Machine Learning in Catalysis, From Proposal to Practicing

Advances, opportunities, and challenges in methods for interrogating the structure activity relationships of natural products

Time span in literature: 1985-early 2024Natural products play a key role in drug discovery, both as a direct source of drugs and as a starting point for the development of synthetic compounds. Most natural products are not suitable to be used as drugs without further modification due to insufficient activity or poor pharmacokinetic properties. Choosing what modifications to make requires an understanding of the compound's structure-activity relationships. Use of structure-activity relationships is commonplace and essential in medicinal chemistry campaigns applied to human-designed synthetic compounds. Structure-activity relationships have also been used to improve the properties of natural products, but several challenges still limit these efforts. Here, we review methods for studying the structure-activity relationships of natural products and their limitations. Specifically, we will discuss how synthesis, including total synthesis, late-stage derivatization, chemoenzymatic synthetic pathways, and engineering and genome mining of biosynthetic pathways can be used to produce natural product analogs and discuss the challenges of each of these approaches. Finally, we will discuss computational methods including machine learning methods for analyzing the relationship between biosynthetic genes and product activity, computer aided drug design techniques, and interpretable artificial intelligence approaches towards elucidating structure-activity relationships from models trained to predict bioactivity from chemical structure. Our focus will be on these latter topics as their applications for natural products have not been extensively reviewed. We suggest that these methods are all complementary to each other, and that only collaborative efforts using a combination of these techniques will result in a full understanding of the structure-activity relationships of natural products.

Bimetallic Single-Atom Catalysts for Water Splitting

Green hydrogen from water splitting has emerged as a critical energy vector with the potential to spearhead the global transition to a fossil fuel-independent society. The field of catalysis has been revolutionized by single-atom catalysts (SACs), which exhibit unique and intricate interactions between atomically dispersed metal atoms and their supports. Recently, bimetallic SACs (bimSACs) have garnered significant attention for leveraging the synergistic functions of two metal ions coordinated on appropriately designed supports. BimSACs offer an avenue for rich metal-metal and metal-support cooperativity, potentially addressing current limitations of SACs in effectively furnishing transformations which involve synchronous proton-electron exchanges, substrate activation with reversible redox cycles, simultaneous multi-electron transfer, regulation of spin states, tuning of electronic properties, and cyclic transition states with low activation energies. This review aims to encapsulate the growing advancements in bimSACs, with an emphasis on their pivotal role in hydrogen generation via water splitting. We subsequently delve into advanced experimental methodologies for the elaborate characterization of SACs, elucidate their electronic properties, and discuss their local coordination environment. Overall, we present comprehensive discussion on the deployment of bimSACs in both hydrogen evolution reaction and oxygen evolution reaction, the two half-reactions of the water electrolysis process.

Catalysing (organo-)catalysis: Trends in the application of machine learning to enantioselective organocatalysis

Organocatalysis has established itself as a third pillar of homogeneous catalysis, besides transition metal catalysis and biocatalysis, as its use for enantioselective reactions has gathered significant interest over the last decades. Concurrent to this development, machine learning (ML) has been increasingly applied in the chemical domain to efficiently uncover hidden patterns in data and accelerate scientific discovery. While the uptake of ML in organocatalysis has been comparably slow, the last two decades have showed an increased interest from the community. This review gives an overview of the work in the field of ML in organocatalysis. The review starts by giving a short primer on ML for experimental chemists, before discussing its application for predicting the selectivity of organocatalytic transformations. Subsequently, we review ML employed for privileged catalysts, before focusing on its application for catalyst and reaction design. Concluding, we give our view on current challenges and future directions for this field, drawing inspiration from the application of ML to other scientific domains.

Accelerated design of nickel-cobalt based catalysts for CO2 hydrogenation with human-in-the-loop active machine learning

Thermo-catalytic conversion of CO2 into more valuable compounds, such as methane, is an attractive strategy for energy storage in chemical bonds and creating a carbon-based circular economy. However, designing heterogeneous catalysts remains a challenging, time- and resource-consuming task. Herein, we present an interpretable, human-in-the-loop active machine learning framework to efficiently plan catalytic experiments, execute them in an automated set-up, and estimate the effect of experimental variables on the catalytic activity. A dataset with 48 catalytic activity tests was compiled from a design space of Ni-Co/Al2O3 catalysts with over 50 million potential combinations in only eight iterations. This small dataset was found sufficient to predict CO2 conversion, methane selectivity, and methane space-time yield with remarkable accuracy (R 2 > 0.9) for untested catalysts and reaction conditions. New experiments and catalysts were selected with this methodology, leading to experimental conditions that improved the methane space-time yield by nearly 50% in comparison to the previously obtained maximum in the dataset. Interpretation of the model predictions unveiled the effect of each catalyst descriptor and reaction condition on the outcome. Particularly, the strong predicted inverse trend between the calcination temperature and the catalytic activity was validated experimentally, and characterization implied an underlying structure-performance relationship. Finally, it is demonstrated that the deployed active learning model is excellently suited to predict and fit kinetic trends with a minimal amount of data. This data-driven framework is a first step to faster, model-based, and interpretable design of catalysts and holds promise for broader applications across catalytic processes.

