Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Differentiable rotamer sampling with molecular force fields.

ABSTRACT: Molecular dynamics is the primary computational method by which modern structural biology explores macromolecule structure and function. Boltzmann generators have been proposed as an alternative to molecular dynamics, by replacing the integration of molecular systems over time with the training of generative neural networks. This neural network approach to MD samples rare events at a higher rate than traditional MD, however critical gaps in the theory and computational feasibility of Boltzmann generators significantly reduce their usability. Here, we develop a mathematical foundation to overcome these barriers; we demonstrate that the Boltzmann generator approach is sufficiently rapid to replace traditional MD for complex macromolecules, such as proteins in specific applications, and we provide a comprehensive toolkit for the exploration of molecular energy landscapes with neural networks.

SUBMITTER: Sha CM

PROVIDER: S-EPMC9980192 | biostudies-literature | 2023 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Differentiable rotamer sampling with molecular force fields.

Sha Congzhou M CM Wang Jian J Dokholyan Nikolay V NV

ArXiv 20230222

Molecular dynamics is the primary computational method by which modern structural biology explores macromolecule structure and function. Boltzmann generators have been proposed as an alternative to molecular dynamics, by replacing the integration of molecular systems over time with the training of generative neural networks. This neural network approach to MD samples rare events at a higher rate than traditional MD, however critical gaps in the theory and computational feasibility of Boltzmann g ...[more]

PMID: 36866228

Similar Datasets

Differentiable rotamer sampling with molecular force fields.

Project description:Molecular dynamics (MD) is the primary computational method by which modern structural biology explores macromolecule structure and function. Boltzmann generators have been proposed as an alternative to MD, by replacing the integration of molecular systems over time with the training of generative neural networks. This neural network approach to MD enables convergence to thermodynamic equilibrium faster than traditional MD; however, critical gaps in the theory and computational feasibility of Boltzmann generators significantly reduce their usability. Here, we develop a mathematical foundation to overcome these barriers; we demonstrate that the Boltzmann generator approach is sufficiently rapid to replace traditional MD for complex macromolecules, such as proteins in specific applications, and we provide a comprehensive toolkit for the exploration of molecular energy landscapes with neural networks.

| S-EPMC10720392 | biostudies-literature

Differentiable simulation to develop molecular dynamics force fields for disordered proteins.

Project description:Implicit solvent force fields are computationally efficient but can be unsuitable for running molecular dynamics on disordered proteins. Here I improve the a99SB-disp force field and the GBNeck2 implicit solvent model to better describe disordered proteins. Differentiable molecular simulations with 5 ns trajectories are used to jointly optimise 108 parameters to better match explicit solvent trajectories. Simulations with the improved force field better reproduce the radius of gyration and secondary structure content seen in experiments, whilst showing slightly degraded performance on folded proteins and protein complexes. The force field, called GB99dms, reproduces the results of a small molecule binding study and improves agreement with experiment for the aggregation of amyloid peptides. GB99dms, which can be used in OpenMM, is available at https://github.com/greener-group/GB99dms. This work is the first to show that gradients can be obtained directly from nanosecond-length differentiable simulations of biomolecules and highlights the effectiveness of this approach to training whole force fields to match desired properties.

| S-EPMC10966991 | biostudies-literature

Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks.

Project description:Neural network (NN) interatomic potentials provide fast prediction of potential energy surfaces, closely matching the accuracy of the electronic structure methods used to produce the training data. However, NN predictions are only reliable within well-learned training domains, and show volatile behavior when extrapolating. Uncertainty quantification methods can flag atomic configurations for which prediction confidence is low, but arriving at such uncertain regions requires expensive sampling of the NN phase space, often using atomistic simulations. Here, we exploit automatic differentiation to drive atomistic systems towards high-likelihood, high-uncertainty configurations without the need for molecular dynamics simulations. By performing adversarial attacks on an uncertainty metric, informative geometries that expand the training domain of NNs are sampled. When combined with an active learning loop, this approach bootstraps and improves NN potentials while decreasing the number of calls to the ground truth method. This efficiency is demonstrated on sampling of kinetic barriers, collective variables in molecules, and supramolecular chemistry in zeolite-molecule interactions, and can be extended to any NN potential architecture and materials system.

| S-EPMC8384857 | biostudies-literature

Q-Force: Quantum Mechanically Augmented Molecular Force Fields.

