Using collective knowledge to assign oxidation states of metal cations in metal-organic frameworks

Facilely tuning the coating layers of Fe nanoparticles from iron carbide to iron nitride for different performance in Fenton-like reactions

In this study, a series of Fe-based materials are facilely synthesized using MIL-88A and melamine as precursors. Changing the mass ratio of melamine and MIL-88A could tune the coating layers of generated zero-valent iron (Fe0) particles from Fe3C to Fe3N facilely. Compared to Fe/Fe3N@NC sample, Fe/Fe3C@NC exhibits better catalytic activity and stability to degrade carbamazepine (CBZ) with peroxymonosulfate (PMS) as oxidant. Free radical quenching tests, open-circuit potential (OCP) test and electron paramagnetic resonance spectra (EPR) prove that hydroxyl radicals (OH) and superoxide radical (O2-) are dominant reactive oxygen species (ROSs) with Fe/Fe3C@NC sample. For Fe/Fe3N@NC sample, the main ROSs are changed into sulfate radicals (SO4-) and high valent iron-oxo (Fe (IV)=O) species. In addition, the better conductivity of Fe3C is beneficial for the electron transfer from Fe0 to the Fe3C, thus could keep the activity of the surface sites and obtain better stability. DFT calculation reveals the better adsorption and activation ability of Fe3C than Fe3N. Moreover, PMS can also be adsorbed on the Fe sites of Fe3N with shorter FeO bonds and longer SO bonds than on Fe3C, the Fe (IV)=O is thus present in the Fe/Fe3N@NC/PMS system. This study provides a novel strategy for the development of highly active Fe-based materials for Fenton-like reactions and thus could promote their real application.

Similarities and Differences in Benzene Reduction with Ca, Sr, Yb and Sm: Strong Evidence for Tetra-Anionic Benzene

Inverse sandwich complexes of Yb and Sm stabilized by a bulky β-diketiminate (BDI) ligand have been prepared: (BDI)Ln(η6,η6-C6H6)Ln(BDI); Ln=lanthanide. Coordinated benzene ligands can be neutral, di-anionic or, often controversially discussed, even tetra-anionic. The formal charge on benzene is correlated to assignment of the metal oxidation state which generally poses a problem. Herein, we take advantage of the structural similarities found when comparing CaII with YbII, and SrII with SmII complexes. In this work, we found an excellent overlap of the Ca/Yb inverse sandwich structures but a striking difference for the Sr/Sm pair. The much shorter Sm-N and Sm-C6H6 distances are strong evidence for a SmIII-benzene-4-SmIII assignment. This was further supported by NMR spectroscopy, magnetic susceptibility, reactivity and comprehensive computational investigation.

Leveraging Machine Learning for Metal-Organic Frameworks: A Perspective

Metal-organic frameworks (MOFs) have attracted tremendous interest because of their tunable structures, functionalities, and physiochemical properties. The nearly infinite combinations of metal nodes and organic linkers have led to the synthesis of over 100,000 experimental MOFs and the construction of millions of hypothetical counterparts. It is intractable to identify the best candidates in the immense chemical space of MOFs for applications via conventional trial-to-error experiments or brute-force simulations. Over the past several years, machine learning (ML) has substantially transformed the way of MOF discovery, design, and synthesis. Driven by the abundant data from experiments or simulations, ML can not only efficiently and accurately predict MOF properties but also quantitatively derive structure-property relationships for rational design and screening. In this Perspective, we summarize recent achievements in leveraging ML for MOFs from the aspects of data acquisition, featurization, model training, and applications. Then, current challenges and new opportunities are discussed for the future exploration of ML to accelerate the development of new MOFs in this vibrant field.

Direct prediction of gas adsorption via spatial atom interaction learning

Physisorption relying on crystalline porous materials offers prospective avenues for sustainable separation processes, greenhouse gas capture, and energy storage. However, the lack of end-to-end deep learning model for adsorption prediction confines the rapid and precise screen of crystalline porous materials. Here, we present DeepSorption, a spatial atom interaction learning network that realizes accurate, fast, and direct structure-adsorption prediction with only information of atomic coordinate and chemical element types. The breakthrough in prediction is attributed to the awareness of global structure and local spatial atom interactions endowed by the developed Matformer, which provides the intuitive visualization of atomic-level thinking and executing trajectory in crystalline porous materials prediction. Complete adsorption curves prediction could be performed using DeepSorption with a higher accuracy than Grand canonical Monte Carlo simulation and other machine learning models, a 20-35% decline in the mean absolute error compared to graph neural network CGCNN and machine learning models based on descriptors. Since the established direct associations between raw structure and target functions are based on the understanding of the fundamental chemistry of interatomic interactions, the deep learning network is rationally universal in predicting the different physicochemical properties of various crystalline materials.

