Machine Learning for Chemical Reactivity: The Importance of Failed Experiments

Ru-Catalyzed Asymmetric Hydrogenation of α,β-Unsaturated γ-Lactams

A highly efficient Ru-catalyzed asymmetric hydrogenation of α,β-unsaturated γ-lactams has been developed by using a C2-symmetric ruthenocenyl phosphine-oxazoline as the chiral ligand. This method achieves the enantioselective synthesis of chiral β-substituted γ-lactams in high yields and with excellent enantioselectivities (up to 99% yield with 99% ee). Mechanistic studies based on detailed control experiments and computational investigation revealed that the cationic Ru-complex acts as the active catalytic species; the protonation process of the oxa-π-allyl-Ru complex, which is formed by the migratory insertion of the C=C double bond to the Ru-H bond (the stereocontrolling step) followed by an isomerization process, is the rate-determining step, and the existence of PPh3 is crucial for the highly efficient catalytic behavior. The protocol provides a straightforward and practical pathway for the synthesis of key intermediates for several chiral drugs and bioactive compounds, particularly for the 150 kg-scale industrial production of Brivaracetam, an antiepileptic drug that shows 13-fold more potent binding to the synaptic vesicle protein 2A compared with the well-known Levetiracetam.

Probing machine learning models based on high throughput experimentation data for the discovery of asymmetric hydrogenation catalysts

Enantioselective hydrogenation of olefins by Rh-based chiral catalysts has been extensively studied for more than 50 years. Naively, one would expect that everything about this transformation is known and that selecting a catalyst that induces the desired reactivity or selectivity is a trivial task. Nonetheless, ligand engineering or selection for any new prochiral olefin remains an empirical trial-error exercise. In this study, we investigated whether machine learning techniques could be used to accelerate the identification of the most efficient chiral ligand. For this purpose, we used high throughput experimentation to build a large dataset consisting of results for Rh-catalyzed asymmetric olefin hydrogenation, specially designed for applications in machine learning. We showcased its alignment with existing literature while addressing observed discrepancies. Additionally, a computational framework for the automated and reproducible quantum-chemistry based featurization of catalyst structures was created. Together with less computationally demanding representations, these descriptors were fed into our machine learning pipeline for both out-of-domain and in-domain prediction tasks of selectivity and reactivity. For out-of-domain purposes, our models provided limited efficacy. It was found that even the most expensive descriptors do not impart significant meaning to the model predictions. The in-domain application, while partly successful for predictions of conversion, emphasizes the need for evaluating the cost-benefit ratio of computationally intensive descriptors and for tailored descriptor design. Challenges persist in predicting enantioselectivity, calling for caution in interpreting results from small datasets. Our insights underscore the importance of dataset diversity with broad substrate inclusion and suggest that mechanistic considerations could improve the accuracy of statistical models.

Self-Driving Laboratories for Chemistry and Materials Science

Self-driving laboratories (SDLs) promise an accelerated application of the scientific method. Through the automation of experimental workflows, along with autonomous experimental planning, SDLs hold the potential to greatly accelerate research in chemistry and materials discovery. This review provides an in-depth analysis of the state-of-the-art in SDL technology, its applications across various scientific disciplines, and the potential implications for research and industry. This review additionally provides an overview of the enabling technologies for SDLs, including their hardware, software, and integration with laboratory infrastructure. Most importantly, this review explores the diverse range of scientific domains where SDLs have made significant contributions, from drug discovery and materials science to genomics and chemistry. We provide a comprehensive review of existing real-world examples of SDLs, their different levels of automation, and the challenges and limitations associated with each domain.

Data-Driven Insights into the Transition-Metal-Catalyzed Asymmetric Hydrogenation of Olefins

The transition-metal-catalyzed asymmetric hydrogenation of olefins is one of the key transformations with great utility in various industrial applications. The field has been dominated by the use of noble metal catalysts, such as iridium and rhodium. The reactions with the earth-abundant cobalt metal have increased only in recent years. In this work, we analyze the large amount of literature data available on iridium- and rhodium-catalyzed asymmetric hydrogenation. The limited data on reactions using Co catalysts are then examined in the context of Ir and Rh to obtain a better understanding of the reactivity pattern. A detailed data-driven study of the types of olefins, ligands, and reaction conditions such as solvent, temperature, and pressure is carried out. Our analysis provides an understanding of the literature trends and demonstrates that only a few olefin-ligand combinations or reaction conditions are frequently used. The knowledge of this bias in the literature data toward a certain group of substrates or reaction conditions can be useful for practitioners to design new reaction data sets that are suitable to obtain meaningful predictions from machine-learning models.

