OpenMM 8: Molecular Dynamics Simulation with Machine Learning Potentials

Eastman, Peter; Galvelis, Raimondas; Peláez, Raúl P.; Abreu, Charlles R. A.; Farr, Stephen E.; Gallicchio, Emilio; Gorenko, Anton; Henry, Michael M.; Hu, Frank; Huang, Jing; Krämer, Andreas; Michel, Julien; Mitchell, Joshua A.; Pande, Vijay S.; Rodrigues, João PGLM; Rodriguez-Guerra, Jaime; Simmonett, Andrew C.; Singh, Sukrit; Swails, Jason; Turner, Philip; Wang, Yuanqing; Zhang, Ivy; Chodera, John D.; De Fabritiis, Gianni; Markland, Thomas E.

doi:10.1021/acs.jpcb.3c06662

Cited by 41 publications

(13 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To generate the input data, the SMILES and the coordinates of interest were used to build a molecule object using openff-toolkit, and the atomic numbers were used as embeddings. Using the more accurate TensorNet 2L model, a 200 ns trajectory, i.e., 2 × 10 8 steps, with a time step of 1 fs was generated for each molecule using OpenMM’s at 298.5 K and a friction coefficient of 1 ps –1 . We also used for one of the molecules a TensorNet 0L model with the same simulation settings to test its stability.…”

Section: Resultsmentioning

confidence: 99%

“…TorchMD-Net emphasizes compatibility with leading molecular dynamics (MD) packages, especially with OpenMM . OpenMM, widely recognized in the computational chemistry field, can now interface directly with TorchMD-Net through the OpenMM-Torch plugin.…”

Section: Introductionmentioning

confidence: 99%

“…It is possible to run TorchMD-Net NNPs as force fields in OpenMM to run MD. The OpenMM-Torch package is leveraged for this.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

TorchMD-Net 2.0: Fast Neural Network Potentials for Molecular Simulations

Pelaez,

Simeon,

Galvelis

et al. 2024

J. Chem. Theory Comput.

Self Cite

View full text Add to dashboard Cite

Achieving a balance between computational speed, prediction accuracy, and universal applicability in molecular simulations has been a persistent challenge. This paper presents substantial advancements in TorchMD-Net software, a pivotal step forward in the shift from conventional force fields to neural network-based potentials. The evolution of TorchMD-Net into a more comprehensive and versatile framework is highlighted, incorporating cutting-edge architectures such as TensorNet. This transformation is achieved through a modular design approach, encouraging customized applications within the scientific community. The most notable enhancement is a significant improvement in computational efficiency, achieving a very remarkable acceleration in the computation of energy and forces for TensorNet models, with performance gains ranging from 2× to 10× over previous, nonoptimized, iterations. Other enhancements include highly optimized neighbor search algorithms that support periodic boundary conditions and smooth integration with existing molecular dynamics frameworks. Additionally, the updated version introduces the capability to integrate physical priors, further enriching its application spectrum and utility in research. The software is available at .

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

TorchMD-Net 2.0: Fast Neural Network Potentials for Molecular Simulations

Pelaez,

Simeon,

Galvelis

et al. 2024

J. Chem. Theory Comput.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Motivated by decades of research into biophysics, molecular dynamics, and protein simulation [10, 23, 24, 27, 35], we present METL, which leverages synthetic data from molecular simulations to pretrain biophysics-aware PLMs. These biophysical pretraining signals are in contrast to existing PLMs or multiple sequence alignment-based methods that train on natural sequences and capture signals related to evolutionary selective pressures [2, 7, 8, 14, 36, 37].…”

Section: Discussionmentioning

confidence: 99%

Biophysics-based protein language models for protein engineering

Gelman,

Johnson,

Freschlin

et al. 2024

Preprint

View full text Add to dashboard Cite

Protein language models trained on evolutionary data have emerged as powerful tools for predictive problems involving protein sequence, structure, and function. However, these models overlook decades of research into biophysical factors governing protein function. We propose Mutational Effect Transfer Learning (METL), a protein language model framework that unites advanced machine learning and biophysical modeling. Using the METL framework, we pretrain transformer-based neural networks on biophysical simulation data to capture fundamental relationships between protein sequence, structure, and energetics. We finetune METL on experimental sequence-function data to harness these biophysical signals and apply them when predicting protein properties like thermostability, catalytic activity, and fluorescence. METL excels in challenging protein engineering tasks like generalizing from small training sets and position extrapolation, although existing methods that train on evolutionary signals remain powerful for many types of experimental assays. We demonstrate METL's ability to design functional green fluorescent protein variants when trained on only 64 examples, showcasing the potential of biophysics-based protein language models for protein engineering.

show abstract

“…In this study, we used the high-performance potential implementation NNPOps (, release 0.2). The interpolation between the potential energy functions was performed using the package (), and all simulations were carried out with 8.0 …”

Section: Detailed Methodsmentioning

confidence: 99%

Reweighting from Molecular Mechanics Force Fields to the ANI-2x Neural Network Potential

Tkaczyk,

Karwounopoulos,

Schöller

et al. 2024

J. Chem. Theory Comput.

View full text Add to dashboard Cite

To achieve chemical accuracy in free energy calculations, it is necessary to accurately describe the system's potential energy surface and efficiently sample configurations from its Boltzmann distribution. While neural network potentials (NNPs) have shown significantly higher accuracy than classical molecular mechanics (MM) force fields, they have a limited range of applicability and are considerably slower than MM potentials, often by orders of magnitude. To address this challenge, Rufa et al.

show abstract

OpenMM 8: Molecular Dynamics Simulation with Machine Learning Potentials

Cited by 41 publications

References 47 publications

TorchMD-Net 2.0: Fast Neural Network Potentials for Molecular Simulations

TorchMD-Net 2.0: Fast Neural Network Potentials for Molecular Simulations

Biophysics-based protein language models for protein engineering

Reweighting from Molecular Mechanics Force Fields to the ANI-2x Neural Network Potential

Contact Info

Product

Resources

About