Explore the vast range of titles available.

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.

To design electrochemical interfaces for efficient electric-chemical energy interconversion, it is critical to reveal the electric double layer (EDL) structure and relate it with electrochemical activity; nonetheless, this has been a long-standing challenge. Of particular, no molecular-level theories have fully explained the characteristic two peaks arising in the potential-dependence of the EDL capacitance, which is sensitively dependent on the EDL structure. We herein demonstrate that our first-principles-based molecular simulation reproduces the experimental capacitance peaks. The origin of two peaks emerging at anodic and cathodic potentials is unveiled to be an electrosorption of ions and a structural phase transition, respectively. We further find a cation complexation gradually modifies the EDL structure and the field strength, which linearly scales the carbon dioxide reduction activity. This study deciphers the complex structural response of the EDL and highlights its catalytic importance, which bridges the mechanistic gap between the EDL structure and electrocatalysis. The structure of the electric double layer (EDL) has been a long-standing question since the 19th century. Here, the authors simulate EDL structures and highlight their importance in catalysis through comparison of atomic simulations and experiment.

ChatMOF is an artificial intelligence (AI) system that is built to predict and generate metal-organic frameworks (MOFs). By leveraging a large-scale language model (GPT-4, GPT-3.5-turbo, and GPT-3.5-turbo-16k), ChatMOF extracts key details from textual inputs and delivers appropriate responses, thus eliminating the necessity for rigid and formal structured queries. The system is comprised of three core components (i.e., an agent, a toolkit, and an evaluator) and it forms a robust pipeline that manages a variety of tasks, including data retrieval, property prediction, and structure generations. ChatMOF shows high accuracy rates of 96.9% for searching, 95.7% for predicting, and 87.5% for generating tasks with GPT-4. Additionally, it successfully creates materials with user-desired properties from natural language. The study further explores the merits and constraints of utilizing large language models (LLMs) in combination with database and machine learning in material sciences and showcases its transformative potential for future advancements. LLMs can be augmented with tools to increase their capabilities. Here, authors have developed an artificial intelligence system called ChatMOF combining LLMs and specialised libraries and utilities to predict and generate metal-organic frameworks.

Intrinsically disordered proteins and regions (collectively, IDRs) are pervasive across proteomes in all kingdoms of life, help to shape biological functions and are involved in numerous diseases. IDRs populate a diverse set of transiently formed structures and defy conventional sequence–structure–function relationships 1 . Developments in protein science have made it possible to predict the three-dimensional structures of folded proteins at the proteome scale 2 . By contrast, there is a lack of knowledge about the conformational properties of IDRs, partly because the sequences of disordered proteins are poorly conserved and also because only a few of these proteins have been characterized experimentally. The inability to predict structural properties of IDRs across the proteome has limited our understanding of the functional roles of IDRs and how evolution shapes them. As a supplement to previous structural studies of individual IDRs 3 , we developed an efficient molecular model to generate conformational ensembles of IDRs and thereby to predict their conformational properties from sequences 4 , 5 . Here we use this model to simulate nearly all of the IDRs in the human proteome. Examining conformational ensembles of 28,058 IDRs, we show how chain compaction is correlated with cellular function and localization. We provide insights into how sequence features relate to chain compaction and, using a machine-learning model trained on our simulation data, show the conservation of conformational properties across orthologues. Our results recapitulate observations from previous studies of individual protein systems and exemplify how to link—at the proteome scale—conformational ensembles with cellular function and localization, amino acid sequence, evolutionary conservation and disease variants. Our freely available database of conformational properties will encourage further experimental investigation and enable the generation of hypotheses about the biological roles and evolution of IDRs. A computational model generates conformational ensembles of 28,058 intrinsically disordered proteins and regions (IDRs) in the human proteome and sheds light on the relationship between sequence, conformational properties and functions of IDRs.

Due to their strong dependence on local atonic environments, NMR chemical shifts are among the most powerful tools for strucutre elucidation of powdered solids or amorphous materials. Unfortunately, using them for structure determination depends on the ability to calculate them, which  comes at the cost of high accuracy first-principles calculations. Machine learning has recently emerged as a way to overcome the need for quantum chemical calculations, but for chemical shifts in solids it is hindered by the chemical and combinatorial space spanned by molecular solids, the strong dependency of chemical shifts on their environment, and the lack of an experimental database of shifts. We propose a machine learning method based on local environments to accurately predict chemical shifts of molecular solids and their polymorphs to within DFT accuracy. We also demonstrate that the trained model is able to determine, based on the match between experimentally measured and ML-predicted shifts, the structures of cocaine and the drug 4-[4-(2-adamantylcarbamoyl)-5-tert-butylpyrazol-1-yl]benzoic acid. Solid-state nuclear magnetic resonance combined with quantum chemical shift predictions is limited by high computational cost. Here, the authors use machine learning based on local atomic environments to predict experimental chemical shifts in molecular solids with accuracy similar to density functional theory.

