Simulate Time-integrated Coarse-grained Molecular Dynamics with Geometric Machine Learning

@article{Fu2022SimulateTC,
  title={Simulate Time-integrated Coarse-grained Molecular Dynamics with Geometric Machine Learning},
  author={Xiang Fu and Tian Xie and Nathan J. Rebello and Bradley D. Olsen and T. Jaakkola},
  journal={ArXiv},
  year={2022},
  volume={abs/2204.10348}
}
Molecular dynamics (MD) simulation is the workhorse of various scientific domains but is limited by high computational cost. Learning-based force fields have made major progress in accelerating ab-initio MD simulation but are still not fast enough for many real-world applications that require long-time MD simulation. In this paper, we adopt a different machine learning approach where we coarse-grain a physical system using graph clustering, and model the system evolution with a very large time… 

Figures and Tables from this paper

Simple synthetic molecular dynamics for efficient trajectory generation

TLDR
This work demonstrates the use of a MSM to generate atomistic synMD trajectories for the fast-folding miniprotein Trp-cage, at a rate of over 200 milliseconds per day on a standard workstation, and employs a non-standard clustering for MSM generation that appears to better preserve kinetic properties at shorter lag times than a conventional MSM.

Faster Optimization on Sparse Graphs via Neural Reparametrization

TLDR
This paper proposes a novel optimization method based on neural reparametrization: parametrizing the solution to the optimization problem with a graph neural network (GNN), leading to significant speed-up on large sparse graphs.

Graph Neural Networks for Molecules

TLDR
This review introduces GNNs and their various applications for small organic molecules and summarizes the recent development of self-supervised learning for molecules withGNNs.

References

SHOWING 1-10 OF 79 REFERENCES

Machine Learning of Coarse-Grained Molecular Dynamics Force Fields

TLDR
CGnets, a deep learning approach, that learns coarse-grained free energy functions and can be trained by a force-matching scheme, is introduced, which shows that CGnets can capture all-atom explicit-solvent free energy surfaces with models using only a few coarse- grained beads and no solvent, while classical coarse-Graining methods fail to capture crucial features of the free energy surface.

Graph Neural Networks Accelerated Molecular Dynamics

TLDR
A GNN Accelerated MD (GAMD) model is developed that directly predicts forces, given the state of the system, bypassing the evaluation of potential energy and is agnostic to the scale, where it can scale to much larger systems at test time.

Coarse-graining auto-encoders for molecular dynamics

TLDR
This work proposes a generative modeling framework based on variational auto-encoders to unify the tasks of learning discrete coarse-grained variables, decoding back to atomistic detail, and parameterizing coarse- grained force fields.

Towards exact molecular dynamics simulations with machine-learned force fields

TLDR
A flexible machine-learning force-field with high-level accuracy for molecular dynamics simulations is developed, for flexible molecules with up to a few dozen atoms and insights into the dynamical behavior of these molecules are provided.

Coarse graining molecular dynamics with graph neural networks.

TLDR
A hybrid architecture for the machine learning of coarse-grained force fields that learn their own features via a subnetwork that leverages continuous filter convolutions on a graph neural network architecture is introduced that succeeds at reproducing the thermodynamics for small biomolecular systems.

Pushing the Limit of Molecular Dynamics with Ab Initio Accuracy to 100 Million Atoms with Machine Learning

  • Weile JiaHan Wang Linfeng Zhang
  • Computer Science
    SC20: International Conference for High Performance Computing, Networking, Storage and Analysis
  • 2020
TLDR
A machine learningbased simulation protocol (Deep Potential Molecular Dynamics), while retaining ab initio accuracy, can simulate more than 1 nanosecond-long trajectory of over 100 million atoms per day, using a highly optimized code (GPU DeePMD-kit) on the Summit supercomputer.

Accurate and scalable graph neural network force field and molecular dynamics with direct force architecture

TLDR
It is demonstrated that GNNFF not only achieves high performance in terms of force prediction accuracy and computational speed on various materials systems, but also accurately predicts the forces of a large MD system after being trained on forces obtained from a smaller system.

Learning to Simulate Complex Physics with Graph Networks

TLDR
A machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains, involving fluids, rigid solids, and deformable materials interacting with one another, and holds promise for solving a wide range of complex forward and inverse problems.

Machine learning for molecular simulation

TLDR
Recent ML methods for molecular simulation are reviewed, with particular focus on (deep) neural networks for the prediction of quantum-mechanical energies and forces, on coarse-grained molecular dynamics, on the extraction of free energy surfaces and kinetics, and on generative network approaches to sample molecular equilibrium structures and compute thermodynamics.

TorchMD: A Deep Learning Framework for Molecular Simulations

TLDR
TorchMD is presented, a framework for molecular simulations with mixed classical and machine learning potentials that enables learning and simulating neural network potentials and provides a useful tool set to support molecular simulations of machinelearning potentials.
...