Project description:The quality of molecular dynamics simulations strongly depends on the accuracy of the underlying force fields (FFs) that determine all intra- and intermolecular interactions of the system. Commonly, transferable FF parameters are determined based on a representative set of small molecules. However, such an approach sacrifices accuracy in favor of generality. In this work, an open-source and automated toolkit named Q-Force is presented, which augments these transferable FFs with molecule-specific bonded parameters and atomic charges that are derived from quantum mechanical (QM) calculations. The molecular fragmentation procedure allows treatment of large molecules (>200 atoms) with a low computational cost. The generated Q-Force FFs can be used at the same computational cost as transferable FFs, but with improved accuracy: We demonstrate this for the vibrational properties on a set of small molecules and for the potential energy surface on a complex molecule (186 atoms) with photovoltaic applications. Overall, the accuracy, user-friendliness, and minimal computational overhead of the Q-Force protocol make it widely applicable for atomistic molecular dynamics simulations.

| S-EPMC8359013 | biostudies-literature

A Differentiable Neural-Network Force Field for Ionic Liquids.

Project description:We present NeuralIL, a model for the potential energy of an ionic liquid that accurately reproduces first-principles results with orders-of-magnitude savings in computational cost. Built on the basis of a multilayer perceptron and spherical Bessel descriptors of the atomic environments, NeuralIL is implemented in such a way as to be fully automatically differentiable. It can thus be trained on ab initio forces instead of just energies, to make the most out of the available data, and can efficiently predict arbitrary derivatives of the potential energy. Using ethylammonium nitrate as the test system, we obtain out-of-sample accuracies better than 2 meV atom-1 (<0.05 kcal mol-1) in the energies and 70 meV Å-1 in the forces. We show that encoding the element-specific density in the spherical Bessel descriptors is key to achieving this. Harnessing the information provided by the forces drastically reduces the amount of atomic configurations required to train a neural network force field based on atom-centered descriptors. We choose the Swish-1 activation function and discuss the role of this choice in keeping the neural network differentiable. Furthermore, the possibility of training on small data sets allows for an ensemble-learning approach to the detection of extrapolation. Finally, we find that a separate treatment of long-range interactions is not required to achieve a high-quality representation of the potential energy surface of these dense ionic systems.

| S-EPMC8757435 | biostudies-literature

Differentiable molecular simulation can learn all the parameters in a coarse-grained force field for proteins.

Project description:Finding optimal parameters for force fields used in molecular simulation is a challenging and time-consuming task, partly due to the difficulty of tuning multiple parameters at once. Automatic differentiation presents a general solution: run a simulation, obtain gradients of a loss function with respect to all the parameters, and use these to improve the force field. This approach takes advantage of the deep learning revolution whilst retaining the interpretability and efficiency of existing force fields. We demonstrate that this is possible by parameterising a simple coarse-grained force field for proteins, based on training simulations of up to 2,000 steps learning to keep the native structure stable. The learned potential matches chemical knowledge and PDB data, can fold and reproduce the dynamics of small proteins, and shows ability in protein design and model scoring applications. Problems in applying differentiable molecular simulation to all-atom models of proteins are discussed along with possible solutions and the variety of available loss functions. The learned potential, simulation scripts and training code are made available at https://github.com/psipred/cgdms.

| S-EPMC8412298 | biostudies-literature

Comparing molecular dynamics force fields in the essential subspace.

Project description:The continued development and utility of molecular dynamics simulations requires improvements in both the physical models used (force fields) and in our ability to sample the Boltzmann distribution of these models. Recent developments in both areas have made available multi-microsecond simulations of two proteins, ubiquitin and Protein G, using a number of different force fields. Although these force fields mostly share a common mathematical form, they differ in their parameters and in the philosophy by which these were derived, and previous analyses showed varying levels of agreement with experimental NMR data. To complement the comparison to experiments, we have performed a structural analysis of and comparison between these simulations, thereby providing insight into the relationship between force-field parameterization, the resulting ensemble of conformations and the agreement with experiments. In particular, our results show that, at a coarse level, many of the motional properties are preserved across several, though not all, force fields. At a finer level of detail, however, there are distinct differences in both the structure and dynamics of the two proteins, which can, together with comparison with experimental data, help to select force fields for simulations of proteins. A noteworthy observation is that force fields that have been reparameterized and improved to provide a more accurate energetic description of the balance between helical and coil structures are difficult to distinguish from their "unbalanced" counterparts in these simulations. This observation implies that simulations of stable, folded proteins, even those reaching 10 microseconds in length, may provide relatively little information that can be used to modify torsion parameters to achieve an accurate balance between different secondary structural elements.

