A Multi-Objective Active Learning Platform and Web App for Reaction Optimization

Multi-armed bandit algorithm for sequential experiments of molecular properties with dynamic feature selection

Sequential optimization is one of the promising approaches in identifying the optimal candidate(s) (molecules, reactants, drugs, etc.) with desired properties (reaction yield, selectivity, efficacy, etc.) from a large set of potential candidates, while minimizing the number of experiments required. However, the high dimensionality of the feature space (e.g., molecular descriptors) makes it often difficult to utilize the relevant features during the process of updating the set of candidates to be examined. In this article, we developed a new sequential optimization algorithm for molecular problems based on reinforcement learning, multi-armed linear bandit framework, and online, dynamic feature selections in which relevant molecular descriptors are updated along with the experiments. We also designed a stopping condition aimed to guarantee the reliability of the chosen candidate from the dataset pool. The developed algorithm was examined by comparing with Bayesian optimization (BO), using two synthetic datasets and two real datasets in which one dataset includes hydration free energy of molecules and another one includes a free energy difference between enantiomer products in chemical reaction. We found that the dynamic feature selection in representing the desired properties along the experiments provides a better performance (e.g., time required to find the best candidate and stop the experiment) as the overall trend and that our multi-armed linear bandit approach with a dynamic feature selection scheme outperforms the standard BO with fixed feature variables. The comparison of our algorithm to BO with dynamic feature selection is also addressed.

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.

Utopia Point Bayesian Optimization Finds Condition-Dependent Selectivity for N-Methyl Pyrazole Condensation

Utopia Point Bayesian Optimization (UPBO) was used to identify reaction conditions that are highly selective for the formation of N1 and N2-methyl-3-aryl pyrazole constitutional isomers. UPBO was used to explore a wide chemical space and identify basic reaction conditions for a typically acid-catalyzed Knorr pyrazole condensation. These studies revealed that selectivity in the reaction stems from a condition-dependent equilibrium of intermediates prior to dehydration. For the N2-methyl isomer reaction pathway, a hemiaminal intermediate was found to form reversibly under the reaction conditions, enabling a highly selective synthesis of the N2 isomer upon dehydrative workup. UPBO was able to successfully optimize conversion and selectivity simultaneously with search spaces of >1 million potential variable combinations without the need for high-performance computational resources.

Sequential closed-loop Bayesian optimization as a guide for organic molecular metallophotocatalyst formulation discovery

Conjugated organic photoredox catalysts (OPCs) can promote a wide range of chemical transformations. It is challenging to predict the catalytic activities of OPCs from first principles, either by expert knowledge or by using a priori calculations, as catalyst activity depends on a complex range of interrelated properties. Organic photocatalysts and other catalyst systems have often been discovered by a mixture of design and trial and error. Here we report a two-step data-driven approach to the targeted synthesis of OPCs and the subsequent reaction optimization for metallophotocatalysis, demonstrated for decarboxylative sp3-sp2 cross-coupling of amino acids with aryl halides. Our approach uses a Bayesian optimization strategy coupled with encoding of key physical properties using molecular descriptors to identify promising OPCs from a virtual library of 560 candidate molecules. This led to OPC formulations that are competitive with iridium catalysts by exploring just 2.4% of the available catalyst formulation space (107 of 4,500 possible reaction conditions).

Toward microfluidic continuous-flow and intelligent downstream processing of biopharmaceuticals

