682 (2022).

J. Yim, B. L. Trippe, V. De Bortoli, E. Mathieu, A. Doucet, R. Barzilay, T. Jaakkola, SE(3) diffusion model with application to protein backbone generation. arXiv:2302.02277 [cs.LG] (2023).

G. Ahdritz, N. Bouatta, C. Floristean, S. Kadyan, Q. Xia, W. Gerecke, T. J. O’Donnell, D. Berenberg, I. Fisk, N. Zanichelli, B. Zhang, A. Nowaczynski, B. Wang, M. M. Stepniewska-Dziubinska, S. Zhang, A. Ojewole, M. E. Guney, S. Biderman, A. M. Watkins, S. Ra, P. R. Lorenzo, L. Nivon, B. Weitzner, Y. A. Ban, S. Chen, M. Zhang, C. Li, S. L. Song, Y. He, P. K. Sorger, E. Mostaque, Z. Zhang, R. Bonneau, M. AlQuraishi, OpenFold: Retraining AlphaFold2 yields new insights into its learning mechanisms and capacity for generalization. Nat. Methods 21, 1514–1524 (2024).

A. Nichol, P. Dhariwal, Improved denoising diffusion probabilistic models. arXiv:2102.09672 [cs.LG] (2021).

V. D. Bortoli, E. Mathieu, M. Hutchinson, J. Thornton, Y. W. Teh, A. Doucet, Riemannian score-based generative modelling. arXiv:2202.02763 [cs.LG] (2022).

Y. Song, J. Sohl-Dickstein, D. P. Kingma, A. Kumar, S. Ermon, B. Poole, Score-based generative modeling through stochastic differential equations. arXiv:2011.13456 [cs.LG] (2020).

T. Karras, M. Aittala, T. Aila, S. Laine, Elucidating the design space of diffusion-based generative models. Adv. Neural Inf. Process. Syst. 35, 26565–26577 (2022).

C. Lu, Y. Zhou, F. Bao, J. Chen, C. Li, J. Zhu, DPM-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps. Adv. Neural Inf. Process. Syst. 35, 5775–5787 (2022).

I. Barrio-Hernandez, J. Yeo, J. Jänes, M. Mirdita, C. L. M. Gilchrist, T. Wein, M. Varadi, S. Velankar, P. Beltrao, M. Steinegger, Clustering predicted structures at the scale of the known protein universe. Nature 622, 637–645 (2023).

C. Wehmeyer, M. K. Scherer, T. Hempel, B. E. Husic, S. Olsson, F. Noé, Introduction to Markov State Modeling with the PyEMMA Software. Living J. Comput. Mol. Sci. 1, 5965 (2018).

M. Hoffmann, M. Scherer, T. Hempel, A. Mardt, B. de Silva, B. E. Husic, S. Klus, H. Wu, N. Kutz, S. L. Brunton, F. Noé, Deeptime: A Python library for machine learning dynamical models from time series data. Mach. Learn. Sci. Technol. 3, 015009 (2022).

R. B. Best, G. Hummer, W. A. Eaton, Native contacts determine protein folding mechanisms in atomistic simulations. Proc. Natl. Acad. Sci. U.S.A. 110, 17874–17879 (2013).

C. Luo, Understanding diffusion models: A unified perspective. arXiv:2208.11970 [cg.LS] (2022).

C. Domingo-Enrich, M. Drozdzal, B. Karrer, R. T. Chen, Adjoint matching: Fine-tuning flow and diffusion generative models with memoryless stochastic optimal control. arXiv:2409.08861 [cs.LG] (2024).

J. Xu, X. Liu, Y. Wu, Y. Tong, Q. Li, M. Ding, J. Tang, Y. Dong, Imagereward: Learning and evaluating human preferences for text-to-image generation. Adv. Neural Inf. Process. Syst. 37, 15903–15935 (2023).

K. Clark, P. Vicol, K. Swersky, D. J. Fleet, Directly fine-tuning diffusion models on differentiable rewards. arXiv:2309.17400 [cs.CV] (2023).

P. Cimermancic, P. Weinkam, T. J. Rettenmaier, L. Bichmann, D. A. Keedy, R. A. Woldeyes, D. Schneidman-Duhovny, O. N. Demerdash, J. C. Mitchell, J. A. Wells, J. S. Fraser, A. Sali, CryptoSite: Expanding the druggable proteome by characterization and prediction of cryptic binding sites. J. Mol. Biol. 428, 709–719 (2016).

