Browse
Submit Data
Databases
API
Help

Dataset Information

22 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

A Differentiable Neural-Network Force Field for Ionic Liquids.

ABSTRACT: 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.

SUBMITTER: Montes-Campos H

PROVIDER: S-EPMC8757435 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

BILFF: All-Atom Force Field for Modeling Triazolium- and Benzoate-Based Ionic Liquids.

Project description:We present an extension of our previously developed all-atom force field BILFF (Bio-polymers in Ionic Liquids Force Field) to three different ionic liquids: 1-ethyl-3-methyl-1,2,3-triazolium acetate ([EMTr][OAc]), 1-ethyl-3-methyl-1,2,3-triazolium benzoate ([EMTr][OBz]), and 1-ethyl-3-methylimidazolium benzoate ([EMIm][OBz]). These ionic liquids are of practical importance as they have the ability to dissolve significant amounts of cellulose even at room temperature. Our force field is optimized to accurately reproduce the strong hydrogen bonding in the system with nearly quantum chemical accuracy. A very good agreement between the microstructure of the quantum chemical simulations over a wide temperature range and experimental density data with the results of BILFF were observed. Non-trivial effects, such as the solvation shell structure and π-π stacking of the cations, are also accurately reproduced. Our force field enables accurate simulations of larger systems, such as solvated cellulose in different (aqueous) ionic liquids, and is the first to present the optimized parameters for mixtures of these solvents and water.

| S-EPMC10674667 | biostudies-literature

Force Field for Water Based on Neural Network.

Project description:We developed a novel neural network-based force field for water based on training with high-level ab initio theory. The force field was built based on an electrostatically embedded many-body expansion method truncated at binary interactions. The many-body expansion method is a common strategy to partition the total Hamiltonian of large systems into a hierarchy of few-body terms. Neural networks were trained to represent electrostatically embedded one-body and two-body interactions, which require as input only one and two water molecule calculations at the level of ab initio electronic structure method CCSD/aug-cc-pVDZ embedded in the molecular mechanics water environment, making it efficient as a general force field construction approach. Structural and dynamic properties of liquid water calculated with our force field show good agreement with experimental results. We constructed two sets of neural network based force fields: nonpolarizable and polarizable force fields. Simulation results show that the nonpolarizable force field using fixed TIP3P charges has already behaved well, since polarization effects and many-body effects are implicitly included due to the electrostatic embedding scheme. Our results demonstrate that the electrostatically embedded many-body expansion combined with neural network provides a promising and systematic way to build next-generation force fields at high accuracy and low computational costs, especially for large systems.

| S-EPMC6241215 | biostudies-literature

Accurate Diels-Alder Energies and Endo Selectivity in Ionic Liquids Using the OPLS-VSIL Force Field.

Project description:Our recently developed optimized potentials for liquid simulations-virtual site ionic liquid (OPLS-VSIL) force field has been shown to provide accurate bulk phase properties and local ion-ion interactions for a wide variety of imidazolium-based ionic liquids. The force field features a virtual site that offloads negative charge to inside the plane of the ring with careful attention given to hydrogen bonding interactions. In this study, the Diels-Alder reaction between cyclopentadiene and methyl acrylate was computationally investigated in the ionic liquid 1-butyl-3-methylimidazolium hexafluorophosphate, [BMIM][PF6], as a basis for the validation of the OPLS-VSIL to properly reproduce a reaction medium environment. Mixed ab initio quantum mechanics and molecular mechanics (QM/MM) calculations coupled to free energy perturbation and Monte Carlo sampling (FEP/MC) that utilized M06-2X/6-31G(d) and OPLS-VSIL gave activation free energy barriers of 14.9 and 16.0 kcal/mol for the endo-cis and exo-cis Diels-Alder reaction pathways, respectively (exptl. ΔH‡ of 14.6 kcal/mol). The endo selectivity trend was correctly predicted with a calculated 73% endo preference. The rate and selectivity enhancements present in the endo conformation were found to arise from preferential hydrogen bonding with the exposed C4 ring hydrogen on the BMIM cation. Weaker electronic stabilization of the exo transition state was predicted. For comparison, our earlier ±0.8 charge-scaled OPLS-2009IL force field also yielded a ΔG‡ of 14.9 kcal/mol for the favorable endo reaction pathway but did not adequately capture the highly organized solvent interactions present between the cation and Diels-Alder transition state.

| S-EPMC7072795 | biostudies-literature

Unravelling the Interactions of Magnetic Ionic Liquids by Energy Decomposition Schemes: Towards a Transferable Polarizable Force Field.

