Hybrid Machine Learning Approach to Predict the Site Selectivity of Iridium-Catalyzed Arene Borylation

Selective C-H Borylation of Polyaromatic Compounds Enabled by Metal-Arene π-Complexation

The undirected Ir-catalyzed C-H borylation usually occurs preferentially at the least hindered and more acidic C-H bond of the aromatic ring. In the case of polyaromatic compounds possessing multiple unbiased and sterically accessible C-H bonds, the site selectivity for the nondirected C-H borylation is low. Here, we report the dramatic effect exerted by the π-complexation of a chromium tricarbonyl unit on the aromatic ring in the context of Ir-catalyzed C-H borylation. Competition experiments demonstrate that the C-H bonds of an aromatic ring bound to the chromium tricarbonyl unit react on average two orders in magnitude faster toward the C-H borylation than the unbound arenes. This enables an unprecedented C-H borylation with high site selectivity of the aromatic ring π-complexed with a chromium tripod in a series of organic polyaromatic compounds. Besides, the drastic enhancement of the reactivity of C-H bonds induced by the chromium tripod allows the C-H borylation to occur at room temperature with the substrate as a limiting reagent. The DFT studies indicate that the oxidative addition of the C-H bonds has lower activation barriers when the arenes are complexed with a chromium tricarbonyl unit, explaining the observed exceptional site selectivity. This study will further spearhead the development of nondirected C-H borylation with a bimetallic system to harness the effect of the noncovalent metal-arene π-type interactions on the reactivity and the selectivity of the C-H functionalization.

From Single-Atom to Dual-Atom: A Universal Principle for the Rational Design of Heterogeneous Fenton-like Catalysts

Developing efficient heterogeneous Fenton-like catalysts is the key point to accelerating the removal of organic micropollutants in the advanced oxidation process. However, a general principle guiding the reasonable design of highly efficient heterogeneous Fenton-like catalysts has not been constructed up to now. In this work, a total of 16 single-atom and 272 dual-atom transition metal/nitrogen/carbon (TM/N/C) catalysts for H2O2 dissociation were explored systematically based on high-throughput density functional theory and machine learning. It was found that H2O2 dissociation on single-atom TM/N/C exhibited a distinct volcano-type relationship between catalytic activity and •OH adsorption energy. The favorable •OH adsorption energies were in the range of -3.11 ∼ -2.20 eV. Three different descriptors, namely, energetic, electronic, and structural descriptors, were found, which can correlate the intrinsic properties of catalysts and their catalytic activity. Using adsorption energy, stability, and activation energy as the evaluation criteria, two dual-atom CoCu/N/C and CoRu/N/C catalysts were screened out from 272 candidates, which exhibited higher catalytic activity than the best single-atom TM/N/C catalyst due to the synergistic effect. This work could present a conceptually novel understanding of H2O2 dissociation on TM/N/C and inspire the structure-oriented catalyst design from the viewpoint of volcano relationship.

The Importance of Atomic Charges for Predicting Site-Selective Ir-, Ru-, and Rh-Catalyzed C-H Borylations

A supervised machine learning model has been developed that allows for the prediction of site selectivity in late-stage C-H borylations. Model development was accomplished using literature data for the site-selective (≥95%) C-H borylation of 189 unique arene, heteroarene, and aliphatic substrates that feature a total of 971 possible sp2 or sp3 C-H borylation sites. The reported experimental data was supplemented with additional chemoinformatic descriptors, computed atomic charges at the C-H borylation sites, and data from parameterization of catalytically active tris-boryl complexes resulting from the combination of seven different Ir-, Ru-, and Rh-based precatalysts with eight different ligands. Of the over 1600 parameters investigated, the computed atomic charges (e.g., Hirshfeld, ChelpG, and Mulliken charges) on the hydrogen and carbon atoms at the site of borylation were identified as the most important features that allow for the successful prediction of whether a particular C-H bond will undergo a site-selective borylation. The overall accuracy of the developed model was 88.9% ± 2.5% with precision, recall, and F1 scores of 92-95% for the nonborylating sites and 65-75% for the sites of borylation. The model was demonstrated to be generalizable to molecules outside of the training/test sets with an additional validation set of 12 electronically and structurally diverse systems.

