Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials

Self-assembly prediction of architecture-controlled bottlebrush copolymers in solution using graph convolutional networks

The investigation of bottlebrush copolymer self-assembly in solution involves a comprehensive approach integrating simulation and experimental research, due to their unique physical characteristics. However, the intricate architecture of bottlebrush copolymers and the diverse solvent conditions introduce a wide range of parameter spaces. In this study, we investigated the solution self-assembly behavior of bottlebrush copolymers by combining dissipative particle dynamics (DPD) simulation results and machine learning (ML) including graph convolutional networks (GCNs). The architecture of bottlebrush copolymers is encoded by graphs including connectivity, side chain length, bead types, and interaction parameters of DPD simulation. Using GCN, we accurately predicted the single chain properties of bottlebrush copolymers with over 95% accuracy. Furthermore, phase behavior was precisely predicted using these single chain properties. Shapley additive explanations (SHAP) values of single chain properties to the various self-assembly morphologies were calculated to investigate the correlation between single chain properties and morphologies. In addition, we analyzed single chain properties and phase behavior as a function of DPD interaction parameters, extracting relevant physical properties for vesicle morphology formation. This work paves the way for tailored design in solution of self-assembled nanostructures of bottlebrush copolymers, offering a GCN framework for precise prediction of self-assembly morphologies under various chain architectures and solvent conditions.

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.

Gel polymer electrolytes for rechargeable batteries toward wide-temperature applications

Rechargeable batteries, typically represented by lithium-ion batteries, have taken a huge leap in energy density over the last two decades. However, they still face material/chemical challenges in ensuring safety and long service life at temperatures beyond the optimum range, primarily due to the chemical/electrochemical instabilities of conventional liquid electrolytes against aggressive electrode reactions and temperature variation. In this regard, a gel polymer electrolyte (GPE) with its liquid components immobilized and stabilized by a solid matrix, capable of retaining almost all the advantageous natures of the liquid electrolytes and circumventing the interfacial issues that exist in the all-solid-state electrolytes, is of great significance to realize rechargeable batteries with extended working temperature range. We begin this review with the main challenges faced in the development of GPEs, based on extensive literature research and our practical experience. Then, a significant section is dedicated to the requirements and design principles of GPEs for wide-temperature applications, with special attention paid to the feasibility, cost, and environmental impact. Next, the research progress of GPEs is thoroughly reviewed according to the strategies applied. In the end, we outline some prospects of GPEs related to innovations in material sciences, advanced characterizations, artificial intelligence, and environmental impact analysis, hoping to spark new research activities that ultimately bring us a step closer to realizing wide-temperature rechargeable batteries.

Computational chemistry for water-splitting electrocatalysis

Electrocatalytic water splitting driven by renewable electricity has attracted great interest in recent years for producing hydrogen with high-purity. However, the practical applications of this technology are limited by the development of electrocatalysts with high activity, low cost, and long durability. In the search for new electrocatalysts, computational chemistry has made outstanding contributions by providing fundamental laws that govern the electron behavior and enabling predictions of electrocatalyst performance. This review delves into theoretical studies on electrochemical water-splitting processes. Firstly, we introduce the fundamentals of electrochemical water electrolysis and subsequently discuss the current advancements in computational methods and models for electrocatalytic water splitting. Additionally, a comprehensive overview of benchmark descriptors is provided to aid in understanding intrinsic catalytic performance for water-splitting electrocatalysts. Finally, we critically evaluate the remaining challenges within this field.

Mixtures Recomposition by Neural Nets: A Multidisciplinary Overview

Artificial Neural Networks (ANNs) are transforming how we understand chemical mixtures, providing an expressive view of the chemical space and multiscale processes. Their hybridization with physical knowledge can bridge the gap between predictivity and understanding of the underlying processes. This overview explores recent progress in ANNs, particularly their potential in the 'recomposition' of chemical mixtures. Graph-based representations reveal patterns among mixture components, and deep learning models excel in capturing complexity and symmetries when compared to traditional Quantitative Structure-Property Relationship models. Key components, such as Hamiltonian networks and convolution operations, play a central role in representing multiscale mixtures. The integration of ANNs with Chemical Reaction Networks and Physics-Informed Neural Networks for inverse chemical kinetic problems is also examined. The combination of sensors with ANNs shows promise in optical and biomimetic applications. A common ground is identified in the context of statistical physics, where ANN-based methods iteratively adapt their models by blending their initial states with training data. The concept of mixture recomposition unveils a reciprocal inspiration between ANNs and reactive mixtures, highlighting learning behaviors influenced by the training environment.

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.