Palladium-catalyzed decarboxylative (4 + 3) cycloadditions of bicyclobutanes with 2-alkylidenetrimethylene carbonates for the synthesis of 2-oxabicyclo[4.1.1]octanes

While cycloaddition reactions of bicyclobutanes (BCBs) have emerged as a potent method for synthesizing (hetero-)bicyclo[n.1.1]alkanes (usually n ≤ 3), their utilization in the synthesis of bicyclo[4.1.1]octane derivatives (BCOs) is still underdeveloped. Here, a palladium-catalyzed formal (4 + 3) reaction of BCBs with 1,4-O/C dipole precursors for the synthesis of oxa-BCOs is described. Unlike previous catalytic polar (3 + X) cycloadditions of BCBs, which are typically achieved through the activation of BCB substrates, the current reaction represents a novel strategy for realizing the cycloaddition of BCBs through the activation of the "X" cycloaddition partner. Moreover, the obtained functionalized oxa-BCOs products can be readily modified through various synthetic transformations.

Reaction rebalancing: a novel approach to curating reaction databases

PURPOSE

Reaction databases are a key resource for a wide variety of applications in computational chemistry and biochemistry, including Computer-aided Synthesis Planning (CASP) and the large-scale analysis of metabolic networks. The full potential of these resources can only be realized if datasets are accurate and complete. Missing co-reactants and co-products, i.e., unbalanced reactions, however, are the rule rather than the exception. The curation and correction of such incomplete entries is thus an urgent need.

METHODS

The SynRBL framework addresses this issue with a dual-strategy: a rule-based method for non-carbon compounds, using atomic symbols and counts for prediction, alongside a Maximum Common Subgraph (MCS)-based technique for carbon compounds, aimed at aligning reactants and products to infer missing entities.

RESULTS

The rule-based method exceeded 99% accuracy, while MCS-based accuracy varied from 81.19 to 99.33%, depending on reaction properties. Furthermore, an applicability domain and a machine learning scoring function were devised to quantify prediction confidence. The overall efficacy of this framework was delineated through its success rate and accuracy metrics, which spanned from 89.83 to 99.75% and 90.85 to 99.05%, respectively.

CONCLUSION

The SynRBL framework offers a novel solution for recalibrating chemical reactions, significantly enhancing reaction completeness. With rigorous validation, it achieved groundbreaking accuracy in reaction rebalancing. This sets the stage for future improvement in particular of atom-atom mapping techniques as well as of downstream tasks such as automated synthesis planning.

SCIENTIFIC CONTRIBUTION

SynRBL features a novel computational approach to correcting unbalanced entries in chemical reaction databases. By combining heuristic rules for inferring non-carbon compounds and common subgraph searches to address carbon unbalance, SynRBL successfully addresses most instances of this problem, which affects the majority of data in most large-scale resources. Compared to alternative solutions, SynRBL achieves a dramatic increase in both success rate and accurary, and provides the first freely available open source solution for this problem.

Harnessing Electro-Descriptors for Mechanistic and Machine Learning Analysis of Photocatalytic Organic Reactions

Photocatalysis has emerged as an effective tool for addressing the contemporary challenges in organic synthesis. However, the trial-and-error-based screening of feasible substrates and optimal reaction conditions remains time-consuming and potentially expensive in industrial practice. Here, we demonstrate an electrochemical-based data-acquisition approach that derives a simple set of redox-relevant electro-descriptors for effective mechanistic analysis and performance evaluation through machine learning (ML) in photocatalytic synthesis. These electro-descriptors correlate to the quantification of shifted charge transfer processes in response to the photoirradiation and enabled construction of reactivity diagram where high-yield reactive "hot zones" can reflect subtle changes of the reaction system. For the model reaction of photocatalytic deoxygenation reaction, the influence of varying carboxylic acids (substrate A, oxidation-intended) and alkenes (substrate B, reduction-intended) and varying reaction conditions on the reaction yield can be visualized, while mathematical analysis of the electro-descriptor patterns further revealed distinct mechanistic/kinetic impacts from different substrates and conditions. Additionally, in the application of ML algorithms, the experimentally derived electro-descriptors reflect an overall redox kinetic outcome contributed from vast reaction parameters, serving as a capable means to reduce the dimensionality in the case of complex multiparameter chemical space. As a result, utilization of electro-descriptors enabled efficient and robust quantitative evaluation of chemical reactivity, demonstrating promising potential of introducing operando-relevant experimental insights in the data-driven chemistry.

Geometric deep learning-guided Suzuki reaction conditions assessment for applications in medicinal chemistry

Suzuki cross-coupling reactions are considered a valuable tool for constructing carbon-carbon bonds in small molecule drug discovery. However, the synthesis of chemical matter often represents a time-consuming and labour-intensive bottleneck. We demonstrate how machine learning methods trained on high-throughput experimentation (HTE) data can be leveraged to enable fast reaction condition selection for novel coupling partners. We show that the trained models support chemists in determining suitable catalyst-solvent-base combinations for individual transformations including an evaluation of the need for HTE screening. We introduce an algorithm for designing 96-well plates optimized towards reaction yields and discuss the model performance of zero- and few-shot machine learning. The best-performing machine learning model achieved a three-category classification accuracy of 76.3% (±0.2%) and an F 1-score for a binary classification of 79.1% (±0.9%). Validation on eight reactions revealed a receiver operating characteristic (ROC) curve (AUC) value of 0.82 (±0.07) for few-shot machine learning. On the other hand, zero-shot machine learning models achieved a mean ROC-AUC value of 0.63 (±0.16). This study positively advocates the application of few-shot machine learning-guided reaction condition selection for HTE campaigns in medicinal chemistry and highlights practical applications as well as challenges associated with zero-shot machine learning.

