Machine learning meets volcano plots: computational discovery of cross-coupling catalysts

Augmenting genetic algorithms with machine learning for inverse molecular design

Evolutionary and machine learning methods have been successfully applied to the generation of molecules and materials exhibiting desired properties. The combination of these two paradigms in inverse design tasks can yield powerful methods that explore massive chemical spaces more efficiently, improving the quality of the generated compounds. However, such synergistic approaches are still an incipient area of research and appear underexplored in the literature. This perspective covers different ways of incorporating machine learning approaches into evolutionary learning frameworks, with the overall goal of increasing the optimization efficiency of genetic algorithms. In particular, machine learning surrogate models for faster fitness function evaluation, discriminator models to control population diversity on-the-fly, machine learning based crossover operations, and evolution in latent space are discussed. The further potential of these synergistic approaches in generative tasks is also assessed, outlining promising directions for future developments.

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.

Discovery of molybdenum based nitrogen fixation catalysts with genetic algorithms

Computational discovery of organometallic catalysts that effectively catalyze nitrogen fixation is a difficult task. The complexity of the chemical reactions involved and the lack of understanding of natures enzyme catalysts raises the need for intricate computational models. In this study, we use a dataset of 91 experimentally verified ligands as starting population for a Genetic Algorithm (GA) and use this to discover molybdenum based nitrogen fixation catalyst in trigonal bipyramidal and octahedral configurations. Through evolutionary discovery with a semi-empirical quantum method driven GA and a density functional theory (DFT) based screening process, we find 3 promising catalyst candidates that are shown to effectively catalyze the first protonation step of the Schrock cycle. Synthetic accessibility (SA) scores are used to guide the GA towards reasonable ligands and the work features a description of the GA framework, including pre-screening of catalyst candidates that involves assignment of metal coordination atoms and catalyst stereoisomers. This research thus not only offers insights into the specific field of molybdenum-based catalysts for nitrogen fixation but also demonstrates the broader applicability and potential of genetic algorithms in the field of catalyst discovery and materials science.

Microkinetic Molecular Volcano Plots for Enhanced Catalyst Selectivity and Activity Predictions

Molecular volcano plots, which facilitate the rapid prediction of the activity and selectivity of prospective catalysts, have emerged as powerful tools for computational catalysis. Here, we integrate microkinetic modeling into the volcano plot framework to develop "microkinetic molecular volcano plots". The resulting unified computational framework allows the influence of important reaction parameters, including temperature, reaction time, and concentration, to be quickly incorporated and more complex situations, such as off-cycle resting states and coupled catalytic cycles, to be tackled. Compared to previous generations of molecular volcanoes, these microkinetic counterparts offer a more comprehensive understanding of catalytic behavior, in which selectivity and product ratios can be explicitly determined by tracking the evolution of each product concentration over time. This is demonstrated by examining two case studies, rhodium-catalyzed hydroformylation and metal-catalyzed hydrosilylation, in which the unique insights provided by microkinetic modeling, as well as the ability to simultaneously screen catalysts and reaction conditions, are highlighted. To facilitate the construction of these plots/maps, we introduce mikimo, a Python program that seamlessly integrates with our previously developed automated volcano builder, volcanic.

In Silico Chemical Experiments in the Age of AI: From Quantum Chemistry to Machine Learning and Back

Computational chemistry is an indispensable tool for understanding molecules and predicting chemical properties. However, traditional computational methods face significant challenges due to the difficulty of solving the Schrödinger equations and the increasing computational cost with the size of the molecular system. In response, there has been a surge of interest in leveraging artificial intelligence (AI) and machine learning (ML) techniques to in silico experiments. Integrating AI and ML into computational chemistry increases the scalability and speed of the exploration of chemical space. However, challenges remain, particularly regarding the reproducibility and transferability of ML models. This review highlights the evolution of ML in learning from, complementing, or replacing traditional computational chemistry for energy and property predictions. Starting from models trained entirely on numerical data, a journey set forth toward the ideal model incorporating or learning the physical laws of quantum mechanics. This paper also reviews existing computational methods and ML models and their intertwining, outlines a roadmap for future research, and identifies areas for improvement and innovation. Ultimately, the goal is to develop AI architectures capable of predicting accurate and transferable solutions to the Schrödinger equation, thereby revolutionizing in silico experiments within chemistry and materials science.

Paving the road towards automated homogeneous catalyst design

In the past decade, computational tools have become integral to catalyst design. They continue to offer significant support to experimental organic synthesis and catalysis researchers aiming for optimal reaction outcomes. More recently, data-driven approaches utilizing machine learning have garnered considerable attention for their expansive capabilities. This Perspective provides an overview of diverse initiatives in the realm of computational catalyst design and introduces our automated tools tailored for high-throughput in silico exploration of the chemical space. While valuable insights are gained through methods for high-throughput in silico exploration and analysis of chemical space, their degree of automation and modularity are key. We argue that the integration of data-driven, automated and modular workflows is key to enhancing homogeneous catalyst design on an unprecedented scale, contributing to the advancement of catalysis research.

