Improvement of the Force Field for β-d-Glucose with Machine Learning
Ontology highlight
ABSTRACT:
SUBMITTER: Ikejo M
PROVIDER: S-EPMC8588059 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:We used the machine learning technique of Li et al. (PRL 114, 2015) for molecular dynamics simulations. Atomic configurations were described by feature matrix based on internal vectors, and linear regression was used as a learning technique. We implemented this approach in the LAMMPS code. The method was applied to crystalline and liquid aluminum and uranium at different temperatures and densities, and showed the highest accuracy among different published potentials. Phonon density of states, entropy and melting temperature of aluminum were calculated using this machine learning potential. The results are in excellent agreement with experimental data and results of full ab initio calculations.
| S-EPMC5561031 | biostudies-other
Project description:Elemental phosphorus is attracting growing interest across fundamental and applied fields of research. However, atomistic simulations of phosphorus have remained an outstanding challenge. Here, we show that a universally applicable force field for phosphorus can be created by machine learning (ML) from a suitably chosen ensemble of quantum-mechanical results. Our model is fitted to density-functional theory plus many-body dispersion (DFT + MBD) data; its accuracy is demonstrated for the exfoliation of black and violet phosphorus (yielding monolayers of "phosphorene" and "hittorfene"); its transferability is shown for the transition between the molecular and network liquid phases. An application to a phosphorene nanoribbon on an experimentally relevant length scale exemplifies the power of accurate and flexible ML-driven force fields for next-generation materials modelling. The methodology promises new insights into phosphorus as well as other structurally complex, e.g., layered solids that are relevant in diverse areas of chemistry, physics, and materials science.
| S-EPMC7596484 | biostudies-literature
Project description:In recent years, the use of machine learning (ML) in computational chemistry has enabled numerous advances previously out of reach due to the computational complexity of traditional electronic-structure methods. One of the most promising applications is the construction of ML-based force fields (FFs), with the aim to narrow the gap between the accuracy of ab initio methods and the efficiency of classical FFs. The key idea is to learn the statistical relation between chemical structure and potential energy without relying on a preconceived notion of fixed chemical bonds or knowledge about the relevant interactions. Such universal ML approximations are in principle only limited by the quality and quantity of the reference data used to train them. This review gives an overview of applications of ML-FFs and the chemical insights that can be obtained from them. The core concepts underlying ML-FFs are described in detail, and a step-by-step guide for constructing and testing them from scratch is given. The text concludes with a discussion of the challenges that remain to be overcome by the next generation of ML-FFs.
| S-EPMC8391964 | biostudies-literature
Project description:We present a complete set of chemo-structural descriptors to significantly extend the applicability of machine-learning (ML) in material screening and mapping energy landscape for multicomponent systems. These new descriptors allow differentiating between structural prototypes, which is not possible using the commonly used chemical-only descriptors. Specifically, we demonstrate that the combination of pairwise radial, nearest neighbor, bond-angle, dihedral-angle and core-charge distributions plays an important role in predicting formation energies, bandgaps, static refractive indices, magnetic properties, and modulus of elasticity for three-dimensional (3D) materials as well as exfoliation energies of two-dimensional (2D) layered materials. The training data consists of 24549 bulk and 616 monolayer materials taken from JARVIS-DFT database. We obtained very accurate ML models using gradient boosting algorithm. Then we use the trained models to discover exfoliable 2D-layered materials satisfying specific property requirements. Additionally, we integrate our formation energy ML model with a genetic algorithm for structure search to verify if the ML model reproduces the DFT convex hull. This verification establishes a more stringent evaluation metric for the ML model than what commonly used in data sciences. Our learnt model is publicly available on the JARVIS-ML website (https://www.ctcms.nist.gov/jarvisml) property predictions of generalized materials.
| S-EPMC7067064 | biostudies-literature
Project description:Intrinsically disordered proteins (IDPs) and proteins with intrinsically disordered regions (IDRs) play important roles in many aspects of normal cell physiology, such as signal transduction and transcription, as well as pathological states, including Alzheimer's, Parkinson's, and Huntington's disease. Unlike their globular counterparts that are defined by a few structures and free energy minima, IDP/IDR comprise a large ensemble of rapidly interconverting structures and a corresponding free energy landscape characterized by multiple minima. This aspect has precluded the use of structural biological techniques, such as X-ray crystallography and nuclear magnetic resonance (NMR) for resolving their structures. Instead, low-resolution techniques, such as small-angle X-ray or neutron scattering (SAXS/SANS), have become a mainstay in characterizing coarse features of the ensemble of structures. These are typically complemented with NMR data if possible or computational techniques, such as atomistic molecular dynamics, to further resolve the underlying ensemble of structures. However, over the past 10-15 years, it has become evident that the classical, pairwise-additive force fields that have enjoyed a high degree of success for globular proteins have been somewhat limited in modeling IDP/IDR structures that agree with experiment. There has thus been a significant effort to rehabilitate these models to obtain better agreement with experiment, typically done by optimizing parameters in a piecewise fashion. In this work, we take a different approach by optimizing a set of force field parameters simultaneously, using machine learning to adapt force field parameters to experimental SAXS scattering profiles. We demonstrate our approach in modeling three biologically IDP ensembles based on experimental SAXS profiles and show that our optimization approach significantly improve force field parameters that generate ensembles in better agreement with experiment.