A. Meller, S. Bhakat, S. Solieva, G. R. Bowman, Accelerating cryptic pocket discovery using AlphaFold. J. Chem. Theory Comput. 19, 4355–4363 (2023).

D. Chakravarty, L. L. Porter, AlphaFold2 fails to predict protein fold switching. Protein Sci. 31, e4353 (2022).

J. M. Dana, A. Gutmanas, N. Tyagi, G. Qi, C. O’Donovan, M. Martin, S. Velankar, SIFTS: Updated Structure Integration with Function, Taxonomy and Sequences resource allows 40-fold increase in coverage of structure-based annotations for proteins. Nucleic Acids Res. 47, D482–D489 (2019).

100

C. W. Müller, G. E. Schulz, Structure of the complex between adenylate kinase from Escherichia coli and the inhibitor Ap₅A refined at 1.9 Å resolution. A model for a catalytic transition state. J. Mol. Biol. 224, 159–177 (1992).

101

C. H. Chan, C. C. Wilbanks, G. I. Makhatadze, K. B. Wong, Electrostatic contribution of surface charge residues to the stability of a thermophilic protein: Benchmarking experimental and predicted pKa values. PLOS ONE 7, e30296 (2012).

102

C. W. Müller, G. J. Schlauderer, J. Reinstein, G. E. Schulz, Adenylate kinase motions during catalysis: An energetic counterweight balancing substrate binding. Structure 4, 147–156 (1996).

103

S. Ahmad, M. Z. Kamal, R. Sankaranarayanan, N. M. Rao, Thermostable Bacillus subtilis lipases: In vitro evolution and structural insight. J. Mol. Biol. 381, 324–340 (2008).

104

R. Vergara, S. Romero-Romero, I. Velázquez-López, G. Espinoza-Pérez, A. Rodríguez-Hernández, N. O. Pulido, A. Sosa-Peinado, A. Rodríguez-Romero, D. A. Fernández-Velasco, The interplay of protein-ligand and water-mediated interactions shape affinity and selectivity in the LAO binding protein. FEBS J. 287, 763–782 (2020).

105

L. H. Weaver, B. W. Matthews, Structure of bacteriophage T4 lysozyme refined at 1.7 Å resolution. J. Mol. Biol. 193, 189–199 (1987).

106

A. Corazza, C. Rosano, K. Pagano, V. Alverdi, G. Esposito, C. Capanni, F. Bemporad, G. Plakoutsi, M. Stefani, F. Chiti, S. Zuccotti, M. Bolognesi, P. Viglino, Structure, conformational stability, and enzymatic properties of acylphosphatase from the hyperthermophile Sulfolobus solfataricus. Proteins 62, 64–79 (2006).

107

G. Kitts, K. M. Giglio, D. Zamorano-Sánchez, J. H. Park, L. Townsley, R. B. Cooley, B. R. Wucher, K. E. Klose, C. D. Nadell, F. H. Yildiz, H. Sondermann, A conserved regulatory circuit controls large adhesins in Vibrio cholerae. mBio 10, e02822-19 (2019).

108

K. Ishikawa, M. Okumura, K. Katayanagi, S. Kimura, S. Kanaya, H. Nakamura, K. Morikawa, Crystal structure of ribonuclease H from Thermus thermophilus HB8 refined at 2.8 Å resolution. J. Mol. Biol. 230, 529–542 (1993).

109

J. C. Sacchettini, J. I. Gordon, L. J. Banaszak, Refined apoprotein structure of rat intestinal fatty acid binding protein produced in Escherichia coli. Proc. Natl. Acad. Sci. U.S.A. 86, 7736–7740 (1989).

110

L. A. Tong, A. M. de Vos, M. V. Milburn, S. H. Kim, Crystal structures at 2.2 Å resolution of the catalytic domains of normal ras protein and an oncogenic mutant complexed with GDP. J. Mol. Biol. 217, 503–516 (1991).

111

Y.W. Chen, M. Bycroft, K. B. Wong, Crystal structure of ribosomal protein L30E from the extreme thermophile Thermocccus celer: Thermal stability and RNA binding. Biochem 42, 2857–2865 (2003).