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.

Reaction-Agnostic Featurization of Bidentate Ligands for Bayesian Ridge Regression of Enantioselectivity

Chiral ligands are important components in asymmetric homogeneous catalysis, but their synthesis and screening can be both time-consuming and resource-intensive. Data-driven approaches, in contrast to screening procedures based on intuition, have the potential to reduce the time and resources needed for reaction optimization by more rapidly identifying an ideal catalyst. These approaches, however, are often nontransferable and cannot be applied across different reactions. To overcome this drawback, we introduce a general featurization strategy for bidentate ligands that is coupled with an automated feature selection pipeline and Bayesian ridge regression to perform multivariate linear regression modeling. This approach, which is applicable to any reaction, incorporates electronic, steric, and topological features (rigidity/flexibility, branching, geometry, and constitution) and is well-suited for early stage ligand optimization. Using only small data sets, our workflow capably predicts the enantioselectivity of four metal-catalyzed asymmetric reactions. Uncertainty estimates provided by Bayesian ridge regression permit the use of Bayesian optimization to efficiently explore pools of prospective ligands. Finally, we constructed the BDL-Cu-2023 data set, composed of 312 bidentate ligands extracted from the Cambridge Structural Database, and screened it with this procedure to identify ligand candidates for a challenging asymmetric oxy-alkynylation reaction.

Incorporating Synthetic Accessibility in Drug Design: Predicting Reaction Yields of Suzuki Cross-Couplings by Leveraging AbbVie's 15-Year Parallel Library Data Set

Despite the increased use of computational tools to supplement medicinal chemists' expertise and intuition in drug design, predicting synthetic yields in medicinal chemistry endeavors remains an unsolved challenge. Existing design workflows could profoundly benefit from reaction yield prediction, as precious material waste could be reduced, and a greater number of relevant compounds could be delivered to advance the design, make, test, analyze (DMTA) cycle. In this work, we detail the evaluation of AbbVie's medicinal chemistry library data set to build machine learning models for the prediction of Suzuki coupling reaction yields. The combination of density functional theory (DFT)-derived features and Morgan fingerprints was identified to perform better than one-hot encoded baseline modeling, furnishing encouraging results. Overall, we observe modest generalization to unseen reactant structures within the 15-year retrospective library data set. Additionally, we compare predictions made by the model to those made by expert medicinal chemists, finding that the model can often predict both reaction success and reaction yields with greater accuracy. Finally, we demonstrate the application of this approach to suggest structurally and electronically similar building blocks to replace those predicted or observed to be unsuccessful prior to or after synthesis, respectively. The yield prediction model was used to select similar monomers predicted to have higher yields, resulting in greater synthesis efficiency of relevant drug-like molecules.

EnTdecker - A Machine Learning-Based Platform for Guiding Substrate Discovery in Energy Transfer Catalysis

Due to the magnitude of chemical space, the discovery of novel substrates in energy transfer (EnT) catalysis remains a daunting task. Experimental and computational strategies to identify compounds that successfully undergo EnT-mediated reactions are limited by their time and cost efficiency. To accelerate the discovery process in EnT catalysis, we herein present the EnTdecker platform, which facilitates the large-scale virtual screening of potential substrates using machine-learning (ML) based predictions of their excited state properties. To achieve this, a data set is created containing more than 34,000 molecules aiming to cover a vast fraction of synthetically relevant compound space for EnT catalysis. Using this data predictive models are trained, and their aptitude for an in-lab application is demonstrated by rediscovering successful substrates from literature as well as experimental validation through luminescence-based screening. By reducing the computational effort needed to obtain excited state properties, the EnTdecker platform represents a tool to efficiently guide substrate selection and increase the experimental success rate for EnT catalysis. Moreover, through an easy-to-use web application, EnTdecker is made publicly accessible under entdecker.uni-muenster.de.

Standardizing Substrate Selection: A Strategy toward Unbiased Evaluation of Reaction Generality

With over 10,000 new reaction protocols arising every year, only a handful of these procedures transition from academia to application. A major reason for this gap stems from the lack of comprehensive knowledge about a reaction's scope, i.e., to which substrates the protocol can or cannot be applied. Even though chemists invest substantial effort to assess the scope of new protocols, the resulting scope tables involve significant biases, reducing their expressiveness. Herein we report a standardized substrate selection strategy designed to mitigate these biases and evaluate the applicability, as well as the limits, of any chemical reaction. Unsupervised learning is utilized to map the chemical space of industrially relevant molecules. Subsequently, potential substrate candidates are projected onto this universal map, enabling the selection of a structurally diverse set of substrates with optimal relevance and coverage. By testing our methodology on different chemical reactions, we were able to demonstrate its effectiveness in finding general reactivity trends by using a few highly representative examples. The developed methodology empowers chemists to showcase the unbiased applicability of novel methodologies, facilitating their practical applications. We hope that this work will trigger interdisciplinary discussions about biases in synthetic chemistry, leading to improved data quality.