| S-EPMC6705226 | biostudies-literature
Project description:The growing number of radio communication devices and limited spectrum resources are drivers for the development of new techniques of dynamic spectrum access and spectrum sharing. In order to make use of the spectrum opportunistically, the concept of cognitive radio was proposed, where intelligent decisions on transmission opportunities are based on spectrum sensing. In this paper, two Machine Learning (ML) algorithms, namely k-Nearest Neighbours and Random Forest, have been proposed to increase spectrum sensing performance. These algorithms have been applied to Energy Detection (ED) and Energy Vector-based data (EV) to detect the presence of a Fourth Generation (4G) Long-Term Evolution (LTE) signal for the purpose of utilizing the available resource blocks by a 5G new radio system. The algorithms capitalize on time, frequency and spatial dependencies in daily communication traffic. Research results show that the ML methods used can significantly improve the spectrum sensing performance if the input training data set is carefully chosen. The input data sets with ED decisions and energy values have been examined, and advantages and disadvantages of their real-life application have been analyzed.
| S-EPMC6806316 | biostudies-literature
Project description:All-atom force fields are now routinely used for more detailed understanding of protein folding mechanisms. However, it has been pointed out that use of all-atom force fields does not guarantee more accurate representations of proteins; in fact, sometimes it even leads to biased structural distributions. Indeed, several issues remain to be solved in force field developments, such as accurate treatment of implicit solvation for efficient conformational sampling and proper treatment of backbone interactions for secondary structure propensities. In this study, we first investigate the quality of several recently improved backbone interaction schemes in AMBER for folding simulations of a beta-hairpin peptide, and further study their influences on the peptide's folding mechanism. Due to the significant number of simulations needed for a thorough analysis of tested force fields, the implicit Poisson-Boltzmann solvent was used in all simulations. The chosen implicit solvent was found to be reasonable for studies of secondary structures based on a set of simulations of both alpha-helical and beta-hairpin peptides with the TIP3P explicit solvent as benchmark. Replica exchange molecular dynamics was also utilized for further efficient conformational sampling. Among the tested AMBER force fields, ff03 and a revised ff99 force field were found to produce structural and thermodynamic data in comparably good agreement with the experiment. However, detailed folding pathways, such as the order of backbone hydrogen bond zipping and the existence of intermediate states, are different between the two force fields, leading to force field-dependent folding mechanisms.
| S-EPMC2242415 | biostudies-literature
Project description:Computer simulation increasingly complements experimental efforts to describe nanoscale structure formation. Molecular mechanics simulations and related computational methods fundamentally rely on the accuracy of classical atomistic force fields for the evaluation of inter- and intramolecular energies. One indispensable component of such force fields, in particular for large organic molecules, is the accuracy of molecule-specific dihedral potentials which are the key determinants of molecular flexibility. We show in this work that non-local correlations of dihedral potentials play a decisive role in the description of the total molecular energy-an effect which is neglected in most state-of-the-art dihedral force fields. We furthermore present an efficient machine learning approach to compute intramolecular conformational energies. We demonstrate with the example of ?-NPD, a molecule frequently used in organic electronics, that this approach outperforms traditional force fields by decreasing the mean absolute deviations by one order of magnitude to values smaller than 0.37?kcal/mol (16.0?meV) per dihedral angle.
| S-EPMC5803249 | biostudies-other
Project description:The use of machine learning techniques in computational chemistry has gained significant momentum since large molecular databases are now readily available. Predictions of molecular properties using machine learning have advantages over the traditional quantum mechanics calculations because they can be cheaper computationally without losing the accuracy. We present a new extrapolatable and explainable molecular representation based on bonds, angles and dihedrals that can be used to train machine learning models. The trained models can accurately predict the electronic energy and the free energy of small organic molecules with atom types C, H N and O, with a mean absolute error of 1.2 kcal mol-1. The models can be extrapolated to larger organic molecules with an average error of less than 3.7 kcal mol-1 for 10 or fewer heavy atoms, which represent a chemical space two orders of magnitude larger. The rapid energy predictions of multiple molecules, up to 7 times faster than previous ML models of similar accuracy, has been achieved by sampling geometries around the potential energy surface minima. Therefore, the input geometries do not have to be located precisely on the minima and we show that accurate density functional theory energy predictions can be made from force-field optimised geometries with a mean absolute error 2.5 kcal mol-1.
| S-EPMC9214916 | biostudies-literature
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