Expanding the Horizons of Machine Learning in Nanomaterials to Chiral Nanostructures

Machine learning holds significant research potential in the field of nanotechnology, enabling nanomaterial structure and property predictions, facilitating materials design and discovery, and reducing the need for time-consuming and labor-intensive experiments and simulations. In contrast to their achiral counterparts, the application of machine learning for chiral nanomaterials is still in its infancy, with a limited number of publications to date. This is despite the great potential of machine learning to advance the development of new sustainable chiral materials with high values of optical activity, circularly polarized luminescence, and enantioselectivity, as well as for the analysis of structural chirality by electron microscopy. In this review, an analysis of machine learning methods used for studying achiral nanomaterials is provided, subsequently offering guidance on adapting and extending this work to chiral nanomaterials. An overview of chiral nanomaterials within the framework of synthesis-structure-property-application relationships is presented and insights on how to leverage machine learning for the study of these highly complex relationships are provided. Some key recent publications are reviewed and discussed on the application of machine learning for chiral nanomaterials. Finally, the review captures the key achievements, ongoing challenges, and the prospective outlook for this very important research field.

Predicting the catalytic activities of transition metal (Cr, Fe, Co, Ni) complexes towards ethylene polymerization by machine learning

The study aims to execute machine learning (ML) method for building an intelligent prediction system for catalytic activities of a relatively big dataset of 1056 transition metal complex precatalysts in ethylene polymerization. Among 14 different algorithms, the CatBoost ensemble model provides the best prediction with the correlation coefficient (R2 ) values of 0.999 for training set and 0.834 for external test set. The interpretation of the obtained model indicates that the catalytic activity is highly correlated with number of atom, conjugated degree in the ligand framework, and charge distributions. Correspondingly, 10 novel complexes are designed and predicted with higher catalytic activities. This work shows the potential application of the ML method as a high-precision tool for designing advanced catalysts for ethylene polymerization.

Metal- and ligand-substitution-induced changes in the kinetics and thermodynamics of hydrogen activation and hydricity in a dinuclear metal complex

Catalytic function in organometallic complexes is achieved by carefully selecting their central metals and ligands. In this study, the effects of a metal and a ligand on the kinetics and thermodynamics of hydrogen activation, hydricity degree of the hydride complex, and susceptibility to electronic oxidation in bioinspired NiFe complexes, [NiIIX FeII(Cl)(CO)Y]+ ([NiFe(Cl)(CO)]+; X = N,N'-diethyl-3,7-diazanonane-1,9-dithiolato and Y = 1,2-bis(diphenylphosphino)ethane), were investigated. The density functional theory calculations revealed that the following order thermodynamically favored hydrogen activation: [NiFe(CO)]2+ > [NiRu(CO)]2+ > [NiFe(CNMe)]2+ ∼ [PdRu(CO)]2+ ∼ [PdFe(CO)]2+ ≫ [NiFe(NCS)]+. Moreover, the reverse order thermodynamically favored the hydricity degree.

Machine-Learning-Assisted Nanozyme Design: Lessons from Materials and Engineered Enzymes

Nanozymes are nanomaterials that exhibit enzyme-like biomimicry. In combination with intrinsic characteristics of nanomaterials, nanozymes have broad applicability in materials science, chemical engineering, bioengineering, biochemistry, and disease theranostics. Recently, the heterogeneity of published results has highlighted the complexity and diversity of nanozymes in terms of consistency of catalytic capacity. Machine learning (ML) shows promising potential for discovering new materials, yet it remains challenging for the design of new nanozymes based on ML approaches. Alternatively, ML is employed to promote optimization of intelligent design and application of catalytic materials and engineered enzymes. Incorporation of the successful ML algorithms used in the intelligent design of catalytic materials and engineered enzymes can concomitantly facilitate the guided development of next-generation nanozymes with desirable properties. Here, recent progress in ML, its utilization in the design of catalytic materials and enzymes, and how emergent ML applications serve as promising strategies to circumvent challenges associated with time-expensive and laborious testing in nanozyme research and development are summarized. The potential applications of successful examples of ML-aided catalytic materials and engineered enzymes in nanozyme design are also highlighted, with special focus on the unified aims in enhancing design and recapitulation of substrate selectivity and catalytic activity.