Hydrodesulfurization of Dibenzothiophene: A Machine Learning Approach

The hydrodesulfurization (HDS) process is widely used in the industry to eliminate sulfur compounds from fuels. However, removing dibenzothiophene (DBT) and its derivatives is a challenge. Here, the key aspects that affect the efficiency of catalysts in the HDS of DBT were investigated using machine learning (ML) algorithms. The conversion of DBT and selectivity was estimated by applying Lasso, Ridge, and Random Forest regression techniques. For the estimation of conversion of DBT, Random Forest and Lasso offer adequate predictions. At the same time, regularized regressions have similar outcomes, which are suitable for selectivity estimations. According to the regression coefficient, the structural parameters are essential predictors for selectivity, highlighting the pore size, and slab length. These properties can connect with aspects like the availability of active sites. The insights gained through ML techniques about the HDS catalysts agree with the interpretations of previous experimental reports.

Artificial Intelligence for Retrosynthetic Planning Needs Both Data and Expert Knowledge

Rapid advancements in artificial intelligence (AI) have enabled breakthroughs across many scientific disciplines. In organic chemistry, the challenge of planning complex multistep chemical syntheses should conceptually be well-suited for AI. Yet, the development of AI synthesis planners trained solely on reaction-example-data has stagnated and is not on par with the performance of "hybrid" algorithms combining AI with expert knowledge. This Perspective examines possible causes of these shortcomings, extending beyond the established reasoning of insufficient quantities of reaction data. Drawing attention to the intricacies and data biases that are specific to the domain of synthetic chemistry, we advocate augmenting the unique capabilities of AI with the knowledge base and the reasoning strategies of domain experts. By actively involving synthetic chemists, who are the end users of any synthesis planning software, into the development process, we envision to bridge the gap between computer algorithms and the intricate nature of chemical synthesis.

Transfer learning for a foundational chemistry model

Data-driven chemistry has garnered much interest concurrent with improvements in hardware and the development of new machine learning models. However, obtaining sufficiently large, accurate datasets of a desired chemical outcome for data-driven chemistry remains a challenge. The community has made significant efforts to democratize and curate available information for more facile machine learning applications, but the limiting factor is usually the laborious nature of generating large-scale data. Transfer learning has been noted in certain applications to alleviate some of the data burden, but this protocol is typically carried out on a case-by-case basis, with the transfer learning task expertly chosen to fit the finetuning. Herein, I develop a machine learning framework capable of accurate chemistry-relevant prediction amid general sources of low data. First, a chemical "foundational model" is trained using a dataset of ∼1 million experimental organic crystal structures. A task specific module is then stacked atop this foundational model and subjected to finetuning. This approach achieves state-of-the-art performance on a diverse set of tasks: toxicity prediction, yield prediction, and odor prediction.

Bridging the information gap in organic chemical reactions

The varying quality of scientific reports is a well-recognized problem and often results from a lack of standardization and transparency in scientific publications. This situation ultimately leads to prominent complications such as reproducibility issues and the slow uptake of newly developed synthetic methods for pharmaceutical and agrochemical applications. In recent years, various impactful approaches have been advocated to bridge information gaps and to improve the quality of experimental protocols in synthetic organic publications. Here we provide a critical overview of these strategies and present the reader with a versatile set of tools to augment their standard procedures. We formulate eight principles to improve data management in scientific publications relating to data standardization, reproducibility and evaluation, and encourage scientists to go beyond current publication standards. We are aware that this is a substantial effort, but we are convinced that the resulting improved data situation will greatly benefit the progress of chemistry.

Probing the chemical 'reactome' with high-throughput experimentation data

High-throughput experimentation (HTE) has the potential to improve our understanding of organic chemistry by systematically interrogating reactivity across diverse chemical spaces. Notable bottlenecks include few publicly available large-scale datasets and the need for facile interpretation of these data's hidden chemical insights. Here we report the development of a high-throughput experimentation analyser, a robust and statistically rigorous framework, which is applicable to any HTE dataset regardless of size, scope or target reaction outcome, which yields interpretable correlations between starting material(s), reagents and outcomes. We improve the HTE data landscape with the disclosure of 39,000+ previously proprietary HTE reactions that cover a breadth of chemistry, including cross-coupling reactions and chiral salt resolutions. The high-throughput experimentation analyser was validated on cross-coupling and hydrogenation datasets, showcasing the elucidation of statistically significant hidden relationships between reaction components and outcomes, as well as highlighting areas of dataset bias and the specific reaction spaces that necessitate further investigation.