A meta-learning approach for selectivity prediction in asymmetric catalysis

Transition metal-catalyzed asymmetric reactions are of high contemporary importance in organic synthesis. Recently, machine learning (ML) has shown promise in accelerating the development of newer catalytic protocols. However, the need for large amount of experimental data can present a bottleneck for implementing ML models. Here, we propose a meta-learning workflow that can harness the literature-derived data to extract shared reaction features and requires only a few examples to predict the outcome of new reactions. Prototypical networks are used as a meta-learning method to predict the enantioselectivity of asymmetric hydrogenation of olefins. This meta-learning model consistently provides significant performance improvement over other popular ML methods such as random forests and graph neural networks. The performance of our meta-model is analyzed with varying sizes of training examples to demonstrate its utility even with limited data. A good model performance on an out-of-sample test set further indicates the general applicability of our approach. We believe this work will provide a leap forward in identifying promising reactions in the early phases of reaction development when minimal data is available.

Computational tools for the prediction of site- and regioselectivity of organic reactions

The regio- and site-selectivity of organic reactions is one of the most important aspects when it comes to synthesis planning. Due to that, massive research efforts were invested into computational models for regio- and site-selectivity prediction, and the introduction of machine learning to the chemical sciences within the past decade has added a whole new dimension to these endeavors. This review article walks through the currently available predictive tools for regio- and site-selectivity with a particular focus on machine learning models while being organized along the individual reaction classes of organic chemistry. Respective featurization techniques and model architectures are described and compared to each other; applications of the tools to critical real-world examples are highlighted. This paper aims to serve as an overview of the field's status quo for both the intended users of the tools, that is synthetic chemists, as well as for developers to find potential new research avenues.

Controlling the Symmetry of Perylene Derivatives via Selective ortho-Borylation

This work presents a systematic and rational approach to the synthesis of previously reported as well as novel tetra- and di-ortho-borylated perylene, perylenediimide, and perylenemonoimide scaffolds. Through optimization of the reaction conditions, employing [Ir(OMe)(COD)]2 as a catalyst and suitable ligands, efficient tetraborylation and regioselective diborylations were achieved. Additionally, the reaction times were reduced from days to hours under microwave irradiation, rendering this methodology a practical and scalable route for the ortho-functionalization of perylene derivatives.

Designing Target-specific Data Sets for Regioselectivity Predictions on Complex Substrates

The development of machine learning models to predict the regioselectivity of C(sp3)-H functionalization reactions is reported. A data set for dioxirane oxidations was curated from the literature and used to generate a model to predict the regioselectivity of C-H oxidation. To assess whether smaller, intentionally designed data sets could provide accuracy on complex targets, a series of acquisition functions were developed to select the most informative molecules for the specific target. Active learning-based acquisition functions that leverage predicted reactivity and model uncertainty were found to outperform those based on molecular and site similarity alone. The use of acquisition functions for data set elaboration significantly reduced the number of data points needed to perform accurate prediction, and it was found that smaller, machine-designed data sets can give accurate predictions when larger, randomly selected data sets fail. Finally, the workflow was experimentally validated on five complex substrates and shown to be applicable to predicting the regioselectivity of arene C-H radical borylation. These studies provide a quantitative alternative to the intuitive extrapolation from "model substrates" that is frequently used to estimate reactivity on complex molecules.

Direct (LC-)MS Identification of Regioisomers from C-H Functionalization by Partial Isotopic Labeling

C-H functionalization of complex substrates is highly enabling in total synthesis and in the development of late-stage drug candidates. Much work has been dedicated to developing new methods as well as predictive modeling to accelerate route scouting. However, workflows to identify regioisomeric products are arduous, typically requiring chromatographic separation and/or nuclear magnetic resonance spectroscopy analysis. In addition, most reports focus on major products or do not assign regioisomeric products, which biases predictive models constructed from such data. Herein, we present a novel approach to complex reaction analysis utilizing partial deuterium labels, which enables direct product identification via liquid chromatography-mass spectrometry. When combined with spectral deconvolution, the method generates product ratios while circumventing chromatography altogether. Competitive kinetic isotope effects can also be determined. The resultant data are expected to be useful in the construction of predictive models across several dimensions including reaction selectivity, the impact of structure on mechanism, and mass spectral ionization patterns and expedite the identification of drug metabolites.