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.

Bridging Together Theoretical and Experimental Perspectives in Single-Atom Alloys for Electrochemical Ammonia Production

Ammonia is an essential commodity in the food and chemical industry. Despite the energy-intensive nature, the Haber-Bosch process is the only player in ammonia production at large scales. Developing other strategies is highly desirable, as sustainable and decentralized ammonia production is crucial. Electrochemical ammonia production by directly reducing nitrogen and nitrogen-based moieties powered by renewable energy sources holds great potential. However, low ammonia production and selectivity rates hamper its utilization as a large-scale ammonia production process. Creating effective and selective catalysts for the electrochemical generation of ammonia is critical for long-term nitrogen fixation. Single-atom alloys (SAAs) have become a new class of materials with distinctive features that may be able to solve some of the problems with conventional heterogeneous catalysts. The design and optimization of SAAs for electrochemical ammonia generation have recently been significantly advanced. This comprehensive review discusses these advancements from theoretical and experimental research perspectives, offering a fundamental understanding of the development of SAAs for ammonia production.

Machine Learning Study on Microwave-Assisted Batch Preparation and Oxygen Reduction Performance of Fe-N-C Catalysts

The Fe-N-C catalyst represents one of the most promising candidates for replacing platinum-based catalysts toward the oxygen reduction reaction. The pivotal factor in the successful integration of Fe-N-C catalysts within applications is the attainment of a large-scale production capability. Microwave-assisted pyrolysis offers various advantages, including enhanced energy and time efficiency, uniform heating, and high yield in single-batch processes. These characteristics render it exceptionally suitable for the mass production of catalysts. Through a synergistic approach involving machine learning techniques and microscopic characterization, we discerned performance trends and underlying mechanisms within batch-synthesized Fe-N-C catalysts under microwave-assisted preparation conditions. Machine learning analysis revealed that the precursor mass exerts the most substantial influence on product performance. Furthermore, microscopic characterization unveiled that these influencing factors impact catalyst performance by modulating the degree of agglomeration. Our research introduces an efficacious machine learning model for prognosticating performance and dissecting the influencing factors pertinent to Fe-N-C catalyst synthesis within a microwave system.

Feed-Forward Neural Network for Predicting Enantioselectivity of the Asymmetric Negishi Reaction

Density functional theory (DFT) is a powerful tool to model transition state (TS) energies to predict selectivity in chemical synthesis. However, a successful multistep synthesis campaign must navigate energetically narrow differences in pathways that create some limits to rapid and unambiguous application of DFT to these problems. While powerful data science techniques may provide a complementary approach to overcome this problem, doing so with the relatively small data sets that are widespread in organic synthesis presents a significant challenge. Herein, we show that a small data set can be labeled with features from DFT TS calculations to train a feed-forward neural network for predicting enantioselectivity of a Negishi cross-coupling reaction with P-chiral hindered phosphines. This approach to modeling enantioselectivity is compared with conventional approaches, including exclusive use of DFT energies and data science approaches, using features from ligands or ground states with neural network architectures.

Towards Machine Learning in Heterogeneous Catalysis-A Case Study of 2,4-Dinitrotoluene Hydrogenation

Utilization of multivariate data analysis in catalysis research has extraordinary importance. The aim of the MIRA21 (MIskolc RAnking 21) model is to characterize heterogeneous catalysts with bias-free quantifiable data from 15 different variables to standardize catalyst characterization and provide an easy tool to compare, rank, and classify catalysts. The present work introduces and mathematically validates the MIRA21 model by identifying fundamentals affecting catalyst comparison and provides support for catalyst design. Literature data of 2,4-dinitrotoluene hydrogenation catalysts for toluene diamine synthesis were analyzed by using the descriptor system of MIRA21. In this study, exploratory data analysis (EDA) has been used to understand the relationships between individual variables such as catalyst performance, reaction conditions, catalyst compositions, and sustainable parameters. The results will be applicable in catalyst design, and using machine learning tools will also be possible.

