High-Precision Atomic Charge Prediction for Protein Systems Using Fragment Molecular Orbital Calculation and Machine Learning

Kato, Koichiro; Masuda, Takuya; Watanabe, Chiduru; Miyagawa, Naoki; Mizouchi, Hideo; Nagase, Shumpei; Kamisaka, Kikuko; Oshima, Kazuteru; Ono, Satoshi; Ueda, Hiroshi; Tokuhisa, Atsushi; Kanada, Ryo; Ohta, Masateru; Ikeguchi, Mitsunori; Okuno, Yasushi; Fukuzawa, Kaori; Honma, Teruki

doi:10.1021/acs.jcim.0c00273

Cited by 22 publications

(22 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is an ongoing effort to develop force fields using quantum‐mechanical calculations to determine parameters, 78,79 including polarizable force fields 53,54,56,55,56 . Machine learning can be employed to facilitate the process 80 . The analysis in this work may be useful for providing data for such studies.…”

Section: Discussionmentioning

confidence: 99%

“…53,54,56,55,56 Machine learning can be employed to facilitate the process. 80 The analysis in this work may be useful for providing data for such studies. In future one could combine the developed methodology with various extensions of tight-binding theories, 81 including the use of multipoles for the embedding, 82 extended basis sets, 83 and long-range corrected DFTB.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Polarization energies in the fragment molecular orbital method

Fedorov

2022

J Comput Chem

View full text Add to dashboard Cite

Using isolated and polarized states of fragments, a method for computing the polarization energies in density functional theory (DFT) and density‐functional tight‐binding (DFTB) is developed in the framework of the fragment molecular orbital method. For DFTB, the method is extended into the use of periodic boundary conditions (PBC), for which a new component, a periodic self‐polarization energy, is derived. The couplings of the polarization to other components in the pair interaction energy analysis (PIEDA) are derived for DFT and DFTB, and compared to Hartree–Fock and second‐order Møller‐Plesset perturbation theory (MP2). The effect of the self‐consistent (DFT) and perturbative (MP2) treatment of the electron correlation on the polarization is discussed. The difference in the polarization in the bulk (PBC) and micro (cluster) solvation is elucidated.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Polarization energies in the fragment molecular orbital method

Fedorov

2022

J Comput Chem

View full text Add to dashboard Cite

show abstract

“…Kato et al [175] constructed ML models to predict accurate charges for three proteins based on fragment molecular orbital (FMO) calculations. Commonly used force fields use fixed atomic charges and therefore neglect electronic polarization.…”

Section: Spectroscopic Techniques For Structure Characterizationmentioning

confidence: 99%

“…Another challenge is data scarcity due to the high computational cost of the QM reference calculations, especially in the case of unstructured systems that cannot be easily described by simplified models, such as proteins in solution. A partial solution already used in several of the discussed applications is to employ fragmentation approaches in which large molecules are divided into smaller fragments for which QM calculations are more feasible [168,175,223]. Transfer learning techniques can also be used to reduce the number of reference calculations, for example by training a model to a more efficient lower-level method first before re-training on a smaller data set obtained from a more expensive higher-level method [224].…”

Section: Remaining Challenges and Outlookmentioning

confidence: 99%

Machine learning-accelerated quantum mechanics-based atomistic simulations for industrial applications

Morawietz

Artrith

2020

J Comput Aided Mol Des

View full text Add to dashboard Cite

Atomistic simulations have become an invaluable tool for industrial applications ranging from the optimization of protein-ligand interactions for drug discovery to the design of new materials for energy applications. Here we review recent advances in the use of machine learning (ML) methods for accelerated simulations based on a quantum mechanical (QM) description of the system. We show how recent progress in ML methods has dramatically extended the applicability range of conventional QM-based simulations, allowing to calculate industrially relevant properties with enhanced accuracy, at reduced computational cost, and for length and time scales that would have otherwise not been accessible. We illustrate the benefits of ML-accelerated atomistic simulations for industrial R&D processes by showcasing relevant applications from two very different areas, drug discovery (pharmaceuticals) and energy materials. Writing from the perspective of both a molecular and a materials modeling scientist, this review aims to provide a unified picture of the impact of ML-accelerated atomistic simulations on the pharmaceutical, chemical, and materials industries and gives an outlook on the exciting opportunities that could emerge in the future.

show abstract

“…In addition, as a method for verifying the relevance of parameters, a comparison of the respective 3 J coupling constants obtained from nuclear magnetic resonance (NMR) experiments and MD calculations was performed [16]. Furthermore, in recent years, machine learning methods have also been used for parameter fitting [19][20][21].…”

Section: Introductionmentioning

confidence: 99%

Improvement of the Force Field for β-d-Glucose with Machine Learning

Ikejo

Watanabe²,

Shimamura

et al. 2021

Molecules

View full text Add to dashboard Cite

While the construction of a dependable force field for performing classical molecular dynamics (MD) simulation is crucial for elucidating the structure and function of biomolecular systems, the attempts to do this for glycans are relatively sparse compared to those for proteins and nucleic acids. Currently, the use of GLYCAM06 force field is the most popular, but there have been a number of concerns about its accuracy in the systematic description of structural changes. In the present work, we focus on the improvement of the GLYCAM06 force field for β-d-glucose, a simple and the most abundant monosaccharide molecule, with the aid of machine learning techniques implemented with the TensorFlow library. Following the pre-sampling over a wide range of configuration space generated by MD simulation, the atomic charge and dihedral angle parameters in the GLYCAM06 force field were re-optimized to accurately reproduce the relative energies of β-d-glucose obtained by the density functional theory (DFT) calculations according to the structural changes. The validation for the newly proposed force-field parameters was then carried out by verifying that the relative energy errors compared to the DFT value were significantly reduced and that some inconsistencies with experimental (e.g., NMR) results observed in the GLYCAM06 force field were resolved relevantly.

show abstract

High-Precision Atomic Charge Prediction for Protein Systems Using Fragment Molecular Orbital Calculation and Machine Learning

Cited by 22 publications

References 31 publications

Polarization energies in the fragment molecular orbital method

Polarization energies in the fragment molecular orbital method

Machine learning-accelerated quantum mechanics-based atomistic simulations for industrial applications

Improvement of the Force Field for β-d-Glucose with Machine Learning

Contact Info

Product

Resources

About