A bridge between trust and control: computational workflows meet automated battery cycling

Compliance with good research data management practices means trust in the integrity of the data, and it is achievable by full control of the data gathering process. In this work, we demonstrate tooling which bridges these two aspects, and illustrate its use in a case study of automated battery cycling. We successfully interface off-the-shelf battery cycling hardware with the computational workflow management software AiiDA, allowing us to control experiments, while ensuring trust in the data by tracking its provenance. We design user interfaces compatible with this tooling, which span the inventory, experiment design, and result analysis stages. Other features, including monitoring of workflows and import of externally generated and legacy data are also implemented. Finally, the full software stack required for this work is made available in a set of open-source packages.

Accessing the usefulness of atomic adsorption configurations in predicting the adsorption properties of molecules with machine learning

We present a systematic study into the effect of adding atomic adsorption configurations into the training and validation dataset for a neural network's predictions of the adsorption energies of small molecules on single metal and bimetallic, single crystal surfaces. Specifically, we examine the efficacy of models trained with and without H and X atomic adsorption configurations, where X is C, N, or O, to predict XHn adsorption energies. In addition, we compare our machine learning models to traditional simple scaling relationships. We find that models trained with the atomic adsorption configurations outperform models trained with only molecular adsorption configurations, with as much as a 0.37 eV decrease in the MAE. We find that models trained with the atomic adsorption configurations slightly outperform traditional scaling relationships. In general, these results suggest it may be possible to vastly reduce the number of adsorption configurations one needs for training and validation datasets by supplementing said data with the adsorption configurations of composite atoms or smaller molecular fragments.

Latent Variable Machine Learning Framework for Catalysis: General Models, Transfer Learning, and Interpretability

Machine learning has been successfully applied in recent years to screen materials for a variety of applications. However, despite recent advances, most screening-based machine learning approaches are limited in generality and transferability, requiring new models to be created from scratch for each new application. This is particularly apparent in catalysis, where there are many possible intermediates and transition states of interest in addition to a large number of potential catalytic materials. In this work, we developed a new machine learning framework that is built on chemical principles and allows the creation of general, interpretable, reusable models. Our new architecture uses latent variables to create a set of submodels that each take on a relatively simple learning task, leading to higher data efficiency and promoting transfer learning. This architecture infuses fundamental chemical principles, such as the existence of elements as discrete entities. We show that this architecture allows for the creation of models that can be reused for many different applications, providing significant improvements in efficiency and convenience. For example, our architecture allows simultaneous prediction of adsorption energies for many adsorbates on a broad array of alloy surfaces with mean absolute errors (MAEs) around 0.20-0.25 eV. The integration of latent variables provides physical interpretability, as predictions can be explained in terms of the learned chemical environment as represented by the latent space. Further, these latent variables also serve as new feature representations, allowing efficient transfer learning. For example, new models with useful levels of accuracy can be created with less than 10 data points, including transfer learning to an experimental data set with an MAE less than 0.15 eV. Lastly, we show that our new machine learning architecture is general and robust enough to handle heterogeneous and multifidelity data sets, allowing researchers to leverage existing data sets to speed up screening using their own computational setup.

Zeolite encapsulated organometallic complexes as model catalysts

Heterogeneities in the structure of active centers in metal-containing porous materials are unavoidable and complicate the description of chemical events occurring along reaction coordinates at the atomic level. Metal containing zeolites include sites of varied local coordination and secondary confining environments, requiring careful titration protocols to quantify the predominant active sites. Hybrid organometallic-zeolite catalysts are useful well-defined platform materials for spectroscopic, kinetic, and computational studies of heterogeneous catalysis that avoid the complications of conventional metal-containing porous materials. Such materials have been synthesized and studied previously, but catalytic applications were mostly limited to liquid-phase oxidation and electrochemical reactions. The hydrothermal stability, time-on-stream stability, and utility of these materials in gas-phase oxidation reactions are under-studied. The potential applications for single-site heterogeneous catalysts in fundamental research are abundant and motivate future synthetic, spectroscopic, kinetic, and computational studies.

Combining Molecular Quantum Mechanical Modeling and Machine Learning for Accelerated Reaction Screening and Discovery

Molecular quantum mechanical modeling, accelerated by machine learning, has opened the door to high-throughput screening campaigns of complex properties, such as the activation energies of chemical reactions and absorption/emission spectra of materials and molecules; in silico. Here, we present an overview of the main principles, concepts, and design considerations involved in such hybrid computational quantum chemistry/machine learning screening workflows, with a special emphasis on some recent examples of their successful application. We end with a brief outlook of further advances that will benefit the field.

