In-layer inhomogeneity of molecular dynamics in quasi-liquid layers of ice.

Quasi-liquid layers (QLLs) are present on the surface of ice and play a significant role in its distinctive chemical and physical properties. These layers exhibit considerable heterogeneity across different scales ranging from nanometers to millimeters. Although the formation of partially ice-like structures has been proposed, the molecular-level understanding of this heterogeneity remains unclear. Here, we examined the heterogeneity of molecular dynamics on QLLs based on molecular dynamics simulations and machine learning analysis of the simulation data. We demonstrated that the molecular dynamics of QLLs do not comprise a mixture of solid- and liquid water molecules. Rather, molecules having similar behaviors form dynamical domains that are associated with the dynamical heterogeneity of supercooled water. Nonetheless, molecules in the domains frequently switch their dynamical state. Furthermore, while there is no observable characteristic domain size, the long-range ordering strongly depends on the temperature and crystal face. Instead of a mixture of static solid- and liquid-like regions, our results indicate the presence of heterogeneous molecular dynamics in QLLs, which offers molecular-level insights into the surface properties of ice.

Graph-Neural-Network-Based Unsupervised Learning of the Temporal Similarity of Structural Features Observed in Molecular Dynamics Simulations.

Classification of molecular structures is a crucial step in molecular dynamics (MD) simulations to detect various structures and phases within systems. Molecular structures, which are commonly identified using order parameters, were recently identified using machine learning (ML), that is, the ML models acquire structural features using labeled crystals or phases via supervised learning. However, these approaches may not identify unlabeled or unknown structures, such as the imperfect crystal structures observed in nonequilibrium systems and interfaces. In this study, we proposed the use of a novel unsupervised learning framework, denoted temporal self-supervised learning (TSSL), to learn structural features and design their parameters. In TSSL, the ML models learn that the structural similarity is learned via contrastive learning based on minor short-term variations caused by perturbations in MD simulations. This learning framework is applied to a sophisticated architecture of graph neural network models that use bond angle and length data of the neighboring atoms. TSSL successfully classifies water and ice crystals based on high local ordering, and furthermore, it detects imperfect structures typical of interfaces such as the water-ice and ice-vapor interfaces.

Unsupervised deep learning for molecular dynamics simulations: a novel analysis of protein-ligand interactions in SARS-CoV-2 Mpro.

Molecular dynamics (MD) simulations, which are central to drug discovery, offer detailed insights into protein-ligand interactions. However, analyzing large MD datasets remains a challenge. Current machine-learning solutions are predominantly supervised and have data labelling and standardisation issues. In this study, we adopted an unsupervised deep-learning framework, previously benchmarked for rigid proteins, to study the more flexible SARS-CoV-2 main protease (Mpro). We ran MD simulations of Mpro with various ligands and refined the data by focusing on binding-site residues and time frames in stable protein conformations. The optimal descriptor chosen was the distance between the residues and the center of the binding pocket. Using this approach, a local dynamic ensemble was generated and fed into our neural network to compute Wasserstein distances across system pairs, revealing ligand-induced conformational differences in Mpro. Dimensionality reduction yielded an embedding map that correlated ligand-induced dynamics and binding affinity. Notably, the high-affinity compounds showed pronounced effects on the protein's conformations. We also identified the key residues that contributed to these differences. Our findings emphasize the potential of combining unsupervised deep learning with MD simulations to extract valuable information and accelerate drug discovery.

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

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 low-shear-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.

Differences in ligand-induced protein dynamics extracted from an unsupervised deep learning approach correlate with protein-ligand binding affinities.

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 ligand binding. However, the relationship between protein dynamics and binding affinity remains unclear. Here, we propose a method that represents ligand-binding-induced protein behavioral change 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 strongly correlates 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 binding dynamics-based drug discovery.