| S-EPMC4374674 | biostudies-literature

Machine Learning of Coarse-Grained Molecular Dynamics Force Fields.

Project description:Atomistic or ab initio molecular dynamics simulations are widely used to predict thermodynamics and kinetics and relate them to molecular structure. A common approach to go beyond the time- and length-scales accessible with such computationally expensive simulations is the definition of coarse-grained molecular models. Existing coarse-graining approaches define an effective interaction potential to match defined properties of high-resolution models or experimental data. In this paper, we reformulate coarse-graining as a supervised machine learning problem. We use statistical learning theory to decompose the coarse-graining error and cross-validation to select and compare the performance of different models. We introduce CGnets, a deep learning approach, that learns coarse-grained free energy functions and can be trained by a force-matching scheme. CGnets maintain all physically relevant invariances and allow one to incorporate prior physics knowledge to avoid sampling of unphysical structures. We show 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. Thus, CGnets are able to capture multibody terms that emerge from the dimensionality reduction.

| S-EPMC6535777 | biostudies-literature

Machine learning of accurate energy-conserving molecular force fields.

Project description:Using conservation of energy-a fundamental property of closed classical and quantum mechanical systems-we develop an efficient gradient-domain machine learning (GDML) approach to construct accurate molecular force fields using a restricted number of samples from ab initio molecular dynamics (AIMD) trajectories. The GDML implementation is able to reproduce global potential energy surfaces of intermediate-sized molecules with an accuracy of 0.3 kcal mol-1 for energies and 1 kcal mol-1 Å̊-1 for atomic forces using only 1000 conformational geometries for training. We demonstrate this accuracy for AIMD trajectories of molecules, including benzene, toluene, naphthalene, ethanol, uracil, and aspirin. The challenge of constructing conservative force fields is accomplished in our work by learning in a Hilbert space of vector-valued functions that obey the law of energy conservation. The GDML approach enables quantitative molecular dynamics simulations for molecules at a fraction of cost of explicit AIMD calculations, thereby allowing the construction of efficient force fields with the accuracy and transferability of high-level ab initio methods.

| S-EPMC5419702 | biostudies-literature

Enhancing Side Chain Rotamer Sampling Using Nonequilibrium Candidate Monte Carlo.

Project description:Molecular simulations are a valuable tool for studying biomolecular motions and thermodynamics. However, such motions can be slow compared to simulation time scales, yet critical. Specifically, adequate sampling of side chain motions in protein binding pockets is crucial for obtaining accurate estimates of ligand binding free energies from molecular simulations. The time scale of side chain rotamer flips can range from a few ps to several hundred ns or longer, particularly in crowded environments like the interior of proteins. Here, we apply a mixed nonequilibrium candidate Monte Carlo (NCMC)/molecular dynamics (MD) method to enhance sampling of side chain rotamers. The NCMC portion of our method applies a switching protocol wherein the steric and electrostatic interactions between target side chain atoms and the surrounding environment are cycled off and then back on during the course of a move proposal. Between NCMC move proposals, simulation of the system continues via traditional molecular dynamics. Here, we first validate this approach on a simple, solvated valine-alanine dipeptide system and then apply it to a well-studied model ligand binding site in T4 lysozyme L99A. We compute the rate of rotamer transitions for a valine side chain using our approach and compare it to that of traditional molecular dynamics simulations. Here, we show that our NCMC/MD method substantially enhances side chain sampling, especially in systems where the torsional barrier to rotation is high (≥10 kcal/mol). These barriers can be intrinsic torsional barriers or steric barriers imposed by the environment. Overall, this may provide a promising strategy to selectively improve side chain sampling in molecular simulations.

| S-EPMC6537864 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data