High-Throughput Enabled Iridium-Catalyzed C-H Borylation Platform for Late-Stage Functionalization

In this work, we present a dedicated, high-throughput reaction optimization platform allowing for the rapid evaluation of regiodivergent C-H borylation protocols while minimizing the amount of starting material required. The workflow was applied to a diverse set of fragment-like compounds, pharmaceuticals, and agrochemicals, and its practicality was demonstrated by successfully isolating 36 derivatives of bioactive compounds. Leveraging the informer library approach, we provide a comprehensive, side-by-side comparison of catalytic methods, revealing insights into the strengths, limitations, and versatility of each borylation protocol. Surprising reactivity patterns, effectiveness of ligand-free C-H borylation, and the utility of previously reported directed C-H borylation catalysts outside of their expected substrate scope have been noticed. This study highlights the potential of dedicated high-throughput optimization platforms to expand the practical utility of late-stage functionalization protocols for pharmaceutical and agrochemical research.

Database Construction for the Virtual Screening of the Ruthenium-Catalyzed Hydrogenation of Ketones

During the recent development of machine-learning (ML) methods for organic synthesis, the value of "failed experiments" has increasingly been acknowledged. Accordingly, we have developed an exhaustive database comprising 300 entries of experimental data obtained by performing ruthenium-catalyzed hydrogenation reactions using 10 ketones as substrates and 30 phosphine ligands. After evaluating the predictive performance of ML models using the constructed database, we conducted a virtual screening of commercially available phosphine ligands. For the virtual screening, we utilized several models, such as histogram-based gradient boosting and Ridge regression, combined with the Mordred descriptors and MACCSKeys, respectively. The disclosed approach resulted in the identification of high-performance phosphine ligands, and the rationale behind the predictions in the virtual screening was analyzed using SHAP.

Simple User-Friendly Reaction Format

Utilizing the growing wealth of chemical reaction data can boost synthesis planning and increase success rates. Yet, the effectiveness of machine learning tools for retrosynthesis planning and forward reaction prediction relies on accessible, well-curated data presented in a structured format. Although some public and licensed reaction databases exist, they often lack essential information about reaction conditions. To address this issue and promote the principles of findable, accessible, interoperable, and reusable (FAIR) data reporting and sharing, we introduce the Simple User-Friendly Reaction Format (SURF). SURF standardizes the documentation of reaction data through a structured tabular format, requiring only a basic understanding of spreadsheets. This format enables chemists to record the synthesis of molecules in a format that is understandable by both humans and machines, which facilitates seamless sharing and integration directly into machine learning pipelines. SURF files are designed to be interoperable, easily imported into relational databases, and convertible into other formats. This complements existing initiatives like the Open Reaction Database (ORD) and Unified Data Model (UDM). At Roche, SURF plays a crucial role in democratizing FAIR reaction data sharing and expediting the chemical synthesis process.

6-Hydroxy Picolinohydrazides Promoted Cu(I)-Catalyzed Hydroxylation Reaction in Water: Machine-Learning Accelerated Ligands Design and Reaction Optimization