A genetic optimization strategy with generality in asymmetric organocatalysis as a primary target

A catalyst possessing a broad substrate scope, in terms of both turnover and enantioselectivity, is sometimes called "general". Despite their great utility in asymmetric synthesis, truly general catalysts are difficult or expensive to discover via traditional high-throughput screening and are, therefore, rare. Existing computational tools accelerate the evaluation of reaction conditions from a pre-defined set of experiments to identify the most general ones, but cannot generate entirely new catalysts with enhanced substrate breadth. For these reasons, we report an inverse design strategy based on the open-source genetic algorithm NaviCatGA and on the OSCAR database of organocatalysts to simultaneously probe the catalyst and substrate scope and optimize generality as a primary target. We apply this strategy to the Pictet-Spengler condensation, for which we curate a database of 820 reactions, used to train statistical models of selectivity and activity. Starting from OSCAR, we define a combinatorial space of millions of catalyst possibilities, and perform evolutionary experiments on a diverse substrate scope that is representative of the whole chemical space of tetrahydro-β-carboline products. While privileged catalysts emerge, we show how genetic optimization can address the broader question of generality in asymmetric synthesis, extracting structure-performance relationships from the challenging areas of chemical space.

Methylene Insertion into Nitrogen-Heteroatom Single Bonds of 1,2-Azoles via a Zinc Carbenoid: An Alternative Tool for Skeletal Editing

The nitrogen-heteroatom single bonds of 1,2-azoles and isoxazolines underwent methylene insertion in the presence of CH2 I2 (6 equiv.) and diethylzinc (3 equiv.) to produce a wide variety of the ring-expanded six-membered heterocycles. Density functional theory calculations suggest that the methylene insertion proceeds via cleavage of nitrogen-heteroatom single bonds followed by ring closure.

Automatic feature engineering for catalyst design using small data without prior knowledge of target catalysis

The empirical aspect of descriptor design in catalyst informatics, particularly when confronted with limited data, necessitates adequate prior knowledge for delving into unknown territories, thus presenting a logical contradiction. This study introduces a technique for automatic feature engineering (AFE) that works on small catalyst datasets, without reliance on specific assumptions or pre-existing knowledge about the target catalysis when designing descriptors and building machine-learning models. This technique generates numerous features through mathematical operations on general physicochemical features of catalytic components and extracts relevant features for the desired catalysis, essentially screening numerous hypotheses on a machine. AFE yields reasonable regression results for three types of heterogeneous catalysis: oxidative coupling of methane (OCM), conversion of ethanol to butadiene, and three-way catalysis, where only the training set is swapped. Moreover, through the application of active learning that combines AFE and high-throughput experimentation for OCM, we successfully visualize the machine's process of acquiring precise recognition of the catalyst design. Thus, AFE is a versatile technique for data-driven catalysis research and a key step towards fully automated catalyst discoveries.

When Yield Prediction Does Not Yield Prediction: An Overview of the Current Challenges

Machine Learning (ML) techniques face significant challenges when predicting advanced chemical properties, such as yield, feasibility of chemical synthesis, and optimal reaction conditions. These challenges stem from the high-dimensional nature of the prediction task and the myriad essential variables involved, ranging from reactants and reagents to catalysts, temperature, and purification processes. Successfully developing a reliable predictive model not only holds the potential for optimizing high-throughput experiments but can also elevate existing retrosynthetic predictive approaches and bolster a plethora of applications within the field. In this review, we systematically evaluate the efficacy of current ML methodologies in chemoinformatics, shedding light on their milestones and inherent limitations. Additionally, a detailed examination of a representative case study provides insights into the prevailing issues related to data availability and transferability in the discipline.

Dataset Design for Building Models of Chemical Reactivity

Models can codify our understanding of chemical reactivity and serve a useful purpose in the development of new synthetic processes via, for example, evaluating hypothetical reaction conditions or in silico substrate tolerance. Perhaps the most determining factor is the composition of the training data and whether it is sufficient to train a model that can make accurate predictions over the full domain of interest. Here, we discuss the design of reaction datasets in ways that are conducive to data-driven modeling, emphasizing the idea that training set diversity and model generalizability rely on the choice of molecular or reaction representation. We additionally discuss the experimental constraints associated with generating common types of chemistry datasets and how these considerations should influence dataset design and model building.

High-Throughput Experimentation and Machine Learning-Assisted Optimization of Iridium-Catalyzed Cross-Dimerization of Sulfoxonium Ylides

A novel and convenient approach that combines high-throughput experimentation (HTE) with machine learning (ML) technologies to achieve the first selective cross-dimerization of sulfoxonium ylides via iridium catalysis is presented. A variety of valuable amide-, ketone-, ester-, and N-heterocycle-substituted unsymmetrical E-alkenes are synthesized in good yields with high stereoselectivities. This mild method avoids the use of diazo compounds and is characterized by simple operation, high step-economy, and excellent chemoselectivity and functional group compatibility. The combined experimental and computational studies identify an amide-sulfoxonium ylide as a carbene precursor. Furthermore, a comprehensive exploration of the reaction space is also performed (600 reactions) and a machine learning model for reaction yield prediction has been constructed.