Machine Learning and Quantum Calculation for Predicting Yield in Cu-Catalyzed P-H Reactions

The paper discussed the use of machine learning (ML) and quantum chemistry calculations to predict the transition state and yield of copper-catalyzed P-H insertion reactions. By analyzing a dataset of 120 experimental data points, the transition state was determined using density functional theory (DFT). ML algorithms were then applied to analyze 16 descriptors derived from the quantum chemical transition state to predict the product yield. Among the algorithms studied, the Support Vector Machine (SVM) achieved the highest prediction accuracy of 97%, with over 80% correlation in Leave-One-Out Cross-Validation (LOOCV). Sensitivity analysis was performed on each descriptor, and a comprehensive investigation of the reaction mechanism was conducted to better understand the transition state characteristics. Finally, the ML model was used to predict reaction plans for experimental design, demonstrating strong predictive performance in subsequent experimental validation.

Designing catalysts with deep generative models and computational data. A case study for Suzuki cross coupling reactions

The need for more efficient catalytic processes is ever-growing, and so are the costs associated with experimentally searching chemical space to find new promising catalysts. Despite the consolidated use of density functional theory (DFT) and other atomistic models for virtually screening molecules based on their simulated performance, data-driven approaches are rising as indispensable tools for designing and improving catalytic processes. Here, we present a deep learning model capable of generating new catalyst-ligand candidates by self-learning meaningful structural features solely from their language representation and computed binding energies. We train a recurrent neural network-based Variational Autoencoder (VAE) to compress the molecular representation of the catalyst into a lower dimensional latent space, in which a feed-forward neural network predicts the corresponding binding energy to be used as the optimization function. The outcome of the optimization in the latent space is then reconstructed back into the original molecular representation. These trained models achieve state-of-the-art predictive performances in catalysts' binding energy prediction and catalysts' design, with a mean absolute error of 2.42 kcal mol-1 and an ability to generate 84% valid and novel catalysts.

Neural network potentials for accelerated metadynamics of oxygen reduction kinetics at Au-water interfaces

The application of ab initio molecular dynamics (AIMD) for the explicit modeling of reactions at solid-liquid interfaces in electrochemical energy conversion systems like batteries and fuel cells can provide new understandings towards reaction mechanisms. However, its prohibitive computational cost severely restricts the time- and length-scales of AIMD. Equivariant graph neural network (GNN) based accurate surrogate potentials can accelerate the speed of performing molecular dynamics after learning on representative structures in a data efficient manner. In this study, we combined uncertainty-aware GNN potentials and enhanced sampling to investigate the reactive process of the oxygen reduction reaction (ORR) at an Au(100)-water interface. By using a well-established active learning framework based on CUR matrix decomposition, we can evenly sample equilibrium structures from MD simulations and non-equilibrium reaction intermediates that are rarely visited during the reaction. The trained GNNs have shown exceptional performance in terms of force prediction accuracy, the ability to reproduce structural properties, and low uncertainties when performing MD and metadynamics simulations. Furthermore, the collective variables employed in this work enabled the automatic search of reaction pathways and provide a detailed understanding towards the ORR reaction mechanism on Au(100). Our simulations identified the associative reaction mechanism without the presence of *O and a low reaction barrier of 0.3 eV, which is in agreement with experimental findings. The methodology employed in this study can pave the way for modeling complex chemical reactions at electrochemical interfaces with an explicit solvent under ambient conditions.

Benchmark of general-purpose machine learning-based quantum mechanical method AIQM1 on reaction barrier heights

Artificial intelligence-enhanced quantum mechanical method 1 (AIQM1) is a general-purpose method that was shown to achieve high accuracy for many applications with a speed close to its baseline semiempirical quantum mechanical (SQM) method ODM2*. Here, we evaluate the hitherto unknown performance of out-of-the-box AIQM1 without any refitting for reaction barrier heights on eight datasets, including a total of ∼24 thousand reactions. This evaluation shows that AIQM1's accuracy strongly depends on the type of transition state and ranges from excellent for rotation barriers to poor for, e.g., pericyclic reactions. AIQM1 clearly outperforms its baseline ODM2* method and, even more so, a popular universal potential, ANI-1ccx. Overall, however, AIQM1 accuracy largely remains similar to SQM methods (and B3LYP/6-31G* for most reaction types) suggesting that it is desirable to focus on improving AIQM1 performance for barrier heights in the future. We also show that the built-in uncertainty quantification helps in identifying confident predictions. The accuracy of confident AIQM1 predictions is approaching the level of popular density functional theory methods for most reaction types. Encouragingly, AIQM1 is rather robust for transition state optimizations, even for the type of reactions it struggles with the most. Single-point calculations with high-level methods on AIQM1-optimized geometries can be used to significantly improve barrier heights, which cannot be said for its baseline ODM2* method.

Predictive chemistry: machine learning for reaction deployment, reaction development, and reaction discovery

The field of predictive chemistry relates to the development of models able to describe how molecules interact and react. It encompasses the long-standing task of computer-aided retrosynthesis, but is far more reaching and ambitious in its goals. In this review, we summarize several areas where predictive chemistry models hold the potential to accelerate the deployment, development, and discovery of organic reactions and advance synthetic chemistry.