Project description:This work aims at unravelling the interactions in magnetic ionic liquids (MILs) by applying Symmetry-Adapted Perturbation Theory (SAPT) calculations, as well as based on those to set-up a polarisable force field model for these liquids. The targeted MILs comprise two different cations, namely: 1-butyl-3-methylimidazolium ([Bmim]+) and 1-ethyl-3-methylimidazolium ([Emim]+), along with several metal halides anions such as [FeCl4]-, [FeBr4]-, [ZnCl3]- and [SnCl4]2- To begin with, DFT geometry optimisations of such MILs were performed, which in turn revealed that the metallic anions prefer to stay close to the region of the carbon atom between the nitrogen atoms in the imidazolium fragment. Then, a SAPT study was carried out to find the optimal separation of the monomers and the different contributions for their interaction energy. It was found that the main contribution to the interaction energy is the electrostatic interaction component, followed by the dispersion one in most of the cases. The SAPT results were compared with those obtained by employing the local energy decomposition scheme based on the DLPNO-CCSD(T) method, the latter showing slightly lower values for the interaction energy as well as an increase of the distance between the minima centres of mass. Finally, the calculated SAPT interaction energies were found to correlate well with the melting points experimentally measured for these MILs.

| S-EPMC8466702 | biostudies-literature

Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting.

Project description:In molecular dynamics (MD), neural network (NN) potentials trained bottom-up on quantum mechanical data have seen tremendous success recently. Top-down approaches that learn NN potentials directly from experimental data have received less attention, typically facing numerical and computational challenges when backpropagating through MD simulations. We present the Differentiable Trajectory Reweighting (DiffTRe) method, which bypasses differentiation through the MD simulation for time-independent observables. Leveraging thermodynamic perturbation theory, we avoid exploding gradients and achieve around 2 orders of magnitude speed-up in gradient computation for top-down learning. We show effectiveness of DiffTRe in learning NN potentials for an atomistic model of diamond and a coarse-grained model of water based on diverse experimental observables including thermodynamic, structural and mechanical properties. Importantly, DiffTRe also generalizes bottom-up structural coarse-graining methods such as iterative Boltzmann inversion to arbitrary potentials. The presented method constitutes an important milestone towards enriching NN potentials with experimental data, particularly when accurate bottom-up data is unavailable.

| S-EPMC8617111 | biostudies-literature

Transcriptional toxicity of imidazolium- and cholinium-based ionic liquids

Project description:Ionic Liquids are a broad group of salts with low melting points that can be specifically tuned for a broad range of applications. Despite being initially considered “green” solvents, their better environmental friendliness compared to traditional solvents has been increasingly challenged. In this study, we aimed to investigate the molecular effects of ILs exposure by using RNA-sequencing to study differential gene expression patterns. Thus, we exposed Daphnia magna to 1-ethyl-3-methylimidazolium chloride ([C2mim]Cl), 1-dodecyl chloride-3-methylimidazolium ([C12mim]Cl) and cholinium chloride ([Chol]Cl). Results suggest that the three ILs share several mechanisms of toxicity, including cellular membrane and cytoskeleton damage, oxidative stress, inhibition of antioxidant enzymes, mitochondrial affectation, changes in protein biosynthesis and energy production, DNA damage, and ultimately, programmed cell death and disease initiation. Overall, the dataset revealed that [C2mim]Cl and [C12mim]Cl were, respectively, the least and the most toxic ILs at the transcriptional level. Also, it is reinforced that [Chol]Cl is not devoid of environmental hazardous potential. Unique gene expression signatures could also be identified for each IL.

2021-08-13 | GSE156769 | GEO

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

Differentiable rotamer sampling with molecular force fields.

Project description: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.

| S-EPMC9980192 | biostudies-literature

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

ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost.

Project description:Deep learning is revolutionizing many areas of science and technology, especially image, text, and speech recognition. In this paper, we demonstrate how a deep neural network (NN) trained on quantum mechanical (QM) DFT calculations can learn an accurate and transferable potential for organic molecules. We introduce ANAKIN-ME (Accurate NeurAl networK engINe for Molecular Energies) or ANI for short. ANI is a new method designed with the intent of developing transferable neural network potentials that utilize a highly-modified version of the Behler and Parrinello symmetry functions to build single-atom atomic environment vectors (AEV) as a molecular representation. AEVs provide the ability to train neural networks to data that spans both configurational and conformational space, a feat not previously accomplished on this scale. We utilized ANI to build a potential called ANI-1, which was trained on a subset of the GDB databases with up to 8 heavy atoms in order to predict total energies for organic molecules containing four atom types: H, C, N, and O. To obtain an accelerated but physically relevant sampling of molecular potential surfaces, we also proposed a Normal Mode Sampling (NMS) method for generating molecular conformations. Through a series of case studies, we show that ANI-1 is chemically accurate compared to reference DFT calculations on much larger molecular systems (up to 54 atoms) than those included in the training data set.

| S-EPMC5414547 | 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