Composition Based Oxidation State Prediction of Materials Using Deep Learning Language Models

Oxidation states (OS) are the charges on atoms due to electrons gained or lost upon applying an ionic approximation to their bonds. As a fundamental property, OS has been widely used in charge-neutrality verification, crystal structure determination, and reaction estimation. Currently, only heuristic rules exist for guessing the oxidation states of a given compound with many exceptions. Recent work has developed machine learning models based on heuristic structural features for predicting the oxidation states of metal ions. However, composition-based oxidation state prediction still remains elusive so far, which has significant implications for the discovery of new materials for which the structures have not been determined. This work proposes a novel deep learning-based BERT transformer language model BERTOS for predicting the oxidation states for all elements of inorganic compounds given only their chemical composition. This model achieves 96.82% accuracy for all-element oxidation states prediction benchmarked on the cleaned ICSD dataset and achieves 97.61% accuracy for oxide materials. It is also demonstrated how it can be used to conduct large-scale screening of hypothetical material compositions for materials discovery.

An Ecosystem for Digital Reticular Chemistry

The vastness of the materials design space makes it impractical to explore using traditional brute-force methods, particularly in reticular chemistry. However, machine learning has shown promise in expediting and guiding materials design. Despite numerous successful applications of machine learning to reticular materials, progress in the field has stagnated, possibly because digital chemistry is more an art than a science and its limited accessibility to inexperienced researchers. To address this issue, we present mofdscribe, a software ecosystem tailored to novice and seasoned digital chemists that streamlines the ideation, modeling, and publication process. Though optimized for reticular chemistry, our tools are versatile and can be used in nonreticular materials research. We believe that mofdscribe will enable a more reliable, efficient, and comparable field of digital chemistry.

Predicting the oxidation states of Mn ions in the oxygen-evolving complex of photosystem II using supervised and unsupervised machine learning

Serial Femtosecond Crystallography at the X-ray Free Electron Laser (XFEL) sources enabled the imaging of the catalytic intermediates of the oxygen evolution reaction of Photosystem II (PSII). However, due to the incoherent transition of the S-states, the resolved structures are a convolution from different catalytic states. Here, we train Decision Tree Classifier and K-means clustering models on Mn compounds obtained from the Cambridge Crystallographic Database to predict the S-state of the X-ray, XFEL, and CryoEM structures by predicting the Mn's oxidation states in the oxygen-evolving complex. The model agrees mostly with the XFEL structures in the dark S₁ state. However, significant discrepancies are observed for the excited XFEL states (S₂, S_3, and S₀) and the dark states of the X-ray and CryoEM structures. Furthermore, there is a mismatch between the predicted S-states within the two monomers of the same dimer, mainly in the excited states. We validated our model against other metalloenzymes, the valence bond model and the Mn spin densities calculated using density functional theory for two of the mismatched predictions of PSII. The model suggests designing a more optimized sample delivery and illumiation systems are crucial to precisely resolve the geometry of the advanced S-states to overcome the noncoherent S-state transition. In addition, significant radiation damage is observed in X-ray and CryoEM structures, particularly at the dangler Mn center (Mn4). Our model represents a valuable tool for investigating the electronic structure of the catalytic metal cluster of PSII to understand the water splitting mechanism.

Gold and palladium supported on an ionic liquid modified Fe-based metal-organic framework (MOF) as highly efficient catalysts for the reduction of nitrophenols, dyes and Sonogashira-Hagihara reactions

Two supported noble metal species, gold and palladium anchored on an ionic liquid-modified Fe-based metal-organic framework (MOF), were successfully synthesized and characterized by FT-IR, XRD, TEM, XPS, SEM, EDX, and elemental mapping. The ionic liquid post-modified MOF was used for anchoring Au or Pd at ppm levels, and the resulting materials were employed as catalysts in the reduction of nitrophenol isomers, dyes, and Sonogashira-Hagihara reactions. Using the Au@Fe-MOF-IL catalyst, reduction of nitrophenol isomers, as well as the reductive degradation of dyes, e.g., methylene blue (MB), methyl orange (MO), and methyl red (MR) were performed efficiently in water. On the other hand, Pd@Fe-MOF-IL was used as an effective catalyst in the Sonogashira-Hagihara coupling reaction of aryl iodides and bromides using very low amounts of Pd. These catalysts were recycled and reused for several runs without deteriorating remarkably in catalytic performance.

A data-science approach to predict the heat capacity of nanoporous materials

The heat capacity of a material is a fundamental property of great practical importance. For example, in a carbon capture process, the heat required to regenerate a solid sorbent is directly related to the heat capacity of the material. However, for most materials suitable for carbon capture applications, the heat capacity is not known, and thus the standard procedure is to assume the same value for all materials. In this work, we developed a machine learning approach, trained on density functional theory simulations, to accurately predict the heat capacity of these materials, that is, zeolites, metal-organic frameworks and covalent-organic frameworks. The accuracy of our prediction is confirmed with experimental data. Finally, for a temperature swing adsorption process that captures carbon from the flue gas of a coal-fired power plant, we show that for some materials, the heat requirement is reduced by as much as a factor of two using the correct heat capacity.