Hydroxylated (hetero)arenes are privileged motifs in natural products, materials, small-molecule pharmaceuticals and serve as versatile intermediates in synthetic organic chemistry. Herein, we report an efficient Cu(I)/6-hydroxy picolinohydrazide-catalyzed hydroxylation reaction of (hetero)aryl halides (Br, Cl) in water. By establishing machine learning (ML) models, the design of ligands and optimization of reaction conditions were effectively accelerated. The N-(1,3-dimethyl-9H- carbazol-9-yl)-6-hydroxypicolinamide (L32, 6-HPA-DMCA) demonstrated high efficiency for (hetero)aryl bromides, promoting hydroxylation reactions with a minimal catalyst loading of 0.01 mol % (100 ppm) at 80 °C to reach 10000 TON; for substrates containing sensitive functional groups, the catalyst loading needs to be increased to 3.0 mol % under near-room temperature conditions. N-(2,7-Di-tert-butyl-9H-carbazol-9-yl)-6-hydroxypicolinamide (L42, 6-HPA-DTBCA) displayed superior reaction activity for chloride substrates, enabling hydroxylation reactions at 100 °C with 2-3 mol % catalyst loading. These represent the state of art for both lowest catalyst loading and temperature in the copper-catalyzed hydroxylation reactions. Furthermore, this method features a sustainable and environmentally friendly solvent system, accommodates a wide range of substrates, and shows potential for developing robust and scalable synthesis processes for key pharmaceutical intermediates.

Spirobipyridine Ligand Enabled Iridium-Catalyzed Site-Selective C-H Activation via Non-Covalent Interactions

The selective borylation of specific C-H bonds in organic synthesis remains a formidable challenge. In this study, we present a novel spirobipyridine ligand that features a binaphthyl backbone. This ligand facilitates the iridium-catalyzed selective C-H borylation of benzene derivatives. The ligand is designed with "side-arm-wall" substituents that allow vicinal di- or multi-substituted benzene derivatives to approach metal center and effectively block other reactive sites by non-covalent interactions with substrates. The effectiveness of this strategy is demonstrated by the successful selective distal C-H activation of various alkaloids and its broad compatibility with functional groups.

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.

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.

pKalculator: A pK a predictor for C-H bonds

Determining the pK a values of various C-H sites in organic molecules offers valuable insights for synthetic chemists in predicting reaction sites. As molecular complexity increases, this task becomes more challenging. This paper introduces pKalculator, a quantum chemistry (QM)-based workflow for automatic computations of C-H pK a values, which is used to generate a training dataset for a machine learning (ML) model. The QM workflow is benchmarked against 695 experimentally determined C-H pK a values in DMSO. The ML model is trained on a diverse dataset of 775 molecules with 3910 C-H sites. Our ML model predicts C-H pK a values with a mean absolute error (MAE) and a root mean squared error (RMSE) of 1.24 and 2.15 pK a units, respectively. Furthermore, we employ our model on 1043 pK a-dependent reactions (aldol, Claisen, and Michael) and successfully indicate the reaction sites with a Matthew's correlation coefficient (MCC) of 0.82.

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.

Leveraging Language Model Multitasking To Predict C-H Borylation Selectivity

C-H borylation is a high-value transformation in the synthesis of lead candidates for the pharmaceutical industry because a wide array of downstream coupling reactions is available. However, predicting its regioselectivity, especially in drug-like molecules that may contain multiple heterocycles, is not a trivial task. Using a data set of borylation reactions from Reaxys, we explored how a language model originally trained on USPTO_500_MT, a broad-scope set of patent data, can be used to predict the C-H borylation reaction product in different modes: product generation and site reactivity classification. Our fine-tuned T5Chem multitask language model can generate the correct product in 79% of cases. It can also classify the reactive aromatic C-H bonds with 95% accuracy and 88% positive predictive value, exceeding purpose-developed graph-based neural networks.

The Role of Base in Reaction Performance of Photochemical Synthesis of Thiazoles: An Integrated Theoretical and Experimental Study

Artificial intelligence (AI)/machine learning (ML) is emerging as pivotal in synthetic chemistry, offering revolutionary potential in retrosynthetic analysis, reaction conditions and reaction prediction. We have combined chemical descriptors, primarily based on Density Functional Theory (DFT) calculations, with various AI/ML tools such as Multi-Layer Perceptron (MLP) and Random Forest (RF), to predict the synthesis of 2-arylbenzothiazole in photoredox reactions. Significantly, our models underscore the critical role of the molecular structure and physicochemical characteristics of the base, especially the total atomic polarizabilities, in the rate-determining steps involving cyclohexyl and phenethyl moieties of the substrate. Moreover, we validated our findings in articles through experimental studies. It showcases the power of AI/ML and quantum chemistry in shaping the future of organic chemistry.