Biopharmaceuticals have emerged as powerful therapeutic agents, revolutionizing the treatment landscape for various diseases, including cancer, infectious diseases, autoimmune and genetic disorders. These biotherapeutics pave the way for precision medicine with their unique and targeted capabilities. The production of high-quality biologics entails intricate manufacturing processes, including cell culture, fermentation, purification, and formulation, necessitating specialized facilities and expertise. These complex processes are subject to rigorous regulatory oversight to evaluate the safety, efficacy, and quality of biotherapeutics prior to clinical approval. Consequently, these drugs undergo extensive purification unit operations to achieve high purity by effectively removing impurities and contaminants. The field of personalized precision medicine necessitates the development of novel and highly efficient technologies. Microfluidic technology addresses unmet needs by enabling precise and compact separation, allowing rapid, integrated and continuous purification modules. Moreover, the integration of intelligent biomanufacturing systems with miniaturized devices presents an opportunity to significantly enhance the robustness of complex downstream processing of biopharmaceuticals, with the benefits of automation and advanced control. This allows seamless data exchange, real-time monitoring, and synchronization of purification steps, leading to improved process efficiency, data management, and decision-making. Integrating autonomous systems into biopharmaceutical purification ensures adherence to regulatory standards, such as good manufacturing practice (GMP), positioning the industry to effectively address emerging market demands for personalized precision nano-medicines. This perspective review will emphasize on the significance, challenges, and prospects associated with the adoption of continuous, integrated, and intelligent methodologies in small-scale downstream processing for various types of biologics. By utilizing microfluidic technology and intelligent systems, purification processes can be enhanced for increased efficiency, cost-effectiveness, and regulatory compliance, shaping the future of biopharmaceutical production and enabling the development of personalized and targeted therapies.

CIME4R: Exploring iterative, AI-guided chemical reaction optimization campaigns in their parameter space

Chemical reaction optimization (RO) is an iterative process that results in large, high-dimensional datasets. Current tools allow for only limited analysis and understanding of parameter spaces, making it hard for scientists to review or follow changes throughout the process. With the recent emergence of using artificial intelligence (AI) models to aid RO, another level of complexity has been added. Helping to assess the quality of a model's prediction and understand its decision is critical to supporting human-AI collaboration and trust calibration. To address this, we propose CIME4R-an open-source interactive web application for analyzing RO data and AI predictions. CIME4R supports users in (i) comprehending a reaction parameter space, (ii) investigating how an RO process developed over iterations, (iii) identifying critical factors of a reaction, and (iv) understanding model predictions. This facilitates making informed decisions during the RO process and helps users to review a completed RO process, especially in AI-guided RO. CIME4R aids decision-making through the interaction between humans and AI by combining the strengths of expert experience and high computational precision. We developed and tested CIME4R with domain experts and verified its usefulness in three case studies. Using CIME4R the experts were able to produce valuable insights from past RO campaigns and to make informed decisions on which experiments to perform next. We believe that CIME4R is the beginning of an open-source community project with the potential to improve the workflow of scientists working in the reaction optimization domain. SCIENTIFIC CONTRIBUTION: To the best of our knowledge, CIME4R is the first open-source interactive web application tailored to the peculiar analysis requirements of reaction optimization (RO) campaigns. Due to the growing use of AI in RO, we developed CIME4R with a special focus on facilitating human-AI collaboration and understanding of AI models. We developed and evaluated CIME4R in collaboration with domain experts to verify its practical usefulness.

Augmenting large language models with chemistry tools

Large language models (LLMs) have shown strong performance in tasks across domains but struggle with chemistry-related problems. These models also lack access to external knowledge sources, limiting their usefulness in scientific applications. We introduce ChemCrow, an LLM chemistry agent designed to accomplish tasks across organic synthesis, drug discovery and materials design. By integrating 18 expert-designed tools and using GPT-4 as the LLM, ChemCrow augments the LLM performance in chemistry, and new capabilities emerge. Our agent autonomously planned and executed the syntheses of an insect repellent and three organocatalysts and guided the discovery of a novel chromophore. Our evaluation, including both LLM and expert assessments, demonstrates ChemCrow's effectiveness in automating a diverse set of chemical tasks. Our work not only aids expert chemists and lowers barriers for non-experts but also fosters scientific advancement by bridging the gap between experimental and computational chemistry.

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.

An integrated self-optimizing programmable chemical synthesis and reaction engine

Robotic platforms for chemistry are developing rapidly but most systems are not currently able to adapt to changing circumstances in real-time. We present a dynamically programmable system capable of making, optimizing, and discovering new molecules which utilizes seven sensors that continuously monitor the reaction. By developing a dynamic programming language, we demonstrate the 10-fold scale-up of a highly exothermic oxidation reaction, end point detection, as well as detecting critical hardware failures. We also show how the use of in-line spectroscopy such as HPLC, Raman, and NMR can be used for closed-loop optimization of reactions, exemplified using Van Leusen oxazole synthesis, a four-component Ugi condensation and manganese-catalysed epoxidation reactions, as well as two previously unreported reactions, discovered from a selected chemical space, providing up to 50% yield improvement over 25-50 iterations. Finally, we demonstrate an experimental pipeline to explore a trifluoromethylations reaction space, that discovers new molecules.