One atom or molecule binds to another through various types of bond, the strengths of which range from several meV to several eV. Although some computational methods can provide accurate descriptions of all bond types, those methods are not efficient enough for many studies (for example, large systems, ab initio molecular dynamics and high-throughput searches for functional materials). Here, we show that the recently developed non-empirical strongly constrained and appropriately normed (SCAN) meta-generalized gradient approximation (meta-GGA) within the density functional theory framework predicts accurate geometries and energies of diversely bonded molecules and materials (including covalent, metallic, ionic, hydrogen and van der Waals bonds). This represents a significant improvement at comparable efficiency over its predecessors, the GGAs that currently dominate materials computation. Often, SCAN matches or improves on the accuracy of a computationally expensive hybrid functional, at almost-GGA cost. SCAN is therefore expected to have a broad impact on chemistry and materials science. Whether a molecule or material can exist, and with what structures and energies, is of critical importance. For demanding calculations the efficiency of density functional theory makes it the only practical electronic structure theory available to help answer these questions. Now, an efficient density functional is shown to have unprecedented accuracy for a diverse set of bonded systems.

Exploratory synthesis in new chemical spaces is the essence of solid-state chemistry. However, uncharted chemical spaces can be difficult to navigate, especially when materials synthesis is challenging. Nitrides represent one such space, where stringent synthesis constraints have limited the exploration of this important class of functional materials. Here, we employ a suite of computational materials discovery and informatics tools to construct a large stability map of the inorganic ternary metal nitrides. Our map clusters the ternary nitrides into chemical families with distinct stability and metastability, and highlights hundreds of promising new ternary nitride spaces for experimental investigation—from which we experimentally realized seven new Zn- and Mg-based ternary nitrides. By extracting the mixed metallicity, ionicity and covalency of solid-state bonding from the density functional theory (DFT)-computed electron density, we reveal the complex interplay between chemistry, composition and electronic structure in governing large-scale stability trends in ternary nitride materials.

Although machine learning (ML) models promise to substantially accelerate the discovery of novel materials, their performance is often still insufficient to draw reliable conclusions. Improved ML models are therefore actively researched, but their design is currently guided mainly by monitoring the average model test error. This can render different models indistinguishable although their performance differs substantially across materials, or it can make a model appear generally insufficient while it actually works well in specific sub-domains. Here, we present a method, based on subgroup discovery, for detecting domains of applicability (DA) of models within a materials class. The utility of this approach is demonstrated by analyzing three state-of-the-art ML models for predicting the formation energy of transparent conducting oxides. We find that, despite having a mutually indistinguishable and unsatisfactory average error, the models have DAs with distinctive features and notably improved performance. Machine learning models insufficient for certain screening tasks can still provide valuable predictions in specific sub-domains of the considered materials. Here, the authors introduce a diagnostic tool to detect regions of low expected model error as demonstrated for the case of transparent conducting oxides.

Crystal structure prediction is a long-standing challenge in condensed matter and chemical science. Here we report a machine-learning approach for crystal structure prediction, in which a graph network (GN) is employed to establish a correlation model between the crystal structure and formation enthalpies at the given database, and an optimization algorithm (OA) is used to accelerate the search for crystal structure with lowest formation enthalpy. The framework of the utilized approach (a database + a GN model + an optimization algorithm) is flexible. We implemented two benchmark databases, i.e ., the open quantum materials database (OQMD) and Matbench (MatB), and three OAs, i.e ., random searching (RAS), particle-swarm optimization (PSO) and Bayesian optimization (BO), that can predict crystal structures at a given number of atoms in a periodic cell. The comparative studies show that the GN model trained on MatB combined with BO, i.e ., GN(MatB)-BO, exhibit the best performance for predicting crystal structures of 29 typical compounds with a computational cost three orders of magnitude less than that required for conventional approaches screening structures through density functional theory calculation. The flexible framework in combination with a materials database, a graph network, and an optimization algorithm may open new avenues for data-driven crystal structural predictions. Predicting crystal structure prior to experimental synthesis is highly desirable. Here the authors propose a machine-learning framework combining graph network and optimization algorithms for crystal structure prediction, which is about three orders of magnitude faster than DFT-based approach.

Structure plays a vital role in determining materials properties. In lithium ion cathode materials, the crystal structure defines the dimensionality and connectivity of interstitial sites, thus determining lithium ion diffusion kinetics. In most conventional cathode materials that are well-ordered, the average structure as seen in diffraction dictates the lithium ion diffusion pathways. Here, we show that this is not the case in a class of recently discovered high-capacity lithium-excess rocksalts. An average structure picture is no longer satisfactory to understand the performance of such disordered materials. Cation short-range order, hidden in diffraction, is not only ubiquitous in these long-range disordered materials, but fully controls the local and macroscopic environments for lithium ion transport. Our discovery identifies a crucial property that has previously been overlooked and provides guidelines for designing and engineering cation-disordered cathode materials. The average crystal structure largely governs the Li diffusion kinetics in well-ordered cathode materials. Here the authors show this rule does not hold true for cation-disordered analogues. Cation short-range order is not only ubiquitous but also controls the Li transport behavior.