SELFIES and the future of molecular string representations

Artificial intelligence (AI) and machine learning (ML) are expanding in popularity for broad applications to challenging tasks in chemistry and materials science. Examples include the prediction of properties, the discovery of new reaction pathways, or the design of new molecules. The machine needs to read and write fluently in a chemical language for each of these tasks. Strings are a common tool to represent molecular graphs, and the most popular molecular string representation, Smiles, has powered cheminformatics since the late 1980s. However, in the context of AI and ML in chemistry, Smiles has several shortcomings-most pertinently, most combinations of symbols lead to invalid results with no valid chemical interpretation. To overcome this issue, a new language for molecules was introduced in 2020 that guarantees 100% robustness: SELF-referencing embedded string (Selfies). Selfies has since simplified and enabled numerous new applications in chemistry. In this perspective, we look to the future and discuss molecular string representations, along with their respective opportunities and challenges. We propose 16 concrete future projects for robust molecular representations. These involve the extension toward new chemical domains, exciting questions at the interface of AI and robust languages, and interpretability for both humans and machines. We hope that these proposals will inspire several follow-up works exploiting the full potential of molecular string representations for the future of AI in chemistry and materials science.

Machine-Learning-Guided Identification of Coordination Polymer Ligands for Crystallizing Separation of Cs/Sr

Separation of Cs/Sr is one of many coordination-chemistry-centered processes in the grand scheme of spent nuclear fuel reprocessing, a critical link for a sustainable nuclear energy industry. To deploy a crystallizing Cs/Sr separation technology, we planned to systematically screen and identify candidate ligands that can efficiently and selectively bind to Sr2+ and form coordination polymers. Therefore, we mined the Cambridge Structural Database for characteristic structural information and developed a machine-learning-guided methodology for ligand evaluation. The optimized machine-learning model, correlating the molecular structures of the ligands with the predicted coordinative properties, generated a ranking list of potential compounds for Cs/Sr selective crystallization. The Sr2+ sequestration capability and selectivity over Cs+ of the promising ligands identified (squaric acid and chloranilic acid) were subsequently confirmed experimentally, with commendable performances, corroborating the artificial-intelligence-guided strategy.

Mining Knowledge from Crystal Structures: Oxidation States of Oxygen-Coordinated Metal Atoms in Ionic and Coordination Compounds

We propose a universal scheme for predicting the oxidation states of metal atoms in ionic and coordination compounds with a small set of structural descriptors, which include the parameters of atomic Voronoi polyhedra. The scheme has been trained and checked with more than 35,000 crystal structures containing more than 90,000 metal atoms in the oxygen environment. The accuracy of the prediction exceeded 95%; we have detected a number of wrong oxidation states and incorrect chemical compositions in the crystallographic databases using this scheme. The scheme is easily extendable to any kind of atomic environment and can be used to search for correlations between geometrical and physical properties of crystal structures.

MOF Synthesis Prediction Enabled by Automatic Data Mining and Machine Learning

Despite rapid progress in the field of metal–organic frameworks (MOFs), the potential of using machine learning (ML) methods to predict MOF synthesis parameters is still untapped. Here, we show how ML can be used for rationalization and acceleration of the MOF discovery process by directly predicting the synthesis conditions of a MOF based on its crystal structure. Our approach is based on: i) establishing the first MOF synthesis database via automatic extraction of synthesis parameters from the literature, ii) training and optimizing ML models by employing the MOF database, and iii) predicting the synthesis conditions for new MOF structures. The ML models, even at an initial stage, exhibit a good prediction performance, outperforming human expert predictions, obtained through a synthesis survey. The automated synthesis prediction is available via a web‐tool on https://mof‐synthesis.aimat.science.

Visualization and Quantification of Geometric Diversity in Metal-Organic Frameworks

With ever-growing numbers of metal-organic framework (MOF) materials being reported, new computational approaches are required for a quantitative understanding of structure-property correlations in MOFs. Here, we show how structural coarse-graining and embedding ("unsupervised learning") schemes can together give new insights into the geometric diversity of MOF structures. Based on a curated data set of 1262 reported experimental structures, we automatically generate coarse-grained and rescaled representations which we couple to a kernel-based similarity metric and to widely used embedding schemes. This approach allows us to visualize the breadth of geometric diversity within individual topologies and to quantify the distributions of local and global similarities across the structural space of MOFs. The methodology is implemented in an openly available Python package and is expected to be useful in future high-throughput studies.