Elucidating Interfacial Dynamics of Ti-Al Systems Using Molecular Dynamics Simulation and Markov State Modeling

Due to their remarkable mechanical and chemical properties, Ti-Al-based materials are attracting considerable interest in numerous fields of engineering, such as automotive, aerospace, and defense. With their low density, high strength, and resistance to corrosion and oxidation, these intermetallic alloys and metal-compound composites have found diverse applications. However, additive manufacturing and heat treatment of Ti-Al alloys frequently lead to brittleness and severe formation of defects. The present study delves into the interfacial dynamics of these Ti-Al systems, particularly focusing on the behavior of Ti and Al atoms in the presence of TiAl3 grain boundaries under experimental heat treatment conditions. Using a combination of molecular dynamics and Markov state modeling, we scrutinize the kinetic processes involved in the formation of TiAl3. The molecular dynamics simulation indicates that at the early stage of heat treatment, the predominating process is the diffusion of Al atoms toward the Ti surface through the TiAl3 grain boundaries. Markov state modeling identifies three distinct dynamic states of Al atoms within the Ti/Al mixture that forms during the process, each exhibiting a unique spatial distribution. Using transition time scales as a qualitative measure of the rapidness of the dynamics, it is observed that the Al dynamics is significantly less rapid near the Ti surface compared to the Al surface. Put together, the results offer a comprehensive understanding of the interfacial dynamics and reveal a three-stage diffusion mechanism. The process initiates with the premelting of Al, proceeds with the prevalent diffusion of Al atoms toward the Ti surface, and eventually ceases as the Ti concentration within the mixture progressively increases. The insights gained from this study could contribute significantly to the control and optimization of manufacturing processes for these high-performing Ti-Al-based materials.

Zero-shot learning of aerosol optical properties with graph neural networks

Black carbon (BC), a strongly absorbing aerosol sourced from combustion, is an important short-lived climate forcer. BC's complex morphology contributes to uncertainty in its direct climate radiative effects, as current methods to accurately calculate the optical properties of these aerosols are too computationally expensive to be used online in models or for observational retrievals. Here we demonstrate that a Graph Neural Network (GNN) trained to predict the optical properties of numerically-generated BC fractal aggregates can accurately generalize to arbitrarily shaped particles, including much larger ([Formula: see text]) aggregates than in the training dataset. This zero-shot learning approach could be used to estimate single particle optical properties of realistically-shaped aerosol and cloud particles for inclusion in radiative transfer codes for atmospheric models and remote sensing inversions. In addition, GNN's can be used to gain physical intuition on the relationship between small-scale interactions (here of the spheres' positions and interactions) and large-scale properties (here of the radiative properties of aerosols).

GraphVAMPnets for uncovering slow collective variables of self-assembly dynamics

Uncovering slow collective variables (CVs) of self-assembly dynamics is important to elucidate its numerous kinetic assembly pathways and drive the design of novel structures for advanced materials through the bottom-up approach. However, identifying the CVs for self-assembly presents several challenges. First, self-assembly systems often consist of identical monomers, and the feature representations should be invariant to permutations and rotational symmetries. Physical coordinates, such as aggregate size, lack high-resolution detail, while common geometric coordinates like pairwise distances are hindered by the permutation and rotational symmetry challenges. Second, self-assembly is usually a downhill process, and the trajectories often suffer from insufficient sampling of backward transitions that correspond to the dissociation of self-assembled structures. Popular dimensionality reduction methods, such as time-structure independent component analysis, impose detailed balance constraints, potentially obscuring the true dynamics of self-assembly. In this work, we employ GraphVAMPnets, which combines graph neural networks with a variational approach for Markovian process (VAMP) theory to identify the slow CVs of the self-assembly processes. First, GraphVAMPnets bears the advantages of graph neural networks, in which the graph embeddings can represent self-assembly structures in high-resolution while being invariant to permutations and rotational symmetries. Second, it is built upon VAMP theory, which studies Markov processes without forcing detailed balance constraints, which addresses the out-of-equilibrium challenge in the self-assembly process. We demonstrate GraphVAMPnets for identifying slow CVs of self-assembly kinetics in two systems: the aggregation of two hydrophobic molecules and the self-assembly of patchy particles. We expect that our GraphVAMPnets can be widely applied to molecular self-assembly.

Learning molecular dynamics: predicting the dynamics of glasses by a machine learning simulator

Many-body dynamics of atoms such as glass dynamics is generally governed by complex (and sometimes unknown) physics laws. This challenges the construction of atom dynamics simulations that both (i) capture the physics laws and (ii) run with little computation cost. Here, based on graph neural network (GNN), we introduce an observation-based graph network (OGN) framework to "bypass all physics laws" to simulate complex glass dynamics solely from their static structure. By taking the example of molecular dynamics (MD) simulations, we successfully apply the OGN to predict atom trajectories evolving up to a few hundred timesteps and ranging over different families of complex atomistic systems, which implies that the atom dynamics is largely encoded in their static structure in disordered phases and, furthermore, allows us to explore the capacity of OGN simulations that is potentially generic to many-body dynamics. Importantly, unlike traditional numerical simulations, the OGN simulations bypass the numerical constraint of small integration timestep by a multiplier of ≥5 to conserve energy and momentum until hundreds of timesteps, thus leapfrogging the execution speed of MD simulations for a modest timescale.