Versatile Triphenylphosphine-Containing Polymeric Catalysts and Elucidation of Structure-Function Relationships

Synthetic polymers are a modular solution to bridging the two most common classes of catalysts: proteins and small molecules. Polymers offer the synthetic versatility of small-molecule catalysts while simultaneously having the ability to construct microenvironments mimicking those of natural proteins. We synthesized a panel of polymeric catalysts containing a novel triphenylphosphine acrylamide monomer and investigated how their properties impact the rate of a model Suzuki-Miyaura cross-coupling reaction. Systematic variation of polymer properties, such as the molecular weight, functional density, and comonomer identity, led to tunable reaction rates and solvent compatibility, including full conversion in an aqueous medium. Studies with bulkier substrates revealed connections between polymer parameters and reaction conditions that were further elucidated with a regression analysis. Some connections were substrate-specific, highlighting the value of the rapidly tunable polymer catalyst. Collectively, these results aid in building structure-function relationships to guide the development of polymer catalysts with tunable substrates and environmental compatibility.

Photo-Antibacterial Activity of Two-Dimensional (2D)-Based Hybrid Materials: Effective Treatment Strategy for Controlling Bacterial Infection

Bacterial contamination in water bodies is a severe scourge that affects human health and causes mortality and morbidity. Researchers continue to develop next-generation materials for controlling bacterial infections from water. Photo-antibacterial activity continues to gain the interest of researchers due to its adequate, rapid, and antibiotic-free process. Photo-antibacterial materials do not have any side effects and have a minimal chance of developing bacterial resistance due to their rapid efficacy. Photocatalytic two-dimensional nanomaterials (2D-NMs) have great potential for the control of bacterial infection due to their exceptional properties, such as high surface area, tunable band gap, specific structure, and tunable surface functional groups. Moreover, the optical and electric properties of 2D-NMs might be tuned by creating heterojunctions or by the doping of metals/carbon/polymers, subsequently enhancing their photo-antibacterial ability. This review article focuses on the synthesis of 2D-NM-based hybrid materials, the effect of dopants in 2D-NMs, and their photo-antibacterial application. We also discuss how we could improve photo-antibacterials by using different strategies and the role of artificial intelligence (AI) in the photocatalyst and in the degradation of pollutants. Finally, we discuss was of improving the photo-antibacterial activity of 2D-NMs, the toxicity mechanism, and their challenges.

Recent Developments and Trends in Asymmetric Organocatalysis

Asymmetric organocatalysis has experienced a long and spectacular way since the early reports over a century ago by von Liebig, Knoevenagel and Bredig, showing that small (chiral) organic molecules can catalyze (asymmetric) reactions. This was followed by impressive first highly enantioselective reports in the second half of the last century, until the hype initiated in 2000 by the milestone publications of MacMillan and List, which finally culminated in the 2021 Nobel Prize in Chemistry. This short Perspective aims at providing a brief introduction to the field by first looking on the historical development and the more classical methods and concepts, followed by discussing selected advanced recent examples that opened new directions and diversity within this still growing field.

Surface and Interface Coordination Chemistry Learned from Model Heterogeneous Metal Nanocatalysts: From Atomically Dispersed Catalysts to Atomically Precise Clusters

The surface and interface coordination structures of heterogeneous metal catalysts are crucial to their catalytic performance. However, the complicated surface and interface structures of heterogeneous catalysts make it challenging to identify the molecular-level structure of their active sites and thus precisely control their performance. To address this challenge, atomically dispersed metal catalysts (ADMCs) and ligand-protected atomically precise metal clusters (APMCs) have been emerging as two important classes of model heterogeneous catalysts in recent years, helping to build bridge between homogeneous and heterogeneous catalysis. This review illustrates how the surface and interface coordination chemistry of these two types of model catalysts determines the catalytic performance from multiple dimensions. The section of ADMCs starts with the local coordination structure of metal sites at the metal-support interface, and then focuses on the effects of coordinating atoms, including their basicity and hardness/softness. Studies are also summarized to discuss the cooperativity achieved by dual metal sites and remote effects. In the section of APMCs, the roles of surface ligands and supports in determining the catalytic activity, selectivity, and stability of APMCs are illustrated. Finally, some personal perspectives on the further development of surface coordination and interface chemistry for model heterogeneous metal catalysts are presented.

Graph-Driven Reaction Discovery: Progress, Challenges, and Future Opportunities

Graph-based descriptors, such as bond-order matrices and adjacency matrices, offer a simple and compact way of categorizing molecular structures; furthermore, such descriptors can be readily used to catalog chemical reactions (i.e., bond-making and -breaking). As such, a number of graph-based methodologies have been developed with the goal of automating the process of generating chemical reaction network models describing the possible mechanistic chemistry in a given set of reactant species. Here, we outline the evolution of these graph-based reaction discovery schemes, with particular emphasis on more recent methods incorporating graph-based methods with semiempirical and ab initio electronic structure calculations, minimum-energy path refinements, and transition state searches. Using representative examples from homogeneous catalysis and interstellar chemistry, we highlight how these schemes increasingly act as "virtual reaction vessels" for interrogating mechanistic questions. Finally, we highlight where challenges remain, including issues of chemical accuracy and calculation speeds, as well as the inherent challenge of dealing with the vast size of accessible chemical reaction space.

