Detection of molecular behavior that characterizes systems using a deep learning approach

Endo, Katsuhiro; Yuhara, Daisuke; Tomobe, Katsufumi; Yasuoka, Kenji

doi:10.1039/c9nr00219g

Cited by 9 publications

(24 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To grasp the features of protein dynamics from MD simulation data within a moderate data size for the DNN, the concept of LDE [28] was employed. LDE should have an appropriate selection of particles and time length to contain important dynamics of interest.…”

Section: Determination Of Lde Of Protein-ligand Systemsmentioning

confidence: 99%

“…The architecture of the DNN is almost identical to that of the previous study by Endo et. al [28], except for two changes. First, the input size was changed to n × 64 × d, where n and d are the number of amino acids in the LDE and dimension, respectively.…”

Section: Selection Of the Ldementioning

confidence: 99%

“…A function g(x i ) [28] represents the contribution of one trajectory fraction to the overall differences between two systems. The definition for a LDE trajectory of system i with the referenced system j is expressed as…”

Section: A Function G(x)mentioning

confidence: 99%

“…Although these methods could identify ligand-induced dynamics changes in proteins, integration of the information and representation of the dynamics with a few variable is still challenging, consequently making it difficult to directly link the dynamics properties with ligand affinity. In this study, we propose a novel method to predict binding energies from proteins' dynamics change upon ligand binding, based on a deep learning approach for MD data analysis [28]. In contrast to general approaches for MD trajectory-based supervised machine learning [29,30], our method uses raw MD trajectories of a ligand binding site with different kinds of ligands, and quantitatively measures differences in the dynamics using unsupervised learning.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Ligand-induced protein dynamics differences correlate with protein-ligand binding affinities: An unsupervised deep learning approach

Yasuda,

Endo,

Yamamoto

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Prediction of protein-ligand binding affinity is a major goal in drug discovery. Generally, free energy gap is calculated between two states (e.g., ligand binding and unbinding). The energy gap implicitly includes the effects of changes in protein dynamics induced by the binding ligand. However, the relationship between protein dynamics and binding affinity remains unclear. Here, we propose a novel method that represents protein behavioral change upon ligand binding with a simple feature that can be used to predict protein-ligand affinity. From unbiased molecular simulation data, an unsupervised deep learning method measures the differences in protein dynamics at a ligand-binding site depending on the bound ligands. A dimension-reduction method extracts a dynamic feature that is strongly correlated to the binding affinities. Moreover, the residues that play important roles in protein-ligand interactions are specified based on their contribution to the differences. These results indicate the potential for dynamics-based drug discovery.

show abstract

Section: Determination Of Lde Of Protein-ligand Systemsmentioning

confidence: 99%

Section: Selection Of the Ldementioning

confidence: 99%

Section: A Function G(x)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Ligand-induced protein dynamics differences correlate with protein-ligand binding affinities: An unsupervised deep learning approach

Yasuda,

Endo,

Yamamoto

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the past few years, many studies have reported the use of machine learning for the analysis and calculation of MD trajectories (8). The construction of a force field model with machine learning (9)(10)(11)(12)(13)(14)(15), the estimation of the free energy surface (16,17), and the detection of specific molecular behavior (18) are useful methods to improve the accuracy of MD simulations and the efficiency of MD trajectory analysis. A major issue increasing the computation cost of MD simulations is the presence of a complex energy plane geometry that has multiple highenergy barriers.…”

Section: Introductionmentioning

confidence: 99%

MD-GAN with multi-particle input: the machine learning of long-time molecular behavior from short-time MD data

Kawada¹,

Endo²,

Yuhara³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

MD-GAN is a machine learning-based method that can evolve part of the system at any time step, accelerating the generation of molecular dynamics data.For the accurate prediction of MD-GAN, sufficient information on the dynamics of a part of the system should be included with the training data. Therefore, the selection of the part of the system is important for efficient learning. In a previous study, only one particle (or vector) of each molecule was extracted as part of the system. Therefore, we investigated the effectiveness of adding information from other particles to the learning process. In the experiment of the polyethylene system, when the dynamics of three particles of each molecule were used, the diffusion was successfully predicted using one-third of the time length of the training data, compared to the single-particle input. Surprisingly, the unobserved transition of diffusion in the training data was also predicted using this method.

show abstract

Combining Molecular Dynamics and Machine Learning to Analyze Shear Thinning for Alkane and Globular Lubricants in the Low Shear Regime

Yasuda

Kobayashi

Endo

et al. 2023

ACS Appl. Mater. Interfaces

Self Cite

View full text Add to dashboard Cite

Lubricants with desirable frictional properties are important in achieving an energy-saving society. Lubricants at the interfaces of mechanical components are confined under high shear rates and pressures and behave quite differently from the bulk material. Computational approaches such as nonequilibrium molecular dynamics (NEMD) simulations have been performed to probe the molecular behavior of lubricants. However, the lowshear-velocity regions of the materials have rarely been simulated owing to the expensive calculations necessary to do so, and the molecular dynamics under shear velocities comparable with that in the experiments are not clearly understood. In this study, we performed NEMD simulations of extremely confined lubricants, i.e., two molecular layers for four types of lubricants confined in mica walls, under shear velocities from 0.001 to 1 m/s. While we confirmed shear thinning, the velocity profiles could not show the flow behavior when the shear velocity was much slower than thermal fluctuations. Therefore, we used an unsupervised machine learning approach to detect molecular movements that contribute to shear thinning. First, we extracted the simple features of molecular movements from large amounts of MD data, which were found to correlate with the effective viscosity. Subsequently, the extracted features were interpreted by examining the trajectories contributing to these features. The magnitude of diffusion corresponded to the viscosity, and the location of slips that varied depending on the spherical and chain lubricants was irrelevant. Finally, we attempted to apply a modified Stokes−Einstein relation at equilibrium to the nonequilibrium and confined systems. While systems with low shear rates obeyed the relation sufficiently, large deviations were observed under large shear rates.

show abstract

Detection of molecular behavior that characterizes systems using a deep learning approach

Abstract: Deep learning approach is applied to detect the representative molecular behavior from the enormous and complex molecular dynamics data.

Cited by 9 publications

References 21 publications

Ligand-induced protein dynamics differences correlate with protein-ligand binding affinities: An unsupervised deep learning approach

Ligand-induced protein dynamics differences correlate with protein-ligand binding affinities: An unsupervised deep learning approach

MD-GAN with multi-particle input: the machine learning of long-time molecular behavior from short-time MD data

Combining Molecular Dynamics and Machine Learning to Analyze Shear Thinning for Alkane and Globular Lubricants in the Low Shear Regime

Contact Info

Product

Resources

About