Sparse identification of Lagrangian for nonlinear dynamical systems via proximal gradient method

The autonomous distillation of physical laws only from data is of great interest in many scientific fields. Data-driven modeling frameworks that adopt sparse regression techniques, such as sparse identification of nonlinear dynamics (SINDy) and its modifications, are developed to resolve difficulties in extracting underlying dynamics from experimental data. However, SINDy faces certain difficulties when the dynamics contain rational functions. The Lagrangian is substantially more concise than the actual equations of motion, especially for complex systems, and it does not usually contain rational functions for mechanical systems. Few proposed methods proposed to date, such as Lagrangian-SINDy we have proposed recently, can extract the true form of the Lagrangian of dynamical systems from data; however, these methods are easily affected by noise as a fact. In this study, we developed an extended version of Lagrangian-SINDy (xL-SINDy) to obtain the Lagrangian of dynamical systems from noisy measurement data. We incorporated the concept of SINDy and used the proximal gradient method to obtain sparse Lagrangian expressions. Further, we demonstrated the effectiveness of xL-SINDy against different noise levels using four mechanical systems. In addition, we compared its performance with SINDy-PI (parallel, implicit) which is a latest robust variant of SINDy that can handle implicit dynamics and rational nonlinearities. The experimental results reveal that xL-SINDy is much more robust than the existing methods for extracting the governing equations of nonlinear mechanical systems from data with noise. We believe this contribution is significant toward noise-tolerant computational method for explicit dynamics law extraction from data.

Accelerating Density Functional Calculation of Adatom Adsorption on Graphene via Machine Learning

Graphene has attracted significant interest due to its unique properties. Herein, we built an adsorption structure selection workflow based on a density functional theory (DFT) calculation and machine learning to provide a guide for the interfacial properties of graphene. There are two main parts in our workflow. One main part is a DFT calculation routine to generate a dataset automatically. This part includes adatom random selection, modeling adsorption structures automatically, and a calculation of adsorption properties. It provides the dataset for the second main part in our workflow, which is a machine learning model. The inputs are atomic characteristics selected by feature engineering, and the network features are optimized by a genetic algorithm. The mean percentage error of our model was below 35%. Our routine is a general DFT calculation accelerating routine, which could be applied to many other problems. An attempt on graphene/magnesium composites design was carried out. Our predicting results match well with the interfacial properties calculated by DFT. This indicated that our routine presents an option for quick-design graphene-reinforced metal matrix composites.

Chemistry-Informed Machine Learning for Polymer Electrolyte Discovery

Solid polymer electrolytes (SPEs) have the potential to improve lithium-ion batteries by enhancing safety and enabling higher energy densities. However, SPEs suffer from significantly lower ionic conductivity than liquid and solid ceramic electrolytes, limiting their adoption in functional batteries. To facilitate more rapid discovery of high ionic conductivity SPEs, we developed a chemistry-informed machine learning model that accurately predicts ionic conductivity of SPEs. The model was trained on SPE ionic conductivity data from hundreds of experimental publications. Our chemistry-informed model encodes the Arrhenius equation, which describes temperature activated processes, into the readout layer of a state-of-the-art message passing neural network and has significantly improved accuracy over models that do not encode temperature dependence. Chemically informed readout layers are compatible with deep learning for other property prediction tasks and are especially useful where limited training data are available. Using the trained model, ionic conductivity values were predicted for several thousand candidate SPE formulations, allowing us to identify promising candidate SPEs. We also generated predictions for several different anions in poly(ethylene oxide) and poly(trimethylene carbonate), demonstrating the utility of our model in identifying descriptors for SPE ionic conductivity.

Exploring glassy dynamics with Markov state models from graph dynamical neural networks

Using machine learning techniques, we introduce a Markov state model (MSM) for a model glass former that reveals structural heterogeneities and their slow dynamics by coarse-graining the molecular dynamics into a low-dimensional feature space. The transition timescale between states is larger than the conventional structural relaxation time τ_{α}, but can be obtained from trajectories much shorter than τ_{α}. The learned map of states assigned to the particles corresponds to local excess Voronoi volume. These results resonate with classic free volume theories of the glass transition, singling out local packing fluctuations as one of the dominant slowly relaxing features.

Machine Learning for Electrocatalyst and Photocatalyst Design and Discovery

Electrocatalysts and photocatalysts are key to a sustainable future, generating clean fuels, reducing the impact of global warming, and providing solutions to environmental pollution. Improved processes for catalyst design and a better understanding of electro/photocatalytic processes are essential for improving catalyst effectiveness. Recent advances in data science and artificial intelligence have great potential to accelerate electrocatalysis and photocatalysis research, particularly the rapid exploration of large materials chemistry spaces through machine learning. Here a comprehensive introduction to, and critical review of, machine learning techniques used in electrocatalysis and photocatalysis research are provided. Sources of electro/photocatalyst data and current approaches to representing these materials by mathematical features are described, the most commonly used machine learning methods summarized, and the quality and utility of electro/photocatalyst models evaluated. Illustrations of how machine learning models are applied to novel electro/photocatalyst discovery and used to elucidate electrocatalytic or photocatalytic reaction mechanisms are provided. The review offers a guide for materials scientists on the selection of machine learning methods for electrocatalysis and photocatalysis research. The application of machine learning to catalysis science represents a paradigm shift in the way advanced, next-generation catalysts will be designed and synthesized.