Revisiting the Paradigm of Reaction Optimization in Flow with a Priori Computational Reaction Intelligence

The use of micro/meso-fluidic reactors has resulted in both new scenarios for chemistry and new requirements for chemists. Through flow chemistry, large-scale reactions can be performed in drastically reduced reactor sizes and reaction times. This obvious advantage comes with the concomitant challenge of re-designing long-established batch processes to fit these new conditions. The reliance on experimental trial-and-error to perform this translation frequently makes flow chemistry unaffordable, thwarting initial aspirations to revolutionize chemistry. By combining computational chemistry and machine learning, we have developed a model that provides predictive power tailored specifically to flow reactions. We show its applications to translate batch to flow, to provide mechanistic insight, to contribute reagent descriptors, and to synthesize a library of novel compounds in excellent yields after executing a single set of conditions.

Machine Learning-Enabled Predictions of Condensed Fukui Functions and Designing of Metal Pincer Complexes for Catalytic Hydrogenation of CO2

This research showcases the machine learning (ML)-enabled homogeneous catalyst discovery to be employed in carbon dioxide hydrogenation. To achieve the desired turnover frequency (TOF), the electrophilicity of the central metal atom is a crucial factor in transition metal pincer complexes. The condensed Fukui function is a direct measure of the catalytic performance of these pincer complexes. Herein, we demonstrate that machine learning is a convenient and effiecient method to calculate condensed Fukui functions of the central metal atom. The electrophilicity values of 202 pincer complexes were calculated by using density functional theory (DFT) to train the ML model. The test data of the experimentally established pincer complexes show a direct linkage between calculated electrophilicity and experimental TOF. Further, this data was used to develop an ML protocol to screen 2,84,062 catalyst complexes to get the electrophilicity values of the Mn, Fe, Co, and Ni transition metals encompassing various permutation combinations of PNP, PNN, NNN, and PCP pincer ligands. These findings validate the efficacy of machine learning in the rapid screening of metal pincer catalysts based on condensed Fukui functions.

The challenge of balancing model sensitivity and robustness in predicting yields: a benchmarking study of amide coupling reactions

Accurate prediction of reaction yield is the holy grail for computer-assisted synthesis prediction, but current models have failed to generalize to large literature datasets. To understand the causes and inspire future design, we systematically benchmarked the yield prediction task. We carefully curated and augmented a literature dataset of 41 239 amide coupling reactions, each with information on reactants, products, intermediates, yields, and reaction contexts, and provided 3D structures for the molecules. We calculated molecular features related to 2D and 3D structure information, as well as physical and electronic properties. These descriptors were paired with 4 categories of machine learning methods (linear, kernel, ensemble, and neural network), yielding valuable benchmarks about feature and model performance. Despite the excellent performance on a high-throughput experiment (HTE) dataset (R2 around 0.9), no method gave satisfactory results on the literature data. The best performance was an R2 of 0.395 ± 0.020 using the stack technique. Error analysis revealed that reactivity cliff and yield uncertainty are among the main reasons for incorrect predictions. Removing reactivity cliffs and uncertain reactions boosted the R2 to 0.457 ± 0.006. These results highlight that yield prediction models must be sensitive to the reactivity change due to the subtle structure variance, as well as be robust to the uncertainty associated with yield measurements.

The rise of automated curiosity-driven discoveries in chemistry

The quest for generating novel chemistry knowledge is critical in scientific advancement, and machine learning (ML) has emerged as an asset in this pursuit. Through interpolation among learned patterns, ML can tackle tasks that were previously deemed demanding to machines. This distinctive capacity of ML provides invaluable aid to bench chemists in their daily work. However, current ML tools are typically designed to prioritize experiments with the highest likelihood of success, i.e., higher predictive confidence. In this perspective, we build on current trends that suggest a future in which ML could be just as beneficial in exploring uncharted search spaces through simulated curiosity. We discuss how low and 'negative' data can catalyse one-/few-shot learning, and how the broader use of curious ML and novelty detection algorithms can propel the next wave of chemical discoveries. We anticipate that ML for curiosity-driven research will help the community overcome potentially biased assumptions and uncover unexpected findings in the chemical sciences at an accelerated pace.

On the use of real-world datasets for reaction yield prediction

The lack of publicly available, large, and unbiased datasets is a key bottleneck for the application of machine learning (ML) methods in synthetic chemistry. Data from electronic laboratory notebooks (ELNs) could provide less biased, large datasets, but no such datasets have been made publicly available. The first real-world dataset from the ELNs of a large pharmaceutical company is disclosed and its relationship to high-throughput experimentation (HTE) datasets is described. For chemical yield predictions, a key task in chemical synthesis, an attributed graph neural network (AGNN) performs as well as or better than the best previous models on two HTE datasets for the Suzuki-Miyaura and Buchwald-Hartwig reactions. However, training the AGNN on an ELN dataset does not lead to a predictive model. The implications of using ELN data for training ML-based models are discussed in the context of yield predictions.

A focus on the use of real-world datasets for yield prediction

The prediction of reaction yields remains a challenging task for machine learning (ML), given the vast search spaces and absence of robust training data. Wiest, Chawla et al. (https://doi.org/10.1039/D2SC06041H) show that a deep learning algorithm performs well on high-throughput experimentation data but surprisingly poorly on real-world, historical data from a pharmaceutical company. The result suggests that there is considerable room for improvement when coupling ML to electronic laboratory notebook data.