Quantum Chemical Roots of Machine-Learning Molecular Similarity Descriptors

In this work, we explore the quantum chemical foundations of descriptors for molecular similarity. Such descriptors are key for traversing chemical compound space with machine learning. Our focus is on the Coulomb matrix and on the smooth overlap of atomic positions (SOAP). We adopt a basic framework that allows us to connect both descriptors to electronic structure theory. This framework enables us to then define two new descriptors that are more closely related to electronic structure theory, which we call Coulomb lists and smooth overlap of electron densities (SOED). By investigating their usefulness as molecular similarity descriptors, we gain new insights into how and why Coulomb matrix and SOAP work. Moreover, Coulomb lists avoid the somewhat mysterious diagonalization step of the Coulomb matrix and might provide a direct means to extract subsystem information that can be compared across Born-Oppenheimer surfaces of varying dimension. For the electron density, we derive the necessary formalism to create the SOED measure in close analogy to SOAP. Because this formalism is more involved than that of SOAP, we review the essential theory as well as introduce a set of approximations that eventually allow us to work with SOED in terms of the same implementation available for the evaluation of SOAP. We focus our analysis on elementary reaction steps, where transition state structures are more similar to either reactant or product structures than the latter two are with respect to one another. The prediction of electronic energies of transition state structures can, however, be more difficult than that of stable intermediates due to multi-configurational effects. The question arises to what extent molecular similarity descriptors rooted in electronic structure theory can resolve these intricate effects.

Electrocatalytic Oxygen Reduction to Produce Hydrogen Peroxide: Rational Design from Single-Atom Catalysts to Devices

Electrocatalytic production of hydrogen peroxide (H2O2) via the 2e- transfer route of the oxygen reduction reaction (ORR) offers a promising alternative to the energy-intensive anthraquinone process, which dominates current industrial-scale production of H2O2. The availability of cost-effective electrocatalysts exhibiting high activity, selectivity, and stability is imperative for the practical deployment of this process. Single-atom catalysts (SACs) featuring the characteristics of both homogeneous and heterogeneous catalysts are particularly well suited for H2O2 synthesis and thus, have been intensively investigated in the last few years. Herein, we present an in-depth review of the current trends for designing SACs for H2O2 production via the 2e- ORR route. We start from the electronic and geometric structures of SACs. Then, strategies for regulating these isolated metal sites and their coordination environments are presented in detail, since these fundamentally determine electrocatalytic performance. Subsequently, correlations between electronic structures and electrocatalytic performance of the materials are discussed. Furthermore, the factors that potentially impact the performance of SACs in H2O2 production are summarized. Finally, the challenges and opportunities for rational design of more targeted H2O2-producing SACs are highlighted. We hope this review will present the latest developments in this area and shed light on the design of advanced materials for electrochemical energy conversion.

Graphical abstract

Synthesis of Heterogeneous Catalysts in Catalyst Informatics to Bridge Experiment and High-Throughput Calculation

The coupling of high-throughput calculations with catalyst informatics is proposed as an alternative way to design heterogeneous catalysts. High-throughput first-principles calculations for the oxidative coupling of methane (OCM) reaction are designed and performed where 1972 catalyst surface planes for the CH₄ to CH₃ reaction are calculated. Several catalysts for the OCM reaction are designed based on key elements that are unveiled via data visualization and network analysis. Among the designed catalysts, several active catalysts such as CoAg/TiO₂, Mg/BaO, and Ti/BaO are found to result in high C₂ yield. Results illustrate that designing catalysts using high-throughput calculations is achievable in principle if appropriate trends and patterns within the data generated via high-throughput calculations are identified. Thus, high-throughput calculations in combination with catalyst informatics offer a potential alternative method for catalyst design.

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.