Understanding Metal-Organic Framework Nucleation from a Solution with Evolving Graphs

A mechanistic understanding of metal-organic framework (MOF) synthesis and scale-up remains underexplored due to the complex nature of the interactions of their building blocks. In this work, we investigate the collective assembly of building units at the early stages of MOF nucleation, using MIL-101(Cr) as a prototypical example. Using large-scale molecular dynamics simulations, we observe that the choice of solvent (water and N,N-dimethylformamide), the introduction of ions (Na⁺ and F^-) and the relative populations of MIL-101(Cr) half-secondary building unit (half-SBU) isomers have a strong influence on the cluster formation process. Additionally, the shape, size, nucleation and growth rates, crystallinity, and short and long-range order largely vary depending on the synthesis conditions. We evaluate these properties as they naturally emerge when interpreting the self-assembly of MOF nuclei as the time evolution of an undirected graph. Solution-induced conformational complexity and ionic concentration have a dramatic effect on the morphology of clusters emerging during assembly. While pure solvents lead to the rapid formation of a small number of large clusters, the presence of ions in aqueous solutions results in smaller clusters and slower nucleation. This diversity is captured by the key features of the graph representation. Principle component analysis on graph properties reveals that only a small number of molecular descriptors is needed to deconvolute MOF self-assembly. Descriptors such as the average coordination number between half-SBUs and fractal dimension are of particulalr interest as they can be can be followed experimentally by techniques like by time-resolved spectroscopy. Ultimately, graph theory emerges as an approach that can be used to understand complex processes revealing molecular descriptors accessible by both simulation and experiment.

Expanding the active charge carriers of polymer electrolytes in lithium-based batteries using an anion-hosting cathode

Ionic-conductive polymers are appealing electrolyte materials for solid-state lithium-based batteries. However, these polymers are detrimentally affected by the electrochemically-inactive anion migration that limits the ionic conductivity and accelerates cell failure. To circumvent this issue, we propose the use of polyvinyl ferrocene (PVF) as positive electrode active material. The PVF acts as an anion-acceptor during redox processes, thus simultaneously setting anions and lithium ions as effective charge carriers. We report the testing of various Li||PVF lab-scale cells using polyethylene oxide (PEO) matrix and Li-containing salts with different anions. Interestingly, the cells using the PEO-lithium bis(trifluoromethanesulfonyl)imide (LiTFSI) solid electrolyte deliver an initial capacity of 108 mAh g⁻¹ at 100 μA cm⁻² and 60 °C, and a discharge capacity retention of 70% (i.e., 70 mAh g⁻¹) after 2800 cycles at 300 μA cm⁻² and 60 °C. The Li|PEO-LiTFSI|PVF cells tested at 50 μA cm⁻² and 30 °C can also deliver an initial discharge capacity of around 98 mAh g⁻¹ with an electrolyte ionic conductivity in the order of 10⁻⁵S cm⁻¹.

The energy content of secondary batteries is often limited by the charge carriers available in the system. Here, the authors employed an anion acceptor cathode for simultaneous use of electrolyte anions and cations as effective charge carriers in solid polymer electrolytes for lithium-based batteries.

GraphVAMPNet, using graph neural networks and variational approach to Markov processes for dynamical modeling of biomolecules

Finding low dimensional representation of data from long-timescale trajectories of biomolecular processes such as protein-folding or ligand-receptor binding is of fundamental importance and kinetic models such as Markov modeling have proven useful in describing the kinetics of these systems. Recently, an unsupervised machine learning technique called VAMPNet was introduced to learn the low dimensional representation and linear dynamical model in an end-to-end manner. VAMPNet is based on variational approach to Markov processes (VAMP) and relies on neural networks to learn the coarse-grained dynamics. In this contribution, we combine VAMPNet and graph neural networks to generate an end-to-end framework to efficiently learn high-level dynamics and metastable states from the long-timescale molecular dynamics trajectories. This method bears the advantages of graph representation learning and uses graph message passing operations to generate an embedding for each datapoint which is used in the VAMPNet to generate a coarse-grained representation. This type of molecular representation results in a higher resolution and more interpretable Markov model than the standard VAMPNet enabling a more detailed kinetic study of the biomolecular processes. Our GraphVAMPNet approach is also enhanced with an attention mechanism to find the important residues for classification into different metastable states.