Identifying general reaction conditions by bandit optimization

Reaction conditions that are generally applicable to a wide variety of substrates are highly desired, especially in the pharmaceutical and chemical industries1-6. Although many approaches are available to evaluate the general applicability of developed conditions, a universal approach to efficiently discover these conditions during optimizations is rare. Here we report the design, implementation and application of reinforcement learning bandit optimization models7-10 to identify generally applicable conditions by efficient condition sampling and evaluation of experimental feedback. Performance benchmarking on existing datasets statistically showed high accuracies for identifying general conditions, with up to 31% improvement over baselines that mimic state-of-the-art optimization approaches. A palladium-catalysed imidazole C-H arylation reaction, an aniline amide coupling reaction and a phenol alkylation reaction were investigated experimentally to evaluate use cases and functionalities of the bandit optimization model in practice. In all three cases, the reaction conditions that were most generally applicable yet not well studied for the respective reaction were identified after surveying less than 15% of the expert-designed reaction space.

Deconvoluting Nonlinear Catalyst-Substrate Effects in the Intramolecular Dirhodium-Catalyzed C-H Insertion of Donor/Donor Carbenes Using Data Science Tools

Interactions between catalysts and substrates can be highly complex and dynamic, often complicating the development of models to either predict or understand such processes. A dirhodium(II)-catalyzed C-H insertion of donor/donor carbenes into 2-alkoxybenzophenone substrates to form benzodihydrofurans was selected as a model system to explore nonlinear methods to achieve a mechanistic understanding. We found that the application of traditional methods of multivariate linear regression (MLR) correlating DFT-derived descriptors of catalysts and substrates leads to poorly performing models. This inspired the introduction of nonlinear descriptor relationships into modeling by applying the sure independence screening and sparsifying operator (SISSO) algorithm. Based on SISSO-generated descriptors, a high-performing MLR model was identified that predicts external validation points well. Mechanistic interpretation was aided by the deconstruction of feature relationships using chemical space maps, decision trees, and linear descriptors. Substrates were found to have a strong dependence on steric effects for determining their innate cyclization selectivity preferences. Catalyst reactive site features can then be matched to product features to tune or override the resultant diastereoselectivity within the substrate-dictated ranges. This case study presents a method for understanding complex interactions often encountered in catalysis by using nonlinear modeling methods and linear deconvolution by pattern recognition.

Bayesian Optimization in Drug Discovery

Drug discovery deals with the search for initial hits and their optimization toward a targeted clinical profile. Throughout the discovery pipeline, the candidate profile will evolve, but the optimization will mainly stay a trial-and-error approach. Tons of in silico methods have been developed to improve and fasten this pipeline. Bayesian optimization (BO) is a well-known method for the determination of the global optimum of a function. In the last decade, BO has gained popularity in the early drug design phase. This chapter starts with the concept of black box optimization applied to drug design and presents some approaches to tackle it. Then it focuses on BO and explains its principle and all the algorithmic building blocks needed to implement it. This explanation aims to be accessible to people involved in drug discovery projects. A strong emphasis is made on the solutions to deal with the specific constraints of drug discovery. Finally, a large set of practical applications of BO is highlighted.

Revolutionizing drug formulation development: The increasing impact of machine learning

Over the past few years, the adoption of machine learning (ML) techniques has rapidly expanded across many fields of research including formulation science. At the same time, the use of lipid nanoparticles to enable the successful delivery of mRNA vaccines in the recent COVID-19 pandemic demonstrated the impact of formulation science. Yet, the design of advanced pharmaceutical formulations is non-trivial and primarily relies on costly and time-consuming wet-lab experimentation. In 2021, our group published a review article focused on the use of ML as a means to accelerate drug formulation development. Since then, the field has witnessed significant growth and progress, reflected by an increasing number of studies published in this area. This updated review summarizes the current state of ML directed drug formulation development, introduces advanced ML techniques that have been implemented in formulation design and shares the progress on making self-driving laboratories a reality. Furthermore, this review highlights several future applications of ML yet to be fully exploited to advance drug formulation research and development.