112

E. F. Pai, U. Krengel, G. A. Petsko, R. S. Goody, W. Kabsch, A. Wittinghofer, Refined crystal structure of the triphosphate conformation of H-ras p21 at 1.35 Å resolution: Implications for the mechanism of GTP hydrolysis. EMBO J. 9, 2351–2359 (1990).

113

S. Dhe-Paganon, R. Shigeta, Y. I. Chi, M. Ristow, S. E. Shoelson, Crystal structure of human frataxin. J. Biol. Chem. 275, 30753–30756 (2000).

114

C. Lazareno-Saez, E. Arutyunova, N. Coquelle, M. J. Lemieux, Domain swapping in the cytoplasmic domain of the Escherichia coli rhomboid protease. J. Mol. Biol. 425, 1127–1142 (2013).

115

H. J. Schirra, C. Renner, M. Czisch, M. Huber-Wunderlich, T. A. Holak, R. Glockshuber, Structure of reduced DsbA from Escherichia coli in solution. Biochemistry 37, 6263–6276 (1998).

116

A. R. Sherratt, D. R. Blais, H. Ghasriani, J. P. Pezacki, N. K. Goto, Activity-based protein profiling of the Escherichia coli GlpG rhomboid protein delineates the catalytic core. Biochemistry 51, 7794–7803 (2012).

117

Y. He, Y. Chen, P. Alexander, P. N. Bryan, J. Orban, NMR structures of two designed proteins with high sequence identity but different fold and function. Proc. Natl. Acad. Sci. U.S.A. 105, 14412–14417 (2008).

118

P. Rellos, A. C. W. Pike, F. H. Niesen, E. Salah, W. H. Lee, F. von Delft, S. Knapp, Structure of the CaMKIIdelta/calmodulin complex reveals the molecular mechanism of CaMKII kinase activation. PLOS Biol. 8, e1000426 (2010).

119

V. Neviani, “Unravelling the molecular mechanisms of tetraspanin CD9,” thesis, Utrecht University (2019).

120

A. Müller, E. Severi, C. Mulligan, A. G. Watts, D. J. Kelly, K. S. Wilson, A. J. Wilkinson, G. H. Thomas, Conservation of structure and mechanism in primary and secondary transporters exemplified by SiaP, a sialic acid binding virulence factor from Haemophilus influenzae. J. Biol. Chem. 281, 22212–22222 (2006).

121

W. Oosterheert, K. T. Xenaki, V. Neviani, W. Pos, S. Doulkeridou, J. Manshande, N. M. Pearce, L. M. J. Kroon-Batenburg, M. Lutz, P. M. P. van Bergen En Henegouwen, P. Gros, Implications for tetraspanin-enriched microdomain assembly based on structures of CD9 with EWI-F. Life Sci. Alliance 3, e202000883 (2020).

122

J. F. Darby, A. P. Hopkins, S. Shimizu, S. M. Roberts, J. A. Brannigan, J. P. Turkenburg, G. H. Thomas, R. E. Hubbard, M. Fischer, Water networks can determine the affinity of ligand binding to proteins. J. Am. Chem. Soc. 141, 15818–15826 (2019).

123

S. Jansen, A. Collins, C. Yang, G. Rebowski, T. Svitkina, R. Dominguez, Mechanism of actin filament bundling by fascin. J. Biol. Chem. 286, 30087–30096 (2011).

124

S. Francis, D. Croft, A. W. Schüttelkopf, C. Parry, A. Pugliese, K. Cameron, S. Claydon, M. Drysdale, C. Gardner, A. Gohlke, G. Goodwin, C. H. Gray, J. Konczal, L. McDonald, M. Mezna, A. Pannifer, N. R. Paul, L. Machesky, H. McKinnon, J. Bower, Structure-based design, synthesis and biological evaluation of a novel series of isoquinolone and pyrazolo[4,3-c]pyridine inhibitors of fascin 1 as potential anti-metastatic agents. Bioorg. Med. Chem. Lett. 29, 1023–1029 (2019).

125

C. R. Muchmore, J. M. Krahn, J. H. Kim, H. Zalkin, J. L. Smith, Crystal structure of glutamine phosphoribosylpyrophosphate amidotransferase from Escherichia coli. Protein Sci. 7, 39–51 (1998).

126

J. M. Krahn, J. H. Kim, M. R. Burns, R. J. Parry, H. Zalkin, J. L. Smith, Coupled formation of an amidotransferase interdomain ammonia channel and a phosphoribosyltransferase active site. Biochemistry 36, 11061–11068 (1997).