Predicting Active Sites in Photocatalytic Degradation Process Using an Interpretable Molecular-Image Combined Convolutional Neural Network

Machine-learning models have great potential to accelerate the design and performance assessment of photocatalysts, leveraging their unique advantages in detecting patterns and making predictions based on data. However, most machine-learning models are “black-box” models due to lack of interpretability. This paper describes the development of an interpretable neural-network model on the performance of photocatalytic degradation of organic contaminants by TiO2. The molecular structures of the organic contaminants are represented by molecular images, which are subsequently encoded by feeding into a special convolutional neural network (CNN), EfficientNet, to extract the critical structural features. The extracted features in addition to five other experimental variables were input to a neural network that was subsequently trained to predict the photodegradation reaction rates of the organic contaminants by TiO2. The results show that this machine-learning (ML) model attains a higher accuracy to predict the photocatalytic degradation rate of organic contaminants than a previously developed machine-learning model that used molecular fingerprint encoding. In addition, the most relevant regions in the molecular image affecting the photocatalytic rates can be extracted with gradient-weighted class activation mapping (Grad-CAM). This interpretable machine-learning model, leveraging the graphic interpretability of CNN model, allows us to highlight regions of the molecular structure serving as the active sites of water contaminants during the photocatalytic degradation process. This provides an important piece of information to understand the influence of molecular structures on the photocatalytic degradation process.

Machine Learning Models Predict Calculation Outcomes with the Transferability Necessary for Computational Catalysis

Virtual high-throughput screening (VHTS) and machine learning (ML) have greatly accelerated the design of single-site transition-metal catalysts. VHTS of catalysts, however, is often accompanied with a high calculation failure rate and wasted computational resources due to the difficulty of simultaneously converging all mechanistically relevant reactive intermediates to expected geometries and electronic states. We demonstrate a dynamic classifier approach, i.e., a convolutional neural network that monitors geometry optimizations on the fly, and exploit its good performance and transferability in identifying geometry optimization failures for catalyst design. We show that the dynamic classifier performs well on all reactive intermediates in the representative catalytic cycle of the radical rebound mechanism for the conversion of methane to methanol despite being trained on only one reactive intermediate. The dynamic classifier also generalizes to chemically distinct intermediates and metal centers absent from the training data without loss of accuracy or model confidence. We rationalize this superior model transferability as arising from the use of electronic structure and geometric information generated on-the-fly from density functional theory calculations and the convolutional layer in the dynamic classifier. When used in combination with uncertainty quantification, the dynamic classifier saves more than half of the computational resources that would have been wasted on unsuccessful calculations for all reactive intermediates being considered.

Prospects and challenges for autonomous catalyst discovery viewed from an experimental perspective

Autonomous catalysis research requires elaborate integration of operando experiments into automated workflows. Suitable experimental data for analysis by artificial intelligence can be measured more readily according to standard operating procedures.

Ab initio molecular dynamics with enhanced sampling in heterogeneous catalysis

Enhanced sampling ab initio simulations enable to study chemical phenomena in catalytic systems including thermal effects & anharmonicity, & collective dynamics describing enthalpic & entropic contributions, which can significantly impact on reaction free energy landscapes.

Machine Learning in Screening High Performance Electrocatalysts for CO2 Reduction

Converting CO₂ into carbon-based fuels is promising for relieving the greenhouse gas effect and the energy crisis. However, the selectivity and efficiency of current electrocatalysts for CO₂ reductions are still not satisfactory. In this paper, the development of machine learning methods in screening CO₂ reduction electrocatalysts over the recent years is reviewed. Through high-throughput calculation of some key descriptors such as adsorption energies, d-band center, and coordination number by well-constructed machine learning models, the catalytic activity, optimal composition, active sites, and CO₂ reduction reaction pathway over various possible materials can be predicted and understood. Machine learning is now realized as a fast and low-cost method to effectively explore high performance electrocatalysts for CO₂ reduction.

Learning the Use of Artificial Intelligence in Heterogeneous Catalysis

We describe the use of artificial intelligence techniques in heterogeneous catalysis. This description is intended to give readers some clues for the use of these techniques in their research or industrial processes related to hydrodesulfurization. Since the description corresponds to supervised learning, first of all, we give a brief introduction to this type of learning, emphasizing the variables X and Y that define it. For each description, there is a particular emphasis on highlighting these variables. This emphasis will help define them when one works on a new application. The descriptions that we present relate to the construction of learning machines that infer adsorption energies, surface areas, adsorption isotherms of nanoporous materials, novel catalysts, and the sulfur content after hydrodesulfurization. These learning machines can predict adsorption energies with mean absolute errors of 0.15 eV for a diverse chemical space. They predict more precise surface areas of porous materials than the BET technique and can calculate their isotherms much faster than the Monte Carlo method. These machines can also predict new catalysts by learning from the catalytic behavior of materials generated through atomic substitutions. When the machines learn from the variables associated with a hydrodesulfurization process, they can predict the sulfur content in the final product.

