Machine learning implicit solvation for molecular dynamics.

@article{Chen2021MachineLI,
  title={Machine learning implicit solvation for molecular dynamics.},
  author={Yaoyi Chen and Andreas Kr{\"a}mer and Nicholas E Charron and Brooke E. Husic and Cecilia Clementi and Frank No'e},
  journal={The Journal of chemical physics},
  year={2021},
  volume={155 8},
  pages={
          084101
        }
}
Accurate modeling of the solvent environment for biological molecules is crucial for computational biology and drug design. A popular approach to achieve long simulation time scales for large system sizes is to incorporate the effect of the solvent in a mean-field fashion with implicit solvent models. However, a challenge with existing implicit solvent models is that they often lack accuracy or certain physical properties compared to explicit solvent models as the many-body effects of the… 

Figures and Tables from this paper

Accurate Sampling of Macromolecular Conformations Using Adaptive Deep Learning and Coarse-Grained Representation

A hierarchical approach based on expressive normalizing flows with rational quadratic neural splines and coarse-grained representation was developed to accurately generate samples of large molecular systems from a high-dimensional multimodal equilibrium distribution function.

Machine Learning Coarse-Grained Potentials of Protein Thermodynamics

It is shown that a single coarse-grained potential can integrate all twelve proteins and can capture experimental structural features of mutated proteins, indicating that machine learning coarse- grained potentials could provide a feasible approach to simulate and understand protein dynamics.

Uncertainty Driven Active Learning of Coarse Grained Free Energy Models

It is shown that principled Bayesian model uncertainty allows for efficient data collection through an on-the-fly active learning framework and open the possibility of adaptive transfer of models across different chemical systems.

Deep coarse-grained potentials via relative entropy minimization.

This work demonstrates that RE training is more data efficient, due to accessing the CG distribution during training, resulting in improved free energy surfaces and reduced sensitivity to prior potentials, and supports the use of training objectives beyond FM, as a promising direction for improving CG NN potential's accuracy and reliability.

Flow-Matching: Efficient Coarse-Graining of Molecular Dynamics without Forces.

Coarse-grained (CG) molecular simulations have become a standard tool to study molecular processes on time and length scales inaccessible to all-atom simulations. Parametrizing CG force fields to

COGRIMEN: Coarse-Grained Method for Modeling of Membrane Proteins in Implicit Environments

The presented methodology is based on coarse-grained representation of biomolecules in implicit environments and is designed for the molecular dynamics simulations of membrane proteins and their complexes and can be useful for fast and brief studies of large membrane protein complexes.

Force-matching Coarse-Graining without Forces

Coarse-grained (CG) molecular simulations have become a standard tool to study molecular processes on timeand length-scales inaccessible to all-atom simulations. Learning CG force fields from

Temporally Coherent Backmapping of Molecular Trajectories From Coarse-Grained to Atomistic Resolution

This work trains a conditional variational autoencoder to nondeterministically reconstruct atomistic detail conditioned on both the target coarse-grain configuration and the previously reconstructed atomistic configuration, and demonstrates the backmapping approach on two exemplar biomolecular systems.

Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations

A novel benchmark suite for ML MD simulation is introduced, identifying stability as a key metric for ML models to improve and illustrating, in particular, how the commonly benchmarked force accuracy is not well aligned with relevant simulation metrics.

References

SHOWING 1-10 OF 21 REFERENCES

Improved Generalized Born Solvent Model Parameters for Protein Simulations.

The new GB model (GB-Neck2) has better agreement to Poisson-Boltzmann (PB) in terms of reproducing solvation energies for a variety of systems ranging from peptides to proteins.

Water models for biomolecular simulations

It is argued that verifying robustness of simulation results to the choice of water model can be of immediate benefit even in the absence of a clear replacement for older models; a specific strategy is proposed.

Transferable Dynamic Molecular Charge Assignment Using Deep Neural Networks.

HIP-NN charge predictions are many orders of magnitude faster than direct DFT calculations, and combined results provide further evidence that ML (specifically HIP-NN) provides a pathway to greatly increase the range of feasible simulations while retaining quantum-level accuracy.

Discovering a Transferable Charge Assignment Model Using Machine Learning.

A machine learning algorithm is used to discover a new charge assignment model, called Affordable Charge Assignment (ACA), that is computationally inexpensive and predicts dipoles of out-of-sample molecules accurately, and dipole-inferred ACA charges are transferable to dipole and even quadrupole moments of much larger molecules than those used for training.

Improvements in Markov State Model Construction Reveal Many Non-Native Interactions in the Folding of NTL9.

An improved method is suggested, which utilizes second order Independent Components Analysis (also known as time-structure based Independent components Analysis, or tICA), to construct the state-space of Markov State Models, and the resulting model is an improvement over previously built models using conventional distance metrics.

Identification of slow molecular order parameters for Markov model construction.

The variational principle of conformation dynamics is used to derive an optimal way of identifying the "slow subspace" of a large set of prior order parameters - either generic internal coordinates or a user-defined set of parameters.

OPLS3: A Force Field Providing Broad Coverage of Drug-like Small Molecules and Proteins.

Together, the improvements made to both the small molecule and protein force field lead to a high level of accuracy in predicting protein-ligand binding measured over a wide range of targets and ligands (less than 1 kcal/mol RMS error) representing a 30% improvement over earlier variants of the OPLS force field.

ff14SB: Improving the Accuracy of Protein Side Chain and Backbone Parameters from ff99SB.

Together, these backbone and side chain modifications (hereafter called ff14SB) not only better reproduced their benchmarks, but also improved secondary structure content in small peptides and reproduction of NMR χ1 scalar coupling measurements for proteins in solution.

Coarse-graining errors and numerical optimization using a relative entropy framework.

It is shown that the relative entropy offers tight control over the errors due to coarse-graining in arbitrary microscopic properties, and a systematic approach to reducing them is suggested.

Water Dynamics in the Hydration Shells of Biomolecules

Progress in theory and molecular dynamics simulations as well as in ultrafast vibrational spectroscopy has led to new and detailed insight into fluctuations of water structure, elementary water motions, electric fields at hydrated biointerfaces, and processes of vibrational relaxation and energy dissipation.