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

Constructing and interpreting volcano plots and activity maps to navigate homogeneous catalyst landscapes

Volcano plots and activity maps are powerful tools for studying homogeneous catalysis. Once constructed, they can be used to estimate and predict the performance of a catalyst from one or more descriptor variables. The relevance and utility of these tools has been demonstrated in several areas of catalysis, with recent applications to homogeneous catalysts having been pioneered by our research group. Both volcano plots and activity maps are built from linear free energy scaling relationships that connect the value of a descriptor variable(s) with the relative energies of other catalytic cycle intermediates/transition states. These relationships must be both constructed and postprocessed appropriately to obtain the resulting plots/maps; this process requires careful execution to obtain meaningful results. In this protocol, we provide a step-by-step guide to building volcano plots and activity maps using curated reaction profile data. The reaction profile data are obtained using density functional theory computations to model the catalytic cycle. In addition, we provide volcanic, a Python code that automates the steps of the process following data acquisition. Unlike the computation of individual reaction energy profiles, our tools lead to a holistic view of homogeneous catalyst performance that can be broadly applied for both explanatory and screening purposes.

Machine learning-based analysis of overall stability constants of metal-ligand complexes

The stability constants of metal(M)-ligand(L) complexes are industrially important because they affect the quality of the plating film and the efficiency of metal separation. Thus, it is desirable to develop an effective screening method for promising ligands. Although there have been several machine-learning approaches for predicting stability constants, most of them focus only on the first overall stability constant of M-L complexes, and the variety of cations is also limited to less than 20. In this study, two Gaussian process regression models are developed to predict the first overall stability constant and the n-th (n > 1) overall stability constants. Furthermore, the feature relevance is quantitatively evaluated via sensitivity analysis. As a result, the electronegativities of both metal and ligand are found to be the most important factor for predicting the first overall stability constant. Interestingly, the predicted value of the first overall stability constant shows the highest correlation with the n-th overall stability constant of the corresponding M-L pair. Finally, the number of features is optimized using validation data where the ligands are not included in the training data, which indicates high generalizability. This study provides valuable insights and may help accelerate molecular screening and design for various applications.

Machine learning and semi-empirical calculations: a synergistic approach to rapid, accurate, and mechanism-based reaction barrier prediction

Modern QM modelling methods, such as DFT, have provided detailed mechanistic insights into countless reactions. However, their computational cost inhibits their ability to rapidly screen large numbers of substrates and catalysts in reaction discovery. For a C-C bond forming nitro-Michael addition, we introduce a synergistic semi-empirical quantum mechanical (SQM) and machine learning (ML) approach that allows the prediction of DFT-quality reaction barriers in minutes, even on a standard laptop using widely available modelling software. Mean absolute errors (MAEs) are obtained that are below the accepted chemical accuracy threshold of 1 kcal mol-1 and substantially better than SQM methods without ML correction (5.71 kcal mol-1). Predictive power is shown to hold when the ML models are applied to an unseen set of compounds from the toxicology literature. Mechanistic insight is also achieved via the generation of full SQM transition state (TS) structures which are found to be very good approximations for the DFT-level geometries, revealing important steric interactions in some TSs. This combination of speed, accuracy, and mechanistic insight is unprecedented; current ML barrier models compromise on at least one of these important criteria.

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.

New Strategies for Direct Methane-to-Methanol Conversion from Active Learning Exploration of 16 Million Catalysts

Despite decades of effort, no earth-abundant homogeneous catalysts have been discovered that can selectively oxidize methane to methanol. We exploit active learning to simultaneously optimize methane activation and methanol release calculated with machine learning-accelerated density functional theory in a space of 16 M candidate catalysts including novel macrocycles. By constructing macrocycles from fragments inspired by synthesized compounds, we ensure synthetic realism in our computational search. Our large-scale search reveals that low-spin Fe(II) compounds paired with strong-field (e.g., P or S-coordinating) ligands have among the best energetic tradeoffs between hydrogen atom transfer (HAT) and methanol release. This observation contrasts with prior efforts that have focused on high-spin Fe(II) with weak-field ligands. By decoupling equatorial and axial ligand effects, we determine that negatively charged axial ligands are critical for more rapid release of methanol and that higher-valency metals [i.e., M(III) vs M(II)] are likely to be rate-limited by slow methanol release. With full characterization of barrier heights, we confirm that optimizing for HAT does not lead to large oxo formation barriers. Energetic span analysis reveals designs for an intermediate-spin Mn(II) catalyst and a low-spin Fe(II) catalyst that are predicted to have good turnover frequencies. Our active learning approach to optimize two distinct reaction energies with efficient global optimization is expected to be beneficial for the search of large catalyst spaces where no prior designs have been identified and where linear scaling relationships between reaction energies or barriers may be limited or unknown.