Molecular Dynamics and Machine Learning in Catalysts

Given the importance of catalysts in the chemical industry, they have been extensively investigated by experimental and numerical methods. With the development of computational algorithms and computer hardware, large-scale simulations have enabled influential studies with more atomic details reflecting microscopic mechanisms. This review provides a comprehensive summary of recent developments in molecular dynamics, including ab initio molecular dynamics and reaction force-field molecular dynamics. Recent research on both approaches to catalyst calculations is reviewed, including growth, dehydrogenation, hydrogenation, oxidation reactions, bias, and recombination of carbon materials that can guide catalyst calculations. Machine learning has attracted increasing interest in recent years, and its combination with the field of catalysts has inspired promising development approaches. Its applications in machine learning potential, catalyst design, performance prediction, structure optimization, and classification have been summarized in detail. This review hopes to shed light and perspective on ML approaches in catalysts.

Machine Learning in Chemical Product Engineering: The State of the Art and a Guide for Newcomers

Chemical Product Engineering (CPE) is marked by numerous challenges, such as the complexity of the properties–structure–ingredients–process relationship of the different products and the necessity to discover and develop constantly and quickly new molecules and materials with tailor-made properties. In recent years, artificial intelligence (AI) and machine learning (ML) methods have gained increasing attention due to their performance in tackling particularly complex problems in various areas, such as computer vision and natural language processing. As such, they present a specific interest in addressing the complex challenges of CPE. This article provides an updated review of the state of the art regarding the implementation of ML techniques in different types of CPE problems with a particular focus on four specific domains, namely the design and discovery of new molecules and materials, the modeling of processes, the prediction of chemical reactions/retrosynthesis and the support for sensorial analysis. This review is further completed by general guidelines for the selection of an appropriate ML technique given the characteristics of each problem and by a critical discussion of several key issues associated with the development of ML modeling approaches. Accordingly, this paper may serve both the experienced researcher in the field as well as the newcomer.

Trends in computational molecular catalyst design

Computational methods have emerged as a powerful tool to augment traditional experimental molecular catalyst design by providing useful predictions of catalyst performance and decreasing the time needed for catalyst screening. In this perspective, we discuss three approaches for computational molecular catalyst design: (i) the reaction mechanism-based approach that calculates all relevant elementary steps, finds the rate and selectivity determining steps, and ultimately makes predictions on catalyst performance based on kinetic analysis, (ii) the descriptor-based approach where physical/chemical considerations are used to find molecular properties as predictors of catalyst performance, and (iii) the data-driven approach where statistical analysis as well as machine learning (ML) methods are used to obtain relationships between available data/features and catalyst performance. Following an introduction to these approaches, we cover their strengths and weaknesses and highlight some recent key applications. Furthermore, we present an outlook on how the currently applied approaches may evolve in the near future by addressing how recent developments in building automated computational workflows and implementing advanced ML models hold promise for reducing human workload, eliminating human bias, and speeding up computational catalyst design at the same time. Finally, we provide our viewpoint on how some of the challenges associated with the up-and-coming approaches driven by automation and ML may be resolved.

Optimizing Catalyst and Reaction Conditions in Gold(I) Catalysis-Ligand Development

This review considers phosphine and N-heterocyclic carbene complexes of gold(I) that are used as (pre)catalysts for a range of reactions in organic synthesis. These are divided according to the structure of the ligand, with the narrative focusing on studies that offer a quantitative comparison between the ligands and readily available or widely used existing systems.

Multi-Instance Learning Approach to Predictive Modeling of Catalysts Enantioselectivity

Here, we report an application of the multi-instance learning approach to predictive modeling of enantioselectivity of chiral catalysts. Catalysts were represented by ensembles of conformations encoded­ by the pmapper physicochemical descriptors capturing stereoconfiguration of the molecule. Each catalyzed chemical reaction was transformed to a condensed graph of reaction for which ISIDA fragment descriptors were generated. This approach does not require any conformations’ alignment and can potentially be used for a diverse set of catalysts bearing different scaffolds. Its efficiency has been demonstrated in predicting the selectivity of BINOL-derived phosphoric acid catalysts in asymmetric thiol addition to N-acylimines and benchmarked with previously reported models.

