Faraday Discussions最新文献

This Faraday Discussion explored the field of NMR crystallography, and considered recent developments in experimental and theoretical approaches, new advances in machine learning and in the generation and handling of large amounts of data. Applications to a wide range of disordered, amorphous and dynamic systems demonstrated the range and quality of information available from this approach and the challenges that are faced in exploiting automation and developing best practice. In these closing remarks I will reflect on the discussions on the current state of the art, questions about what we want from these studies, how accurate we need results to be, how we best generate models for complex materials and what machine learning approaches can offer. These remarks close with thoughts about the future direction of the field, who will be carrying out this type of research, how they might be doing it and what their focus will be, along with likely possible challenges and opportunities.

Properly spin-adapted coupled-cluster theory for general open-shell configurations remains an active area of research in electronic structure theory. In this contribution we examine Lindgren's normal-ordered exponential ansatz to correlate specific spin states using spin-free excitation operators, with the aid of automatic equation generation software. We present an intermediately normalised and size-extensive reformulation of the unlinked working equations, and analyse the performance of the method with single and double excitations for simple molecular systems in terms of accuracy and size-consistency.

Generative models for the inverse design of molecules with particular properties have been heavily hyped, but have yet to demonstrate significant gains over machine-learning-augmented expert intuition. A major challenge of such models is their limited accuracy in predicting molecules with targeted properties in the data-scarce regime, which is the regime typical of the prized outliers that it is hoped inverse models will discover. For example, activity data for a drug target or stability data for a material may only number in the tens to hundreds of samples, which is insufficient to learn an accurate and reasonably general property-to-structure inverse mapping from scratch. We’ve hypothesized that the property-to-structure mapping becomes unique when a sufficient number of properties are supplied to the models during training. This hypothesis has several important corollaries if true. It would imply that data-scarce properties can be completely determined using a set of more accessible molecular properties. It would also imply that a generative model trained on multiple properties would exhibit an accuracy phase transition after achieving a sufficient size—a process analogous to what has been observed in the context of large language models. To interrogate these behaviors, we have built the first transformers trained on the property-to-molecular-graph task, which we dub “large property models” (LPMs). A key ingredient is supplementing these models during training with relatively basic but abundant chemical property data. The motivation for the large-property-model paradigm, the model architectures, and case studies are presented here.

Machine learning has gained popularity for predicting molecular properties based on molecular structure. This study explores the uncertainty estimates of neural fingerprint-based models by comparing pure graph neural networks (GNN) to classical machine learning algorithms combined with neural fingerprints. We investigate the advantage of extracting the neural fingerprint from the GNN and integrating it into a method known for producing better-calibrated probability estimates. Comparisons are made using three classical machine learning methods and the Chemprop model, considering different molecular representations and calibration techniques. We utilize 19 datasets from Toxcast, reflecting real-world scenarios with balanced accuracies ranging from 0.6 to 0.8. Results demonstrate that neural fingerprints combined with classical machine learning methods exhibit a slight decrease in prediction performance compared to the native Chemprop model. However, these models provide significantly improved uncertainty estimates. Notably, uncertainty estimates of neural fingerprint-based methods remain relatively robust for molecules dissimilar to the training set. This suggests that methods like random forest with neural fingerprints can deliver strong prediction performance and reliable uncertainty estimates. When considering both performance and uncertainty, the calibrated Chemprop model and the combination of neural fingerprints with random forest or support vector classifier (SVC) yield comparable results. Surprisingly, the SVC method shows promising performance when combined with neural or count fingerprints. These findings are particularly relevant in real-world industrial projects where accurate predictions and reliable uncertainty estimates are crucial.

Lithium-rich early transition metal oxides are the source of excess removeable lithium that affords high energy density to lithium-rich battery cathodes. They are also candidates for solid electrolytes in all-solid-state batteries. These highly ionic compounds are sparse on phase diagrams of thermodynamically stable oxides, but soft chemical routes offer an alternative to explore new alkali-rich crystal chemistries. In this work, a new layered polymorph of Li₃NbO₄ with coplanar [Nb₄O₁₆]¹²⁻ clusters is discovered through ion exchange chemistry. A more detailed study of the ion exchange reaction reveals that it takes place almost instantaneously, changing the crystal volume by more than 22% within seconds. The transformation of coplanar [Nb₄O₁₆]¹²⁻ in L-Li₃NbO₄ into the supertetrahedral [Nb₄O₁₆]¹²⁻ clusters found in the stable cubic c-Li₃NbO₄ is also explored. Furthermore, this synthetic pathway is extended to access a new layered polymorph of Li₃TaO₄. NMR crystallography with ^6,7Li, ²³Na, and ⁹³Nb NMR, X-ray diffraction, neutron diffraction, and first-principles calculations is applied to A₃MO₄ (A = Li, Na; M = Nb, Ta) to identify local and long-range atomic structure, to monitor the unusually rapid reaction progression, and to track the phase transitions from the metastable layered phases to the known compounds found using high-temperature synthesis. A mechanism is proposed whereby some sodium is retained at short reaction times, which then undergoes proton exchange during water washing, forming a phase with hydrogen bonds bridging the coplanar [Nb₄O₁₆]¹²⁻ clusters. This study has implications for lithium-rich transition metal oxides and associated battery materials and for ion exchange chemistry in non-framework structures. The role of techniques that can detect light elements, local structure, and subtle structural changes in soft-chemical synthesis is emphasized.