Applications of Machine Learning in Alloy Catalysts: Rational Selection and Future Development of Descriptors

At present, alloys have broad application prospects in heterogeneous catalysis, due to their various catalytic active sites produced by their vast element combinations and complex geometric structures. However, it is the diverse variables of alloys that lead to the difficulty in understanding the structure-property relationship for conventional experimental and theoretical methods. Fortunately, machine learning methods are helpful to address the issue. Machine learning can not only deal with a large number of data rapidly, but also help establish the physical picture of reactions in multidimensional heterogeneous catalysis. The key challenge in machine learning is the exploration of suitable general descriptors to accurately describe various types of alloy catalysts, which help reasonably design catalysts and efficiently screen candidates. In this review, several kinds of machine learning methods commonly used in the design of alloy catalysts is introduced, and the applications of various reactivity descriptors corresponding to different alloy systems is summarized. Importantly, this work clarifies the existing understanding of physical picture of heterogeneous catalysis, and emphasize the significance of rational selection of universal descriptors. Finally, the development of heterogeneous catalytic descriptors for machine learning are presented.

Assessing the persistence of chalcogen bonds in solution with neural network potentials

Non-covalent bonding patterns are commonly harvested as a design principle in the field of catalysis, supramolecular chemistry and functional materials to name a few. Yet, their computational description generally neglects finite temperature and environment effects, which promote competing interactions and alter their static gas-phase properties. Recently, neural network potentials (NNPs) trained on Density Functional Theory (DFT) data have become increasingly popular to simulate molecular phenomena in condensed phase with an accuracy comparable to ab initio methods. To date, most applications have centered on solid-state materials or fairly simple molecules made of a limited number of elements. Herein, we focus on the persistence and strength of chalcogen bonds involving a benzotelluradiazole in condensed phase. While the tellurium-containing heteroaromatic molecules are known to exhibit pronounced interactions with anions and lone pairs of different atoms, the relevance of competing intermolecular interactions, notably with the solvent, is complicated to monitor experimentally but also challenging to model at an accurate electronic structure level. Here, we train direct and baselined NNPs to reproduce hybrid DFT energies and forces in order to identify what are the most prevalent non-covalent interactions occurring in a solute-Cl$^-$-THF mixture. The simulations in explicit solvent highlight competition with chalcogen bonds formed with the solvent and the short-range directionality of the interaction with direct consequences for the molecular properties in the solution. The comparison with other potentials (e.g., AMOEBA, direct NNP and continuum solvent model) also demonstrates that baselined NNPs offer a reliable picture of the non-covalent interaction interplay occurring in solution.

Local Kernel Regression and Neural Network Approaches to the Conformational Landscapes of Oligopeptides

The application of machine learning to theoretical chemistry has made it possible to combine the accuracy of quantum chemical energetics with the thorough sampling of finite-temperature fluctuations. To reach this goal, a diverse set of methods has been proposed, ranging from simple linear models to kernel regression and highly nonlinear neural networks. Here we apply two widely different approaches to the same, challenging problem: the sampling of the conformational landscape of polypeptides at finite temperature. We develop a local kernel regression (LKR) coupled with a supervised sparsity method and compare it with a more established approach based on Behler-Parrinello type neural networks. In the context of the LKR, we discuss how the supervised selection of the reference pool of environments is crucial to achieve accurate potential energy surfaces at a competitive computational cost and leverage the locality of the model to infer which chemical environments are poorly described by the DFTB baseline. We then discuss the relative merits of the two frameworks and perform Hamiltonian-reservoir replica-exchange Monte Carlo sampling and metadynamics simulations, respectively, to demonstrate that both frameworks can achieve converged and transferable sampling of the conformational landscape of complex and flexible biomolecules with comparable accuracy and computational cost.

Quantum chemistry-augmented neural networks for reactivity prediction: Performance, generalizability, and explainability

There is a perceived dichotomy between structure-based and descriptor-based molecular representations used for predictive chemistry tasks. Here, we study the performance, generalizability, and explainability of the quantum mechanics-augmented graph neural network (ml-QM-GNN) architecture as applied to the prediction of regioselectivity (classification) and of activation energies (regression). In our hybrid QM-augmented model architecture, structure-based representations are first used to predict a set of atom- and bond-level reactivity descriptors derived from density functional theory calculations. These estimated reactivity descriptors are combined with the original structure-based representation to make the final reactivity prediction. We demonstrate that our model architecture leads to significant improvements over structure-based GNNs in not only overall accuracy but also in generalization to unseen compounds. Even when provided training sets of only a couple hundred labeled data points, the ml-QM-GNN outperforms other state-of-the-art structure-based architectures that have been applied to these tasks as well as descriptor-based (linear) regressions. As a primary contribution of this work, we demonstrate a bridge between data-driven predictions and conceptual frameworks commonly used to gain qualitative insights into reactivity phenomena, taking advantage of the fact that our models are grounded in (but not restricted to) QM descriptors. This effort results in a productive synergy between theory and data science, wherein QM-augmented models provide a data-driven confirmation of previous qualitative analyses, and these analyses in turn facilitate insights into the decision-making process occurring within ml-QM-GNNs.