Rhodium chemistry: A gas phase cluster study

Due to the extraordinary catalytic activity in redox reactions, the noble metal, rhodium, has substantial industrial and laboratory applications in the production of value-added chemicals, synthesis of biomedicine, removal of automotive exhaust gas, and so on. The main drawback of rhodium catalysts is its high-cost, so it is of great importance to maximize the atomic efficiency of the precious metal by recognizing the structure-activity relationship of catalytically active sites and clarifying the root cause of the exceptional performance. This Perspective concerns the significant progress on the fundamental understanding of rhodium chemistry at a strictly molecular level by the joint experimental and computational study of the reactivity of isolated Rh-based gas phase clusters that can serve as ideal models for the active sites of condensed-phase catalysts. The substrates cover the important organic and inorganic molecules including CH₄, CO, NO, N₂, and H₂. The electronic origin for the reactivity evolution of bare Rh_x ^q clusters as a function of size is revealed. The doping effect and support effect as well as the synergistic effect among heteroatoms on the reactivity and product selectivity of Rh-containing species are discussed. The ingenious employment of diverse experimental techniques to assist the Rh₁- and Rh₂-doped clusters in catalyzing the challenging endothermic reactions is also emphasized. It turns out that the chemical behavior of Rh identified from the gas phase cluster study parallels the performance of condensed-phase rhodium catalysts. The mechanistic aspects derived from Rh-based cluster systems may provide new clues for the design of better performing rhodium catalysts including the single Rh atom catalysts.

Reaction-based machine learning representations for predicting the enantioselectivity of organocatalysts

Hundreds of catalytic methods are developed each year to meet the demand for high-purity chiral compounds. The computational design of enantioselective organocatalysts remains a significant challenge, as catalysts are typically discovered through experimental screening. Recent advances in combining quantum chemical computations and machine learning (ML) hold great potential to propel the next leap forward in asymmetric catalysis. Within the context of quantum chemical machine learning (QML, or atomistic ML), the ML representations used to encode the three-dimensional structure of molecules and evaluate their similarity cannot easily capture the subtle energy differences that govern enantioselectivity. Here, we present a general strategy for improving molecular representations within an atomistic machine learning model to predict the DFT-computed enantiomeric excess of asymmetric propargylation organocatalysts solely from the structure of catalytic cycle intermediates. Mean absolute errors as low as 0.25 kcal mol-1 were achieved in predictions of the activation energy with respect to DFT computations. By virtue of its design, this strategy is generalisable to other ML models, to experimental data and to any catalytic asymmetric reaction, enabling the rapid screening of structurally diverse organocatalysts from available structural information.

Machine Learning-Enabled Design and Prediction of Protein Resistance on Self-Assembled Monolayers and Beyond

The rational design of highly antifouling materials is crucial for a wide range of fundamental research and practical applications. The immense variety and complexity of the intrinsic physicochemical properties of materials (i.e., chemical structure, hydrophobicity, charge distribution, and molecular weight) and their surface coating properties (i.e., packing density, film thickness and roughness, and chain conformation) make it challenging to rationally design antifouling materials and reveal their fundamental structure-property relationships. In this work, we developed a data-driven machine learning model, a combination of factor analysis of functional group (FAFG), Pearson analysis, random forest (RF) and artificial neural network (ANN) algorithms, and Bayesian statistics, to computationally extract structure/chemical/surface features in correlation with the antifouling activity of self-assembled monolayers (SAMs) from a self-construction data set. The resultant model demonstrates the robustness of Q_CV² = 0.90 and RMSE_CV = 0.21 and the predictive ability of Q_ext² = 0.84 and RMSE_ext = 0.28, determines key descriptors and functional groups important for the antifouling activity, and enables to design original antifouling SAMs using the predicted antifouling functional groups. Three computationally designed molecules were further coated onto the surfaces in different forms of SAMs and polymer brushes. The resultant coatings with negative fouling indexes exhibited strong surface resistance to protein adsorption from undiluted blood serum and plasma, validating the model predictions. The data-driven machine learning model demonstrates their design and predictive capacity for next-generation antifouling materials and surfaces, which hopefully help to accelerate the discovery and understanding of functional materials.

Machine Learning Enables Selection of Epistatic Enzyme Mutants for Stability Against Unfolding and Detrimental Aggregation

Machine learning (ML) has pervaded most areas of protein engineering, including stability and stereoselectivity. Using limonene epoxide hydrolase as the model enzyme and innov'SAR as the ML platform, comprising a digital signal process, we achieved high protein robustness that can resist unfolding with concomitant detrimental aggregation. Fourier transform (FT) allows us to take into account the order of the protein sequence and the nonlinear interactions between positions, and thus to grasp epistatic phenomena. The innov'SAR approach is interpolative, extrapolative and makes outside-the-box, predictions not found in other state-of-the-art ML or deep learning approaches. Equally significant is the finding that our approach to ML in the present context, flanked by advanced molecular dynamics simulations, uncovers the connection between epistatic mutational interactions and protein robustness.