Atomistic simulations of matter, especially those that leverage first-principles (ab initio) electronic structure theory, provide a microscopic view of the world, underpinning much of our understanding of chemistry and materials science. Over the last decade or so, machine-learned force fields have transformed atomistic modeling by enabling simulations of ab initio quality over unprecedented time and length scales. However, early machine-learning (ML) force fields have largely been limited by (i) the substantial computational and human effort required to develop and validate potentials for each particular system of interest and (ii) a general lack of transferability from one chemical system to the next. Here, we show that it is possible to create a general-purpose atomistic ML model, trained on a public dataset of moderate size, that is capable of running stable molecular dynamics for a wide range of molecules and materials. We demonstrate the power of the MACE-MP-0 model—and its qualitative and at times quantitative accuracy—on a diverse set of problems in the physical sciences, including properties of solids, liquids, gases, chemical reactions, interfaces, and even the dynamics of a small protein. The model can be applied out of the box as a starting or “foundation” model for any atomistic system of interest and, when desired, can be fine-tuned on just a handful of application-specific data points to reach ab initio accuracy. Establishing that a stable force-field model can cover almost all materials changes atomistic modeling in a fundamental way: experienced users obtain reliable results much faster, and beginners face a lower barrier to entry. Foundation models thus represent a step toward democratizing the revolution in atomic-scale modeling that has been brought about by ML force fields.

We introduce a training protocol for developing machine learning force fields (MLFFs), capable of accurately determining energy barriers in catalytic reaction pathways. The protocol is validated on the extensively explored hydrogenation of carbon dioxide to methanol over indium oxide. With the help of active learning, the final force field obtains energy barriers within 0.05 eV of Density Functional Theory. Thanks to the computational speedup, not only do we reduce the cost of routine in-silico catalytic tasks, but also find an alternative path for the previously established rate-limiting step, with a 40% reduction in activation energy. Furthermore, we illustrate the importance of finite temperature effects and compute free energy barriers. The transferability of the protocol is demonstrated on the experimentally relevant, yet unexplored, top-layer reduced indium oxide surface. The ability of MLFFs to enhance our understanding of extensively studied catalysts underscores the need for fast and accurate alternatives to direct ab-initio simulations.

Carbon dioxide capture technologies are set to play a vital role in mitigating the current climate crisis. Solid‐state ¹⁷O NMR spectroscopy can provide key mechanistic insights that are crucial to effective sorbent development. In this work, we present the fundamental aspects and complexities for the study of hydroxide‐based CO₂ capture systems by ¹⁷O NMR. We perform static density functional theory (DFT) NMR calculations to assign peaks for general hydroxide CO₂ capture products, finding that ¹⁷O NMR can readily distinguish bicarbonate, carbonate and water species. However, in application to CO₂ binding in two test case hydroxide‐functionalised metal‐organic frameworks (MOFs) – MFU‐4l and KHCO₃‐cyclodextrin‐MOF, we find that a dynamic treatment is necessary to obtain agreement between computational and experimental spectra. We therefore introduce a workflow that leverages machine‐learning force fields to capture dynamics across multiple chemical exchange regimes, providing a significant improvement on static DFT predictions. In MFU‐4l, we parameterise a two‐component dynamic motion of the bicarbonate motif involving a rapid carbonyl seesaw motion and intermediate hydroxyl proton hopping. For KHCO₃‐CD‐MOF, we combined experimental and modelling approaches to propose a new mixed carbonate‐bicarbonate binding mechanism and thus, we open new avenues for the study and modelling of hydroxide‐based CO₂ capture materials by ¹⁷O NMR.

Machine learning potentials have become a standard tool for atomistic materials modeling. While models continue to become more generalizable, an open challenge relates to efficient uncertainty predictions for active learning and robust error analysis. In this work, we utilize MACE and its multi-head mechanism to implement a committee neural network potential for message-passing architectures, where the committee comprises multiple output modules attached to the same atomic environment descriptors. As with traditional committees of independent networks, the standard deviation of the predictions functions as an estimate of the model’s uncertainty. We show for a range of datasets in custom-build models that the uncertainty of the force predictions correlates well with the true errors. We subsequently apply this concept to foundation models, in particular MACE-MP-0, where we train only the newly attached output heads while keeping the remaining part of the model fixed. We use this approach in an active learning workflow to condense the training set of the foundation model to just 5% of its original size. The foundation model multi-head committee trained on the condensed training set enables reliable uncertainty estimation without any substantial decrease in prediction accuracy.

We show that neural networks can be optimized to represent minimum energy paths as continuous functions, offering a flexible alternative to discrete path-search methods such as Nudged Elastic Band (NEB). Our approach parameterizes reaction paths with a network trained on a loss function that discards tangential energy gradients and enables instant estimation of the transition state. We first validate the method on two-dimensional potentials and then demonstrate its advantages over NEB on challenging atomistic systems where (i) poor initial guesses yield unphysical paths, (ii) multiple competing paths exist, or (iii) the reaction follows a complex multi-step mechanism. Results highlight the versatility of the method: for instance, a simple adjustment to the sampling strategy during optimization can help escape local-minimum solutions. Finally, in a low-dimensional setting, we demonstrate that a single neural network can learn from existing paths and generalize to unseen systems, showing promise for a universal reaction path representation.

The catalytic and other sophisticated functions of biomolecules arise from the placement of many atoms in three-dimensional space. Here, we describe a generative artificial intelligence method for biopolymers, RFdiffusion3 (RFD3), which employs free atom diffusion to satisfy complex sets of atomic constraints more rapidly and accurately than previous methods across several challenges from enzyme design to RNA structure design. We demonstrate experimentally the power of the RFD3 pipeline for enzyme design by designing de novo phosphotriesterases with a complex active site architecture incorporating a carbamylated lysine coordinating two metal ions and zinc proteases specific for the transthyretin protein involved in amyloid diseases; in both cases we obtain active catalysts in zero shot 96 construct design campaigns.