Global structural stability and the role of cooperation in mutualistic systems

Dynamical systems on graphs allow to describe multiple phenomena from different areas of Science. In particular, many complex systems in Ecology are studied by this approach. In this paper we analize the mathematical framework for the study of the structural stability of each stationary point, feasible or not, introducing a generalization for this concept, defined as Global Structural Stability. This approach would fit with the proper mathematical concept of structural stability, in which we find a full description of the complex dynamics on the phase space due to nonlinear dynamics. This fact can be analyzed as an informational field grounded in a global attractor whose structure can be completely characterized. These attractors are stable under perturbation and suppose the minimal structurally stable sets. We also study in detail, mathematically and computationally, the zones characterizing different levels of biodiversity in bipartite graphs describing mutualistic antagonistic systems of population dynamics. In particular, we investigate the dependence of the region of maximal biodiversity of a system on its connectivity matrix. On the other hand, as the network topology does not completely determine the robustness of the dynamics of a complex network, we study the correlation between structural stability and several graph measures. A systematic study on synthetic and biological graphs is presented, including 10 mutualistic networks of plants and seed-dispersal and 1000 random synthetic networks. We compare the role of centrality measures and modularity, concluding the importance of just cooperation strength among nodes when describing areas of maximal biodiversity. Indeed, we show that cooperation parameters are the central role for biodiversity while other measures act as secondary supporting functions.

Progress in deep Markov state modeling: Coarse graining and experimental data restraints

Recent advances in deep learning frameworks have established valuable tools for analyzing the long-timescale behavior of complex systems, such as proteins. In particular, the inclusion of physical constraints, e.g., time-reversibility, was a crucial step to make the methods applicable to biophysical systems. Furthermore, we advance the method by incorporating experimental observables into the model estimation showing that biases in simulation data can be compensated for. We further develop a new neural network layer in order to build a hierarchical model allowing for different levels of details to be studied. Finally, we propose an attention mechanism, which highlights important residues for the classification into different states. We demonstrate the new methodology on an ultralong molecular dynamics simulation of the Villin headpiece miniprotein.

Crystal graph attention networks for the prediction of stable materials

Graph neural networks for crystal structures typically use the atomic positions and the atomic species as input. Unfortunately, this information is not available when predicting new materials, for which the precise geometrical information is unknown. We circumvent this problem by replacing the precise bond distances with embeddings of graph distances. This allows our networks to be applied directly in high-throughput studies based on both composition and crystal structure prototype without using relaxed structures as input. To train these networks, we curate a dataset of over 2 million density functional calculations of crystals with consistent calculation parameters. We apply the resulting model to the high-throughput search of 15 million tetragonal perovskites of composition ABCD₂. As a result, we identify several thousand potentially stable compounds and demonstrate that transfer learning from the newly curated dataset reduces the required training data by 50%.

Simplified, interpretable graph convolutional neural networks for small molecule activity prediction

We here present a streamlined, explainable graph convolutional neural network (gCNN) architecture for small molecule activity prediction. We first conduct a hyperparameter optimization across nearly 800 protein targets that produces a simplified gCNN QSAR architecture, and we observe that such a model can yield performance improvements over both standard gCNN and RF methods on difficult-to-classify test sets. Additionally, we discuss how reductions in convolutional layer dimensions potentially speak to the “anatomical” needs of gCNNs with respect to radial coarse graining of molecular substructure. We augment this simplified architecture with saliency map technology that highlights molecular substructures relevant to activity, and we perform saliency analysis on nearly 100 data-rich protein targets. We show that resultant substructural clusters are useful visualization tools for understanding substructure-activity relationships. We go on to highlight connections between our models’ saliency predictions and observations made in the medicinal chemistry literature, focusing on four case studies of past lead finding and lead optimization campaigns.

Artificial Intelligence Applied to Battery Research: Hype or Reality?

This is a critical review of artificial intelligence/machine learning (AI/ML) methods applied to battery research. It aims at providing a comprehensive, authoritative, and critical, yet easily understandable, review of general interest to the battery community. It addresses the concepts, approaches, tools, outcomes, and challenges of using AI/ML as an accelerator for the design and optimization of the next generation of batteries—a current hot topic. It intends to create both accessibility of these tools to the chemistry and electrochemical energy sciences communities and completeness in terms of the different battery R&D aspects covered.

ReaxFF-MPNN machine learning potential: a combination of reactive force field and message passing neural networks

Reactive force field (ReaxFF) is a powerful computational tool for exploring material properties. In this work, we proposed an enhanced reactive force field model, which uses message passing neural networks (MPNN) to compute the bond order and bond energies. MPNN are a variation of graph neural networks (GNN), which are derived from graph theory. In MPNN or GNN, molecular structures are treated as a graph and atoms and chemical bonds are represented by nodes and edges. The edge states correspond to the bond order in ReaxFF and are updated by message functions according to the message passing algorithms. The results are very encouraging; the investigation of the potential, such as the potential energy surface, reaction energies and equation of state, are greatly improved by this simple improvement. The new potential model, called reactive force field with message passing neural networks (ReaxFF-MPNN), is provided as an interface in an atomic simulation environment (ASE) with which the original ReaxFF and ReaxFF-MPNN potential models can do MD simulations and geometry optimizations within the ASE. Furthermore, machine learning, based on an active learning algorithm and gradient optimizer, is designed to train the model. We found that the active learning machine not only saves the manual work to collect the training data but is also much more effective than the general optimizer.