Emerging Landscape of Computational Modeling in Pharmaceutical Development

Computational chemistry applications have become an integral part of the drug discovery workflow over the past 35 years. However, computational modeling in support of drug development has remained a relatively uncharted territory for a significant part of both academic and industrial communities. This review considers the computational modeling workflows for three key components of drug preclinical and clinical development, namely, process chemistry, analytical research and development, as well as drug product and formulation development. An overview of the computational support for each step of the respective workflows is presented. Additionally, in context of solid form design, special consideration is given to modern physics-based virtual screening methods. This covers rational approaches to polymorph, coformer, counterion, and solvent virtual screening in support of solid form selection and design.

Machine Learning for the Discovery, Design, and Engineering of Materials

Machine learning (ML) has become a part of the fabric of high-throughput screening and computational discovery of materials. Despite its increasingly central role, challenges remain in fully realizing the promise of ML. This is especially true for the practical acceleration of the engineering of robust materials and the development of design strategies that surpass trial and error or high-throughput screening alone. Depending on the quantity being predicted and the experimental data available, ML can either outperform physics-based modes, be used to accelerate such models, or be integrated with them to improve their performance. We cover recent advances in algorithms and in their application that are starting to make inroads toward (a) the discovery of new materials through large-scale enumerative screening, (b) the design of materials through identification of rules and principles that govern materials properties, and (c) the engineering of practical materials by satisfying multiple objectives. We conclude with opportunities for further advancement to realize ML as a widespread tool for practical computational materials design. Expected final online publication date for the Annual Review of Chemical and Biomolecular Engineering, Volume 13 is October 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Volcano Plots of Reaction Yields in Cross-Coupling Catalysis

It is critical to identify the influence of phosphine ligands on cross-coupling reactions to obtain a higher yield. In order to reveal ligands' effects, many descriptors have been proposed, which allow statistical analysis to be implemented in mining the structure-property relationship and providing mechanistic insights. This work combines the steric and electronic effects into a descriptor, %V_bur (min) - 3·HOMO-LUMO gap (eV) where %V_bur (min) is the minimum percent buried volume and the Boltzmann averaged gap is used. Volcano plots were well presented by yields (y-axis) and the descriptor (x-axis) for Ni- and Pd-catalyzed cross-coupling reactions. In addition, volcano peaks in these plots can be located to optimize reaction yields for experiments. Our work sheds light on the reaction mechanisms of phosphine ligands and delivers a strategy for choosing ligands in cross-coupling catalysis.

Autonomous Reaction Network Exploration in Homogeneous and Heterogeneous Catalysis

Autonomous computations that rely on automated reaction network elucidation algorithms may pave the way to make computational catalysis on a par with experimental research in the field. Several advantages of this approach are key to catalysis: (i) automation allows one to consider orders of magnitude more structures in a systematic and open-ended fashion than what would be accessible by manual inspection. Eventually, full resolution in terms of structural varieties and conformations as well as with respect to the type and number of potentially important elementary reaction steps (including decomposition reactions that determine turnover numbers) may be achieved. (ii) Fast electronic structure methods with uncertainty quantification warrant high efficiency and reliability in order to not only deliver results quickly, but also to allow for predictive work. (iii) A high degree of autonomy reduces the amount of manual human work, processing errors, and human bias. Although being inherently unbiased, it is still steerable with respect to specific regions of an emerging network and with respect to the addition of new reactant species. This allows for a high fidelity of the formalization of some catalytic process and for surprising in silico discoveries. In this work, we first review the state of the art in computational catalysis to embed autonomous explorations into the general field from which it draws its ingredients. We then elaborate on the specific conceptual issues that arise in the context of autonomous computational procedures, some of which we discuss at an example catalytic system.

GRAPHICAL ABSTRACT

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s11244-021-01543-9.

A reactivity model for oxidative addition to palladium enables quantitative predictions for catalytic cross-coupling reactions

Making accurate, quantitative predictions of chemical reactivity based on molecular structure is an unsolved problem in chemical synthesis, particularly for complex molecules. We report an approach to reactivity prediction for...

The Evolution of Data-Driven Modeling in Organic Chemistry

Organic chemistry is replete with complex relationships: for example, how a reactant's structure relates to the resulting product formed; how reaction conditions relate to yield; how a catalyst's structure relates to enantioselectivity. Questions like these are at the foundation of understanding reactivity and developing novel and improved reactions. An approach to probing these questions that is both longstanding and contemporary is data-driven modeling. Here, we provide a synopsis of the history of data-driven modeling in organic chemistry and the terms used to describe these endeavors. We include a timeline of the steps that led to its current state. The case studies included highlight how, as a community, we have advanced physical organic chemistry tools with the aid of computers and data to augment the intuition of expert chemists and to facilitate the prediction of structure-activity and structure-property relationships.