Open data and algorithms for open science in AI-driven molecular informatics

Recent years have seen a sharp increase in the development of deep learning and artificial intelligence-based molecular informatics. There has been a growing interest in applying deep learning to several subfields, including the digital transformation of synthetic chemistry, extraction of chemical information from the scientific literature, and AI in natural product-based drug discovery. The application of AI to molecular informatics is still constrained by the fact that most of the data used for training and testing deep learning models are not available as FAIR and open data. As open science practices continue to grow in popularity, initiatives which support FAIR and open data as well as open-source software have emerged. It is becoming increasingly important for researchers in the field of molecular informatics to embrace open science and to submit data and software in open repositories. With the advent of open-source deep learning frameworks and cloud computing platforms, academic researchers are now able to deploy and test their own deep learning models with ease. With the development of new and faster hardware for deep learning and the increasing number of initiatives towards digital research data management infrastructures, as well as a culture promoting open data, open source, and open science, AI-driven molecular informatics will continue to grow. This review examines the current state of open data and open algorithms in molecular informatics, as well as ways in which they could be improved in future.

Data-Centric Heterogeneous Catalysis: Identifying Rules and Materials Genes of Alkane Selective Oxidation

Artificial intelligence (AI) can accelerate catalyst design by identifying key physicochemical descriptive parameters correlated with the underlying processes triggering, favoring, or hindering the performance. In analogy to genes in biology, these parameters might be called "materials genes" of heterogeneous catalysis. However, widely used AI methods require big data, and only the smallest part of the available data meets the quality requirement for data-efficient AI. Here, we use rigorous experimental procedures, designed to consistently take into account the kinetics of the catalyst active states formation, to measure 55 physicochemical parameters as well as the reactivity of 12 catalysts toward ethane, propane, and n-butane oxidation reactions. These materials are based on vanadium or manganese redox-active elements and present diverse phase compositions, crystallinities, and catalytic behaviors. By applying the sure-independence-screening-and-sparsifying-operator symbolic-regression approach to the consistent data set, we identify nonlinear property-function relationships depending on several key parameters and reflecting the intricate interplay of processes that govern the formation of olefins and oxygenates: local transport, site isolation, surface redox activity, adsorption, and the material dynamical restructuring under reaction conditions. These processes are captured by parameters derived from N₂ adsorption, X-ray photoelectron spectroscopy (XPS), and near-ambient-pressure in situ XPS. The data-centric approach indicates the most relevant characterization techniques to be used for catalyst design and provides "rules" on how the catalyst properties may be tuned in order to achieve the desired performance.

Machine Learning C-N Couplings: Obstacles for a General-Purpose Reaction Yield Prediction

Pd-catalyzed C-N couplings are commonplace in academia and industry. Despite their significance, finding suitable reaction conditions leading to a high yield, for instance, remains a challenging and time-consuming task which usually requires screening over many sets of conditions. To help select promising reaction conditions in the vast space of reagent combinations, machine learning is an emerging technique with a lot of promise. In this work, we assess whether the reaction yield of C-N couplings can be predicted from databases of chemical reactions. We test the generalizability of models both on challenging data splits and on a dedicated experimental test set. We find that, provided the chemical space represented by the training set is not left, the models perform well. However, the applicability domain is quickly left even for simple reactions of the same type, as, for instance, present in our plate test set. The results show that yield prediction for new reactions is possible from the algorithmic side but in practice is hindered by the available data. Most importantly, more data that cover the diversity in reagents are needed for a general-purpose prediction of reaction yields. Our findings also expose a challenge to this field in that it appears to be extremely deceiving to judge models based on literature data with test sets which are split off the same literature data, even when challenging splits are considered.

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.

Machine learning for yield prediction for chemical reactions using in situ sensors

Machine learning models were developed to predict product formation from time-series reaction data for ten Buchwald-Hartwig coupling reactions. The data was provided by DeepMatter and was collected in their DigitalGlassware cloud platform. The reaction probe has 12 sensors to measure properties of interest, including temperature, pressure, and colour. Colour was a good predictor of product formation for this reaction and machine learning models were able to learn which of the properties were important. Predictions for the current product formation (in terms of % yield) had a mean absolute error of 1.2%. For predicting 30, 60 and 120 min ahead the error rose to 3.4, 4.1 and 4.6%, respectively. The work here presents an example into the insight that can be obtained from applying machine learning methods to sensor data in synthetic chemistry.

Closed-loop optimization of general reaction conditions for heteroaryl Suzuki-Miyaura coupling

General conditions for organic reactions are important but rare, and efforts to identify them usually consider only narrow regions of chemical space. Discovering more general reaction conditions requires considering vast regions of chemical space derived from a large matrix of substrates crossed with a high-dimensional matrix of reaction conditions, rendering exhaustive experimentation impractical. Here, we report a simple closed-loop workflow that leverages data-guided matrix down-selection, uncertainty-minimizing machine learning, and robotic experimentation to discover general reaction conditions. Application to the challenging and consequential problem of heteroaryl Suzuki-Miyaura cross-coupling identified conditions that double the average yield relative to a widely used benchmark that was previously developed using traditional approaches. This study provides a practical road map for solving multidimensional chemical optimization problems with large search spaces.