Advanced Electron Microscopy of Nanophased Synthetic Polymers and Soft Complexes for Energy and Medicine Applications

After decades of developments, electron microscopy has become a powerful and irreplaceable tool in understanding the ionic, electrical, mechanical, chemical, and other functional performances of next-generation polymers and soft complexes. The recent progress in electron microscopy of nanostructured polymers and soft assemblies is important for applications in many different fields, including, but not limited to, mesoporous and nanoporous materials, absorbents, membranes, solid electrolytes, battery electrodes, ion- and electron-transporting materials, organic semiconductors, soft robotics, optoelectronic devices, biomass, soft magnetic materials, and pharmaceutical drug design. For synthetic polymers and soft complexes, there are four main characteristics that differentiate them from their inorganic or biomacromolecular counterparts in electron microscopy studies: (1) lower contrast, (2) abundance of light elements, (3) polydispersity or nanomorphological variations, and (4) large changes induced by electron beams. Since 2011, the Center for Nanophase Materials Sciences (CNMS) at Oak Ridge National Laboratory has been working with numerous facility users on nanostructured polymer composites, block copolymers, polymer brushes, conjugated molecules, organic-inorganic hybrid nanomaterials, organic-inorganic interfaces, organic crystals, and other soft complexes. This review crystalizes some of the essential challenges, successes, failures, and techniques during the process in the past ten years. It also presents some outlooks and future expectations on the basis of these works at the intersection of electron microscopy, soft matter, and artificial intelligence. Machine learning is expected to automate and facilitate image processing and information extraction of polymer and soft hybrid nanostructures in aspects such as dose-controlled imaging and structure analysis.

The Middle Science: Traversing Scale In Complex Many-Body Systems

A roadmap is developed that integrates simulation methodology and data science methods to target new theories that traverse the multiple length- and time-scale features of many-body phenomena.

Unsupervised Learning Methods for Molecular Simulation Data

Unsupervised learning is becoming an essential tool to analyze the increasingly large amounts of data produced by atomistic and molecular simulations, in material science, solid state physics, biophysics, and biochemistry. In this Review, we provide a comprehensive overview of the methods of unsupervised learning that have been most commonly used to investigate simulation data and indicate likely directions for further developments in the field. In particular, we discuss feature representation of molecular systems and present state-of-the-art algorithms of dimensionality reduction, density estimation, and clustering, and kinetic models. We divide our discussion into self-contained sections, each discussing a specific method. In each section, we briefly touch upon the mathematical and algorithmic foundations of the method, highlight its strengths and limitations, and describe the specific ways in which it has been used-or can be used-to analyze molecular simulation data.

Independent Markov decomposition: Toward modeling kinetics of biomolecular complexes

To advance the mission of in silico cell biology, modeling the interactions of large and complex biological systems becomes increasingly relevant. The combination of molecular dynamics (MD) simulations and Markov state models (MSMs) has enabled the construction of simplified models of molecular kinetics on long timescales. Despite its success, this approach is inherently limited by the size of the molecular system. With increasing size of macromolecular complexes, the number of independent or weakly coupled subsystems increases, and the number of global system states increases exponentially, making the sampling of all distinct global states unfeasible. In this work, we present a technique called independent Markov decomposition (IMD) that leverages weak coupling between subsystems to compute a global kinetic model without requiring the sampling of all combinatorial states of subsystems. We give a theoretical basis for IMD and propose an approach for finding and validating such a decomposition. Using empirical few-state MSMs of ion channel models that are well established in electrophysiology, we demonstrate that IMD models can reproduce experimental conductance measurements with a major reduction in sampling compared with a standard MSM approach. We further show how to find the optimal partition of all-atom protein simulations into weakly coupled subunits.

Exploring the octanol-water partition coefficient dataset using deep learning techniques and data augmentation

Today more and more data are freely available. Based on these big datasets deep neural networks (DNNs) rapidly gain relevance in computational chemistry. Here, we explore the potential of DNNs to predict chemical properties from chemical structures. We have selected the octanol-water partition coefficient (log P) as an example, which plays an essential role in environmental chemistry and toxicology but also in chemical analysis. The predictive performance of the developed DNN is good with an rmse of 0.47 log units in the test dataset and an rmse of 0.33 for an external dataset from the SAMPL6 challenge. To this end, we trained the DNN using data augmentation considering all potential tautomeric forms of the chemicals. We further demonstrate how DNN models can help in the curation of the log P dataset by identifying potential errors, and address limitations of the dataset itself.