Deciphering Cryptic Behavior in Bimetallic Transition-Metal Complexes with Machine Learning

We demonstrate an alternative, data-driven approach to uncovering structure-property relationships for the rational design of heterobimetallic transition-metal complexes that exhibit metal-metal bonding. We tailor graph-based representations of the metal-local environment for these complexes for use in multiple linear regression and kernel ridge regression (KRR) models. We curate a set of 28 experimentally characterized complexes to develop a multiple linear regression model for oxidation potentials. We achieve good accuracy (mean absolute error of 0.25 V) and preserve transferability to unseen experimental data with a new ligand structure. We also train a KRR model on a subset of 330 structurally characterized heterobimetallics to predict the degree of metal-metal bonding. This KRR model predicts relative metal-metal bond lengths in the test set to within 5%, and analysis of key features reveals the fundamental atomic contributions (e.g., the valence electron configuration) that most strongly influence the behavior of these complexes. Our work provides guidance for rational bimetallic design, suggesting that properties, including the formal shortness ratio, should be transferable from one period to another.

Machine Learning to Predict Diels-Alder Reaction Barriers from the Reactant State Electron Density

Reaction barriers are key to our understanding of chemical reactivity and catalysis. Certain reactions are so seminal in chemistry that countless variants, with or without catalysts, have been studied, and their barriers have been computed or measured experimentally. This wealth of data represents a perfect opportunity to leverage machine learning models, which could quickly predict barriers without explicit calculations or measurement. Here, we show that the topological descriptors of the quantum mechanical charge density in the reactant state constitute a set that is both rigorous and continuous and can be used effectively for the prediction of reaction barrier energies to a high degree of accuracy. We demonstrate this on the Diels-Alder reaction, highly important in biology and medicinal chemistry, and as such, studied extensively. This reaction exhibits a range of barriers as large as 270 kJ/mol. While we trained our single-objective supervised (labeled) regression algorithms on simpler Diels-Alder reactions in solution, they predict reaction barriers also in significantly more complicated contexts, such a Diels-Alder reaction catalyzed by an artificial enzyme and its evolved variants, in agreement with experimental changes in k_cat. We expect this tool to apply broadly to a variety of reactions in solution or in the presence of a catalyst, for screening and circumventing heavily involved computations or experiments.

Combining artificial intelligence and physics-based modeling to directly assess atomic site stabilities: from sub-nanometer clusters to extended surfaces

The performance of functional materials is dictated by chemical and structural properties of individual atomic sites. In catalysts, for example, the thermodynamic stability of constituting atomic sites is a key descriptor from which more complex properties, such as molecular adsorption energies and reaction rates, can be derived. In this study, we present a widely applicable machine learning (ML) approach to instantaneously compute the stability of individual atomic sites in structurally and electronically complex nano-materials. Conventionally, we determine such site stabilities using computationally intensive first-principles calculations. With our approach, we predict the stability of atomic sites in sub-nanometer metal clusters of 3-55 atoms with mean absolute errors in the range of 0.11-0.14 eV. To extract physical insights from the ML model, we introduce a genetic algorithm (GA) for feature selection. This algorithm distills the key structural and chemical properties governing the stability of atomic sites in size-selected nanoparticles, allowing for physical interpretability of the models and revealing structure-property relationships. The results of the GA are generally model and materials specific. In the limit of large nanoparticles, the GA identifies features consistent with physics-based models for metal-metal interactions. By combining the ML model with the physics-based model, we predict atomic site stabilities in real time for structures ranging from sub-nanometer metal clusters (3-55 atom) to larger nanoparticles (147 to 309 atoms) to extended surfaces using a physically interpretable framework. Finally, we present a proof of principle showcasing how our approach can determine stable and active nanocatalysts across a generic materials space of structure and composition.

Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems

Machine learning models are poised to make a transformative impact on chemical sciences by dramatically accelerating computational algorithms and amplifying insights available from computational chemistry methods. However, achieving this requires a confluence and coaction of expertise in computer science and physical sciences. This Review is written for new and experienced researchers working at the intersection of both fields. We first provide concise tutorials of computational chemistry and machine learning methods, showing how insights involving both can be achieved. We follow with a critical review of noteworthy applications that demonstrate how computational chemistry and machine learning can be used together to provide insightful (and useful) predictions in molecular and materials modeling, retrosyntheses, catalysis, and drug design.

