Efficient interatomic descriptors for accurate machine learning force fields of extended molecules

Kabylda, Adil M.; Vassilev-Galindo, Valentín; Chmiela, Stefan; Poltavsky, Igor; Tkatchenko, Alexandre

doi:10.1038/s41467-023-39214-w

Cited by 13 publications

(4 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, we construct the neural network term to augment the intermolecular interactions only. ,,,, In contrast to the prevailing practice of partitioning the potential energy onto individual atoms, ,,, we partition the energy onto interacting pairs of atoms (A–B). , A representative diagram of the fingerprint of an interacting pair is shown in Figure a . To encode the pair interaction A–B, we use atom pair symmetry functions (APSF) centered at the midpoint X between A and B (A–X–B).…”

Section: Interaction Modelmentioning

confidence: 99%

Combining Force Fields and Neural Networks for an Accurate Representation of Chemically Diverse Molecular Interactions

Illarionov,

Sakipov,

Pereyaslavets

et al. 2023

J. Am. Chem. Soc.

View full text Add to dashboard Cite

A key goal of molecular modeling is the accurate reproduction of the true quantum mechanical potential energy of arbitrary molecular ensembles with a tractable classical approximation. The challenges are that analytical expressions found in general purpose force fields struggle to faithfully represent the intermolecular quantum potential energy surface at close distances and in strong interaction regimes; that the more accurate neural network approximations do not capture crucial physics concepts, e.g., nonadditive inductive contributions and application of electric fields; and that the ultra-accurate narrowly targeted models have difficulty generalizing to the entire chemical space. We therefore designed a hybrid wide-coverage intermolecular interaction model consisting of an analytically polarizable force field combined with a short-range neural network correction for the total intermolecular interaction energy. Here, we describe the methodology and apply the model to accurately determine the properties of water, the free energy of solvation of neutral and charged molecules, and the binding free energy of ligands to proteins. The correction is subtyped for distinct chemical species to match the underlying force field, to segment and reduce the amount of quantum training data, and to increase accuracy and computational speed. For the systems considered, the hybrid ab initio parametrized Hamiltonian reproduces the two-body dimer quantum mechanics (QM) energies to within 0.03 kcal/mol and the nonadditive many-molecule contributions to within 2%. Simulations of molecular systems using this interaction model run at speeds of several nanoseconds per day.

show abstract

Section: Interaction Modelmentioning

confidence: 99%

Combining Force Fields and Neural Networks for an Accurate Representation of Chemically Diverse Molecular Interactions

Illarionov,

Sakipov,

Pereyaslavets

et al. 2023

J. Am. Chem. Soc.

View full text Add to dashboard Cite

show abstract

“…Recent works have tried to address this challenge by designing specific training schemes [ 192 ] or by reducing the dimensionality of global descriptors via automatic identification of those most relevant for the description of large and flexible molecules. [ 193 ]…”

Section: Machine Learning Potentials and Force Fieldsmentioning

confidence: 99%

In Silico Chemical Experiments in the Age of AI: From Quantum Chemistry to Machine Learning and Back

Aldossary,

Campos‐Gonzalez‐Angulo,

Pablo‐García

et al. 2024

Advanced Materials

View full text Add to dashboard Cite

Computational chemistry is an indispensable tool for understanding molecules and predicting chemical properties. However, traditional computational methods face significant challenges due to the difficulty of solving the Schrödinger equations and the increasing computational cost with the size of the molecular system. In response, there has been a surge of interest in leveraging artificial intelligence (AI) and machine learning (ML) techniques to in silico experiments. Integrating AI and ML into computational chemistry increases the scalability and speed of the exploration of chemical space. However, challenges remain, particularly regarding the reproducibility and transferability of ML models. This review highlights the evolution of ML in learning from, complementing, or replacing traditional computational chemistry for energy and property predictions. Starting from models trained entirely on numerical data, a journey set forth toward the ideal model incorporating or learning the physical laws of quantum mechanics. This paper also reviews existing computational methods and ML models and their intertwining, outlines a roadmap for future research, and identifies areas for improvement and innovation. Ultimately, the goal is to develop AI architectures capable of predicting accurate and transferable solutions to the Schrödinger equation, thereby revolutionizing in silico experiments within chemistry and materials science.

show abstract

“…Due to the cubic scaling of DFT implementations, the average number of atoms is typically below one hundred for dense systems under periodic boundary conditions. It is questionable whether long-range interactions [39] can be learned from such databases, considering the recent finding that features related to interatomic distances as large as 15 Å can play an essential role in describing non-local interactions [40].…”

Section: Introductionmentioning

confidence: 99%

Accurate machine learning force fields via experimental and simulation data fusion

Zavadlav,

Röcken

2023

Preprint

View full text Add to dashboard Cite

Machine Learning (ML)-based force fields are attracting ever-increasing interest due to their capacity to span spatiotemporal scales of classical interatomic potentials at quantum-level accuracy. They can be trained based on high-fidelity simulations or experiments, the former being the common case. However, both approaches are impaired by scarce and erroneous data resulting in models that either do not agree with well-known experimental observations or are under-constrained and only reproduce some properties. Here we leverage both Density Functional Theory (DFT) calculations and experimentally measured mechanical properties and lattice parameters to train an ML potential of titanium. We demonstrate that the fused data learning strategy can concurrently satisfy all target objectives, thus resulting in a molecular model of higher accuracy compared to the models trained with a single data source. The inaccuracies of DFT functionals at target experimental properties were corrected, while the investigated off-target properties remained largely unperturbed. Our approach is applicable to any material and can serve as a general strategy to obtain highly accurate ML potentials.

show abstract

Efficient interatomic descriptors for accurate machine learning force fields of extended molecules

Cited by 13 publications

References 68 publications

Combining Force Fields and Neural Networks for an Accurate Representation of Chemically Diverse Molecular Interactions

Combining Force Fields and Neural Networks for an Accurate Representation of Chemically Diverse Molecular Interactions

In Silico Chemical Experiments in the Age of AI: From Quantum Chemistry to Machine Learning and Back

Accurate machine learning force fields via experimental and simulation data fusion

Contact Info

Product

Resources

About