Disentangling Rotational Dynamics and Ordering Transitions in a System of Self-Organizing Protein Nanorods via Rotationally Invariant Latent Representations

The dynamics of complex ordering systems with active rotational degrees of freedom exemplified by protein self-assembly is explored using a machine learning workflow that combines deep learning-based semantic segmentation and rotationally invariant variational autoencoder-based analysis of orientation and shape evolution. The latter allows for disentanglement of the particle orientation from other degrees of freedom and compensates for lateral shifts. The disentangled representations in the latent space encode the rich spectrum of local transitions that can now be visualized and explored via continuous variables. The time dependence of ensemble averages allows insight into the time dynamics of the system and, in particular, illustrates the presence of the potential ordering transition. Finally, analysis of the latent variables along the single-particle trajectory allows tracing these parameters on a single-particle level. The proposed approach is expected to be universally applicable for the description of the imaging data in optical, scanning probe, and electron microscopy seeking to understand the dynamics of complex systems where rotations are a significant part of the process.

How Machine Learning Will Revolutionize Electrochemical Sciences

Electrochemical systems function via interconversion of electric charge and chemical species and represent promising technologies for our cleaner, more sustainable future. However, their development time is fundamentally limited by our ability to identify new materials and understand their electrochemical response. To shorten this time frame, we need to switch from the trial-and-error approach of finding useful materials to a more selective process by leveraging model predictions. Machine learning (ML) offers data-driven predictions and can be helpful. Herein we ask if ML can revolutionize the development cycle from decades to a few years. We outline the necessary characteristics of such ML implementations. Instead of enumerating various ML algorithms, we discuss scientific questions about the electrochemical systems to which ML can contribute.

Deep potential generation scheme and simulation protocol for the Li10GeP2S12-type superionic conductors

Solid-state electrolyte materials with superior lithium ionic conductivities are vital to the next-generation Li-ion batteries. Molecular dynamics could provide atomic scale information to understand the diffusion process of Li-ion in these superionic conductor materials. Here, we implement the deep potential generator to set up an efficient protocol to automatically generate interatomic potentials for Li₁₀GeP₂S₁₂-type solid-state electrolyte materials (Li₁₀GeP₂S₁₂, Li₁₀SiP₂S₁₂, and Li₁₀SnP₂S₁₂). The reliability and accuracy of the fast interatomic potentials are validated. With the potentials, we extend the simulation of the diffusion process to a wide temperature range (300 K-1000 K) and systems with large size (∼1000 atoms). Important technical aspects such as the statistical error and size effect are carefully investigated, and benchmark tests including the effect of density functional, thermal expansion, and configurational disorder are performed. The computed data that consider these factors agree well with the experimental results, and we find that the three structures show different behaviors with respect to configurational disorder. Our work paves the way for further research on computation screening of solid-state electrolyte materials.

Computational design of enzymes for biotechnological applications

Enzymes are the natural catalysts that execute biochemical reactions upholding life. Their natural effectiveness has been fine-tuned as a result of millions of years of natural evolution. Such catalytic effectiveness has prompted the use of biocatalysts from multiple sources on different applications, including the industrial production of goods (food and beverages, detergents, textile, and pharmaceutics), environmental protection, and biomedical applications. Natural enzymes often need to be improved by protein engineering to optimize their function in non-native environments. Recent technological advances have greatly facilitated this process by providing the experimental approaches of directed evolution or by enabling computer-assisted applications. Directed evolution mimics the natural selection process in a highly accelerated fashion at the expense of arduous laboratory work and economic resources. Theoretical methods provide predictions and represent an attractive complement to such experiments by waiving their inherent costs. Computational techniques can be used to engineer enzymatic reactivity, substrate specificity and ligand binding, access pathways and ligand transport, and global properties like protein stability, solubility, and flexibility. Theoretical approaches can also identify hotspots on the protein sequence for mutagenesis and predict suitable alternatives for selected positions with expected outcomes. This review covers the latest advances in computational methods for enzyme engineering and presents many successful case studies.

Predicting materials properties without crystal structure: deep representation learning from stoichiometry

Machine learning has the potential to accelerate materials discovery by accurately predicting materials properties at a low computational cost. However, the model inputs remain a key stumbling block. Current methods typically use descriptors constructed from knowledge of either the full crystal structure — therefore only applicable to materials with already characterised structures — or structure-agnostic fixed-length representations hand-engineered from the stoichiometry. We develop a machine learning approach that takes only the stoichiometry as input and automatically learns appropriate and systematically improvable descriptors from data. Our key insight is to treat the stoichiometric formula as a dense weighted graph between elements. Compared to the state of the art for structure-agnostic methods, our approach achieves lower errors with less data.

Predicting the structure of unknown materials’ compositions represents a challenge for high-throughput computational approaches. Here the authors introduce a new stoichiometry-based machine learning approach for predicting the properties of inorganic materials from their elemental compositions.