Uncovering the Activity of Alkaline Earth Metal Hydrogenation Catalysis Through Molecular Volcano Plots

Recent advances in alkaline earth (Ae) metal hydrogenation catalysis have broadened the spectrum of potential catalysts to include candidates from the main group, providing a sustainable alternative to the commonly used transition metals. Although Ae-amides have already been demonstrated to catalyze hydrogenation of imines and alkenes, a lucid understanding of how different metal/ligand combinations influence the catalytic activity is yet to be established. In this article, we use linear scaling relationships and molecular volcano plots to assess the potential of the Ae metal-based catalysts for the hydrogenation of alkenes. By analyzing combinations of eight metals (mono-, bi-, tri-, and tetravalent) and seven ligands, we delineate the impact of metal-ligand interplay on the hydrogenation activity. Our findings highlight that the catalytic activity is majorly determined by the charge and the size of the metal ions. While bivalent Ae metal cations delicately regulate the binding and the release of the reactants and the products, respectively, providing the right balance for this reaction, ligands play only a minor role in determining their catalytic activity. We show how volcano plots can be utilized for the rapid screening of prospective Ae catalysts to establish a guideline to achieve maximum activity in facilitating the hydrogenation process.

SUPPLEMENTARY INFORMATION

The online version of this article at 10.1007/s11244-021-01480-7.

Ab Initio Machine Learning in Chemical Compound Space

Chemical compound space (CCS), the set of all theoretically conceivable combinations of chemical elements and (meta-)stable geometries that make up matter, is colossal. The first-principles based virtual sampling of this space, for example, in search of novel molecules or materials which exhibit desirable properties, is therefore prohibitive for all but the smallest subsets and simplest properties. We review studies aimed at tackling this challenge using modern machine learning techniques based on (i) synthetic data, typically generated using quantum mechanics based methods, and (ii) model architectures inspired by quantum mechanics. Such Quantum mechanics based Machine Learning (QML) approaches combine the numerical efficiency of statistical surrogate models with an ab initio view on matter. They rigorously reflect the underlying physics in order to reach universality and transferability across CCS. While state-of-the-art approximations to quantum problems impose severe computational bottlenecks, recent QML based developments indicate the possibility of substantial acceleration without sacrificing the predictive power of quantum mechanics.

Computational Discovery of Transition-metal Complexes: From High-throughput Screening to Machine Learning

Transition-metal complexes are attractive targets for the design of catalysts and functional materials. The behavior of the metal-organic bond, while very tunable for achieving target properties, is challenging to predict and necessitates searching a wide and complex space to identify needles in haystacks for target applications. This review will focus on the techniques that make high-throughput search of transition-metal chemical space feasible for the discovery of complexes with desirable properties. The review will cover the development, promise, and limitations of "traditional" computational chemistry (i.e., force field, semiempirical, and density functional theory methods) as it pertains to data generation for inorganic molecular discovery. The review will also discuss the opportunities and limitations in leveraging experimental data sources. We will focus on how advances in statistical modeling, artificial intelligence, multiobjective optimization, and automation accelerate discovery of lead compounds and design rules. The overall objective of this review is to showcase how bringing together advances from diverse areas of computational chemistry and computer science have enabled the rapid uncovering of structure-property relationships in transition-metal chemistry. We aim to highlight how unique considerations in motifs of metal-organic bonding (e.g., variable spin and oxidation state, and bonding strength/nature) set them and their discovery apart from more commonly considered organic molecules. We will also highlight how uncertainty and relative data scarcity in transition-metal chemistry motivate specific developments in machine learning representations, model training, and in computational chemistry. Finally, we will conclude with an outlook of areas of opportunity for the accelerated discovery of transition-metal complexes.

Towards the object-oriented design of active hydrogen evolution catalysts on single-atom alloys

Given a desired property, locating relevant materials is always highly desired but very challenging in a range of areas, including heterogeneous catalysis. Obviously, object-oriented design/screening is an ideal solution to this problem. Herein, we develop an inverse catalyst design workflow in Python (CATIDPy) that utilizes a genetic-algorithm-based global optimization method to guide on-the-fly density functional theory calculations, successfully realizing the highly accelerated location of active single-atom alloy (SAA) catalysts for the hydrogen evolution reaction (HER). 70 binary and 752 ternary SAA candidate catalysts are identified for the HER. Furthermore, via considering the segregation stability and cost of materials, we extracted 6 binary and 142 ternary SAA candidate catalysts that are recommended for experimental synthesis. Remarkably, guided by these theoretical identifications, homogeneously dispersed Ni-based bimetallic catalysts (e.g., NiMo, NiAl, Ni₃Al, NiGa, and NiIn) were synthesized experimentally to test the reliability of the CATIDPy workflow, and they showed superior HER performance to bare Ni foam, indicating huge potential for use in real-world water electrolysis techniques. Perhaps more importantly, these results demonstrate the capacity of such a proposed approach for investigating unexplored chemical spaces to efficiently design promising catalysts without knowledge from the expert domain, which has far-reaching implications.

An inverse catalyst design workflow in Python (CATIDPy) for discovering unexplored chemical spaces successfully realized the highly accelerated location of active single-atom alloy (SAA) catalysts for the hydrogen evolution reaction (HER).