Benchmarking Force Field and the ANI Neural Network Potentials for the Torsional Potential Energy Surface of Biaryl Drug Fragments

Lahey, Shae-Lynn; Phuc, Tu Nguyen Thien; Rowley, Christopher N.

doi:10.1021/acs.jcim.0c00904

Cited by 27 publications

(39 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Small chemical changes to molecules, both local and remote, can drastically alter their electronic properties. This poses a challenge to force field parametrization, specifically that of torsion parameters which rely on computationally expensive QC torsion scans for reference data [23]. Given how poorly QC torsion scans scale with molecular size, molecules are fragmented to smaller entities to generate the reference data.…”

Section: Resultsmentioning

confidence: 99%

“…However, since atom types are locally defined, they do not always capture long-range effects such as conjugation. This is especially problematic for torsions since the torsion energy function (or profile) of a bond is determined by a combination of local and non-local effects such as conjugation, hyperconjugation, sterics, and electrostatics [12, 23, 27, 36, 48]. In this study, we define local atoms as those within two bonds of the central bond of a torsion, and remote atoms as any atom beyond those two bonds.…”

Section: Theory and Definitionsmentioning

confidence: 99%

See 1 more Smart Citation

Capturing non-local through-bond effects in molecular mechanics force fields I: Fragmenting molecules for quantum chemical torsion scans [Article v1.1]

Stern

Bayly²,

Smith

et al. 2020

Preprint

View full text Add to dashboard Cite

Accurate molecular mechanics force fields for small molecules are essential for predicting protein-ligand binding affinities in drug discovery and understanding the biophysics of biomolecular systems. Torsion potentials derived from quantum chemical (QC) calculations are critical for determining the conformational distributions of small molecules, but are computationally expensive and scale poorly with molecular size. To reduce computational cost and avoid the complications of distal through-space intramolecular interactions, molecules are generally fragmented into smaller entities to carry out QC torsion scans. However, torsion potentials, particularly for conjugated bonds, can be strongly affected by through-bond chemistry distal to the torsion itself. Poor fragmentation schemes have the potential to significantly disrupt electronic properties in the region around the torsion by removing important, distal chemistries, leading to poor representation of the parent molecule’s chemical environment and the resulting torsion energy profile. Here we show that a rapidly computable quantity, the fractional Wiberg bond order (WBO), is a sensitive reporter on whether the chemical environment around a torsion has been disrupted. We show that the WBO can be used as a surrogate to assess the robustness of fragmentation schemes and identify conjugated bond sets. We use this concept to construct a validation set by exhaustively fragmenting a set of druglike organic molecules and examine their corresponding WBO distributions derived from accessible conformations that can be used to evaluate fragmentation schemes. To illustrate the utility of the WBO in assessing fragmentation schemes that preserve the chemical environment, we propose a new fragmentation scheme that uses rapidly-computable AM1 WBOs, which are available essentially for free as part of standard AM1-BCC partial charge assignment. This approach can simultaneously maximize the chemical equivalency of the fragment and the substructure in the larger molecule while minimizing fragment size to accelerate QC torsion potential computation for small molecules and reducing undesired through-space steric interactions.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Theory and Definitionsmentioning

confidence: 99%

Capturing non-local through-bond effects in molecular mechanics force fields I: Fragmenting molecules for quantum chemical torsion scans [Article v1.1]

Stern

Bayly²,

Smith

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The difference of the ligand RMSD is expect because, as previous works 37,38,42 indicates, ANI-2x models the dihedral angles more accurately than GAFF. Also, it is important to note that our simulations are 50 times longer than previously reported 39 and have not resulted to any non-physical conformation.…”

Section: Analysis Of Protein-ligand Complexesmentioning

confidence: 87%

NNP/MM: Fast molecular dynamics simulations with machine learning potentials and molecular mechanics

Galvelis¹,

Varela-Rial²,

Doerr³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The ANI/MM scheme has been expanded with another work on torsional barriers of drug molecules containing biaryl fragments 137 . The data was taken from a benchmark dataset developed by Dahlgren et al 137 The biaryl molecules were specifically chosen since their torsional PES vary due to the steric and electronic effects within proteins and particularly challenging to parametrize. The study benchmarked four FF: generalized AMBER force field (GAFF), 138 open force field (OpenFF), 139 CHARMM general force field (CGenFF), 140 and OPLS 141 .…”

Section: Selected Applications With Neural Network Potentialsmentioning

confidence: 99%

Learning molecular potentials with neural networks

Gökcan

Isayev

2021

WIREs Comput Mol Sci

View full text Add to dashboard Cite

The potential energy of molecular species and their conformers can be computed with a wide range of computational chemistry methods, from molecular mechanics to ab initio quantum chemistry. However, the proper choice of the computational approach based on computational cost and reliability of calculated energies is a dilemma, especially for large molecules. This dilemma is proved to be even more problematic for studies that require hundreds and thousands of calculations, such as drug discovery. On the other hand, driven by their pattern recognition capabilities, neural networks started to gain popularity in the computational chemistry community. During the last decade, many neural network potentials have been developed to predict a variety of chemical information of different systems. Neural network potentials are proved to predict chemical properties with accuracy comparable to quantum mechanical approaches but with the cost approaching molecular mechanics calculations. As a result, the development of more reliable, transferable, and extensible neural network potentials became an attractive field of study for researchers. In this review, we outlined an overview of the status of current neural network potentials and strategies to improve their accuracy. We provide recent examples of studies that prove the applicability of these potentials. We also discuss the capabilities and shortcomings of the current models and the challenges and future aspects of their development and applications. It is expected that this review would provide guidance for the development of neural network potentials and the exploitation of their applicability. This article is categorized under: Data Science > Artificial Intelligence/Machine Learning Molecular and Statistical Mechanics > Molecular Interactions Software > Molecular Modeling

show abstract

Benchmarking Force Field and the ANI Neural Network Potentials for the Torsional Potential Energy Surface of Biaryl Drug Fragments

Cited by 27 publications

References 57 publications

Capturing non-local through-bond effects in molecular mechanics force fields I: Fragmenting molecules for quantum chemical torsion scans [Article v1.1]

Capturing non-local through-bond effects in molecular mechanics force fields I: Fragmenting molecules for quantum chemical torsion scans [Article v1.1]

NNP/MM: Fast molecular dynamics simulations with machine learning potentials and molecular mechanics

Learning molecular potentials with neural networks

Contact Info

Product

Resources

About