Chemistry must respond to the crisis of transgression of planetary boundaries

Recent assessments alarmingly indicate that many of the world's leading chemicals are transgressing one or more of the nine planetary boundaries, which define safe operating spaces within which humanity can continue to develop and thrive for generations to come. The unfolding crisis cannot be ignored and there is a once-in-a-century opportunity for chemistry - the science of transformation of matter - to make a critical difference to the future of people and planet. How can chemists contribute to meeting these challenges and restore stability and strengthen resilience to the planetary system that humanity needs for its survival? To respond to the wake-up call, three crucial steps are outlined: (1) urgently working to understand the nature of the looming threats, from a chemistry perspective; (2) harnessing the ingenuity and innovation that are central to the practice of chemistry to develop sustainable solutions; and (3) transforming chemistry itself, in education, research and industry, to re-position it as 'chemistry for sustainability' and lead the stewardship of the world's chemical resources. This will require conservation of material stocks in forms that remain available for use, through attention to circularity, as well as strengthening engagement in systems-based approaches to designing chemistry research and processes informed by convergent working with many other disciplines.

Autonomous Chemical Experiments: Challenges and Perspectives on Establishing a Self-Driving Lab

We must accelerate the pace at which we make technological advancements to address climate change and disease risks worldwide. This swifter pace of discovery requires faster research and development cycles enabled by better integration between hypothesis generation, design, experimentation, and data analysis. Typical research cycles take months to years. However, data-driven automated laboratories, or self-driving laboratories, can significantly accelerate molecular and materials discovery. Recently, substantial advancements have been made in the areas of machine learning and optimization algorithms that have allowed researchers to extract valuable knowledge from multidimensional data sets. Machine learning models can be trained on large data sets from the literature or databases, but their performance can often be hampered by a lack of negative results or metadata. In contrast, data generated by self-driving laboratories can be information-rich, containing precise details of the experimental conditions and metadata. Consequently, much larger amounts of high-quality data are gathered in self-driving laboratories. When placed in open repositories, this data can be used by the research community to reproduce experiments, for more in-depth analysis, or as the basis for further investigation. Accordingly, high-quality open data sets will increase the accessibility and reproducibility of science, which is sorely needed.In this Account, we describe our efforts to build a self-driving lab for the development of a new class of materials: organic semiconductor lasers (OSLs). Since they have only recently been demonstrated, little is known about the molecular and material design rules for thin-film, electrically-pumped OSL devices as compared to other technologies such as organic light-emitting diodes or organic photovoltaics. To realize high-performing OSL materials, we are developing a flexible system for automated synthesis via iterative Suzuki-Miyaura cross-coupling reactions. This automated synthesis platform is directly coupled to the analysis and purification capabilities. Subsequently, the molecules of interest can be transferred to an optical characterization setup. We are currently limited to optical measurements of the OSL molecules in solution. However, material properties are ultimately most important in the solid state (e.g., as a thin-film device). To that end and for a different scientific goal, we are developing a self-driving lab for inorganic thin-film materials focused on the oxygen evolution reaction.While the future of self-driving laboratories is very promising, numerous challenges still need to be overcome. These challenges can be split into cognition and motor function. Generally, the cognitive challenges are related to optimization with constraints or unexpected outcomes for which general algorithmic solutions have yet to be developed. A more practical challenge that could be resolved in the near future is that of software control and integration because few instrument manufacturers design their products with self-driving laboratories in mind. Challenges in motor function are largely related to handling heterogeneous systems, such as dispensing solids or performing extractions. As a result, it is critical to understand that adapting experimental procedures that were designed for human experimenters is not as simple as transferring those same actions to an automated system, and there may be more efficient ways to achieve the same goal in an automated fashion. Accordingly, for self-driving laboratories, we need to carefully rethink the translation of manual experimental protocols.

Machine Learning Yield Prediction from NiCOlit, a Small-Size Literature Data Set of Nickel Catalyzed C-O Couplings

Synthetic yield prediction using machine learning is intensively studied. Previous work has focused on two categories of data sets: high-throughput experimentation data, as an ideal case study, and data sets extracted from proprietary databases, which are known to have a strong reporting bias toward high yields. However, predicting yields using published reaction data remains elusive. To fill the gap, we built a data set on nickel-catalyzed cross-couplings extracted from organic reaction publications, including scope and optimization information. We demonstrate the importance of including optimization data as a source of failed experiments and emphasize how publication constraints shape the exploration of the chemical space by the synthetic community. While machine learning models still fail to perform out-of-sample predictions, this work shows that adding chemical knowledge enables fair predictions in a low-data regime. Eventually, we hope that this unique public database will foster further improvements of machine learning methods for reaction yield prediction in a more realistic context.