Enabling late-stage drug diversification by high-throughput experimentation with geometric deep learning

Late-stage functionalization is an economical approach to optimize the properties of drug candidates. However, the chemical complexity of drug molecules often makes late-stage diversification challenging. To address this problem, a late-stage functionalization platform based on geometric deep learning and high-throughput reaction screening was developed. Considering borylation as a critical step in late-stage functionalization, the computational model predicted reaction yields for diverse reaction conditions with a mean absolute error margin of 4-5%, while the reactivity of novel reactions with known and unknown substrates was classified with a balanced accuracy of 92% and 67%, respectively. The regioselectivity of the major products was accurately captured with a classifier F-score of 67%. When applied to 23 diverse commercial drug molecules, the platform successfully identified numerous opportunities for structural diversification. The influence of steric and electronic information on model performance was quantified, and a comprehensive simple user-friendly reaction format was introduced that proved to be a key enabler for seamlessly integrating deep learning and high-throughput experimentation for late-stage functionalization.

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.

Kinetic and thermodynamic control of C(sp2)-H activation enables site-selective borylation

Catalysts that distinguish between electronically distinct carbon-hydrogen (C-H) bonds without relying on steric effects or directing groups are challenging to design. In this work, cobalt precatalysts supported by N-alkyl-imidazole-substituted pyridine dicarbene (ACNC) pincer ligands are described that enable undirected, remote borylation of fluoroaromatics and expansion of scope to include electron-rich arenes, pyridines, and tri- and difluoromethoxylated arenes, thereby addressing one of the major limitations of first-row transition metal C-H functionalization catalysts. Mechanistic studies established a kinetic preference for C-H bond activation at the meta-position despite cobalt-aryl complexes resulting from ortho C-H activation being thermodynamically preferred. Switchable site selectivity in C-H borylation as a function of the boron reagent was thereby preliminarily demonstrated using a single precatalyst.

Identifying opportunities for late-stage C-H alkylation with high-throughput experimentation and in silico reaction screening

Enhancing the properties of advanced drug candidates is aided by the direct incorporation of specific chemical groups, avoiding the need to construct the entire compound from the ground up. Nevertheless, their chemical intricacy often poses challenges in predicting reactivity for C-H activation reactions and planning their synthesis. We adopted a reaction screening approach that combines high-throughput experimentation (HTE) at a nanomolar scale with computational graph neural networks (GNNs). This approach aims to identify suitable substrates for late-stage C-H alkylation using Minisci-type chemistry. GNNs were trained using experimentally generated reactions derived from in-house HTE and literature data. These trained models were then used to predict, in a forward-looking manner, the coupling of 3180 advanced heterocyclic building blocks with a diverse set of sp3-rich carboxylic acids. This predictive approach aimed to explore the substrate landscape for Minisci-type alkylations. Promising candidates were chosen, their production was scaled up, and they were subsequently isolated and characterized. This process led to the creation of 30 novel, functionally modified molecules that hold potential for further refinement. These results positively advocate the application of HTE-based machine learning to virtual reaction screening.

Transition-Metal-Catalyzed Silylation and Borylation of C-H Bonds for the Synthesis and Functionalization of Complex Molecules

The functionalization of C-H bonds in organic molecules containing functional groups has been one of the holy grails of catalysis. One synthetically important approach to the diverse functionalization of C-H bonds is the catalytic silylation or borylation of C-H bonds, which enables a broad array of downstream transformations to afford diverse structures. Advances in both undirected and directed methods for the transition-metal-catalyzed silylation and borylation of C-H bonds have led to their rapid adoption in early-, mid-, and late-stage of the synthesis of complex molecules. In this Review, we review the application of the transition-metal-catalyzed silylation and borylation of C-H bonds to the synthesis of bioactive molecules, organic materials, and ligands. Overall, we aim to provide a picture of the state of art of the silylation and borylation of C-H bonds as applied to the synthesis and modification of diverse architectures that will spur further application and development of these reactions.