Voxelized Atomic Structure Potentials: Predicting Atomic Forces with the Accuracy of Quantum Mechanics Using Convolutional Neural Networks

This paper introduces voxelized atomic structure (VASt) potentials as a machine learning (ML) framework for developing interatomic potentials. The VASt framework utilizes a voxelized representation of the atomic structure directly as the input to a convolutional neural network (CNN). This allows for high-fidelity representations of highly complex and diverse spatial arrangements of the atomic environments of interest. The CNN implicitly establishes the low-dimensional features needed to correlate each atomic neighborhood to its net atomic force. The selection of the salient features of the atomic structure (i.e., feature engineering) in the VASt framework is implicit, comprehensive, automated, scalable, and highly efficient. The calibrated convolutional layers learn the complex spatial relationships and multibody interactions that govern the physics of atomic systems with remarkable fidelity. We show that VASt potentials predict highly accurate forces on two phases of silicon carbide and the thermal conductivity of silicon over a range of isotropic strain.

Differentiable Optimization for the Prediction of Ground State Structures (DOGSS)

Ground state or relaxed inorganic structures are the starting point for most computational materials science or surface science analyses. Many of these structure relaxations represent systematic changes to the structure, but there are currently no general methods to improve the initial structure guess based on past calculations. Here we present a method to directly predict the ground state configuration using differentiable optimization and graph neural networks to learn the properties of a simple harmonic force field that approximates the ground state structure and properties. We demonstrate this flexible open source tool for improving the initial configurations for large datasets of inorganic multicomponent surface relaxations across 32 elements and the relaxation of adsorbates (H and CO) on these surfaces. Using these improved initial configurations reduces the expensive adsorbate-covered surface relaxations by approximately 50% and is complementary to other approaches to accelerate the relaxation process.

Big-Data Science in Porous Materials: Materials Genomics and Machine Learning

By combining metal nodes with organic linkers we can potentially synthesize millions of possible metal-organic frameworks (MOFs). The fact that we have so many materials opens many exciting avenues but also create new challenges. We simply have too many materials to be processed using conventional, brute force, methods. In this review, we show that having so many materials allows us to use big-data methods as a powerful technique to study these materials and to discover complex correlations. The first part of the review gives an introduction to the principles of big-data science. We show how to select appropriate training sets, survey approaches that are used to represent these materials in feature space, and review different learning architectures, as well as evaluation and interpretation strategies. In the second part, we review how the different approaches of machine learning have been applied to porous materials. In particular, we discuss applications in the field of gas storage and separation, the stability of these materials, their electronic properties, and their synthesis. Given the increasing interest of the scientific community in machine learning, we expect this list to rapidly expand in the coming years.

Developing high safety Li-metal anodes for future high-energy Li-metal batteries: strategies and perspectives

Developing high-safety Li-metal anodes (LMAs) are extremely important for the application of high-energy Li-metal batteries. The recently state-of-the-art technologies, strategies and perspectives for developing LMAs are comprehensively summarized in this review.

Molecular Dynamics Properties without the Full Trajectory: A Denoising Autoencoder Network for Properties of Simple Liquids

Molecular dynamics (MD) simulation is a popularly used computational tool to compute microscopic and macroscopic properties of a variety of systems including liquids, solids, biological systems, etc. To determine properties of atomic systems to a good level of accuracy with minimal noise or fluctuation, MD simulations are performed over a long time ranging from a few nanoseconds to several tens to hundreds of nanoseconds depending on the system and the properties of interest. In this study, by considering simple liquids, we explore the feasibility of significantly reducing the MD simulation time to compute various properties of monatomic systems such as the structure, pressure, and isothermal compressibility. To do so, extensive MD simulations are performed on 12 000 distinct Lennard-Jones systems at various thermodynamic states. Then, a deep denoising autoencoder network is trained to take the radial distribution function (RDF) from a single snapshot of a Lennard-Jones liquid to compute the mean, temporally averaged RDF. We show that the method is successful in the prediction of RDF and other properties such as the pressure and isothermal compressibility that can be computed based on the RDF not only for Lennard-Jones liquids at various thermodynamic states but also for various simple liquids described by exponential, Yukawa, and inverse-power-law pair potentials.

Dynamic graphical models of molecular kinetics

Most current molecular dynamics simulation and analysis methods rely on the idea that the molecular system can be represented by a single global state (e.g., a Markov state in a Markov state model [MSM]). In this approach, molecules can be extensively sampled and analyzed when they only possess a few metastable states, such as small- to medium-sized proteins. However, this approach breaks down in frustrated systems and in large protein assemblies, where the number of global metastable states may grow exponentially with the system size. To address this problem, we here introduce dynamic graphical models (DGMs) that describe molecules as assemblies of coupled subsystems, akin to how spins interact in the Ising model. The change of each subsystem state is only governed by the states of itself and its neighbors. DGMs require fewer parameters than MSMs or other global state models; in particular, we do not need to observe all global system configurations to characterize them. Therefore, DGMs can predict previously unobserved molecular configurations. As a proof of concept, we demonstrate that DGMs can faithfully describe molecular thermodynamics and kinetics and predict previously unobserved metastable states for Ising models and protein simulations.