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

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

Mechanism to model: a physical organic chemistry approach to reaction prediction

The application of mechanistic generalizations is at the core of chemical reaction development and application. These strategies are rooted in physical organic chemistry where mechanistic understandings can be derived from one reaction and applied to explain another. Over time these techniques have evolved from rationalizing observed outcomes to leading experimental design through reaction prediction. In parallel, significant progression in asymmetric organocatalysis has expanded the reach of chiral transfer to new reactions with increased efficiency. However, the complex and diverse catalyst structures applied in this arena have rendered the generalization of asymmetric catalytic processes to be exceptionally challenging. Recognizing this, a portion of our research has been focused on understanding the transferability of chemical observations between similar reactions and exploiting this phenomenon as a platform for prediction. Through these experiences, we have relied on a working knowledge of reaction mechanism to guide the development and application of our models which have been advanced from simple qualitative rules to large statistical models for quantitative predictions. In this feature article, we describe the models acquired to generalize organocatalytic reaction mechanisms and demonstrate their use as a powerful approach for accelerating enantioselective synthesis.

Parallel multi-droplet platform for reaction kinetics and optimization

We present an automated droplet reactor platform possessing parallel reactor channels and a scheduling algorithm that orchestrates all of the parallel hardware operations and ensures droplet integrity as well as overall efficiency. We design and incorporate all of the necessary hardware and software to enable the platform to be used to study both thermal and photochemical reactions. We incorporate a Bayesian optimization algorithm into the control software to enable reaction optimization over both categorical and continuous variables. We demonstrate the capabilities of both the preliminary single-channel and parallelized versions of the platform using a series of model thermal and photochemical reactions. We conduct a series of reaction optimization campaigns and demonstrate rapid acquisition of the data necessary to determine reaction kinetics. The platform is flexible in terms of use case: it can be used either to investigate reaction kinetics or to perform reaction optimization over a wide range of chemical domains.

A Customized Bayesian Algorithm to Optimize Enzyme-Catalyzed Reactions

Design of experiments (DoE) plays an important role in optimizing the catalytic performance of chemical reactions. The most commonly used DoE relies on the response surface methodology (RSM) to model the variable space of experimental conditions with the fewest number of experiments. However, the RSM leads to an exponential increase in the number of required experiments as the number of variables increases. Herein we describe a Bayesian optimization algorithm (BOA) to optimize the continuous parameters (e.g., temperature, reaction time, reactant and enzyme concentrations, etc.) of enzyme-catalyzed reactions with the aim of maximizing performance. Compared to existing Bayesian optimization methods, we propose an improved algorithm that leads to better results under limited resources and time for experiments. To validate the versatility of the BOA, we benchmarked its performance with biocatalytic C-C bond formation and amination for the optimization of the turnover number. Gratifyingly, up to 80% improvement compared to RSM and up to 360% improvement vs previous Bayesian optimization algorithms were obtained. Importantly, this strategy enabled simultaneous optimization of both the enzyme's activity and selectivity for cross-benzoin condensation.

Continuous flow synthesis of pyridinium salts accelerated by multi-objective Bayesian optimization with active learning

We report a human-in-the-loop implementation of the multi-objective experimental design via a Bayesian optimization platform (EDBO+) towards the optimization of butylpyridinium bromide synthesis under continuous flow conditions. The algorithm simultaneously optimized reaction yield and production rate (or space-time yield) and generated a well defined Pareto front. The versatility of EDBO+ was demonstrated by expanding the reaction space mid-campaign by increasing the upper temperature limit. Incorporation of continuous flow techniques enabled improved control over reaction parameters compared to common batch chemistry processes, while providing a route towards future automated syntheses and improved scalability. To that end, we applied the open-source Python module, nmrglue, for semi-automated nuclear magnetic resonance (NMR) spectroscopy analysis, and compared the acquired outputs against those obtained through manual processing methods from spectra collected on both low-field (60 MHz) and high-field (400 MHz) NMR spectrometers. The EDBO+ based model was retrained with these four different datasets and the resulting Pareto front predictions provided insight into the effect of data analysis on model predictions. Finally, quaternization of poly(4-vinylpyridine) with bromobutane illustrated the extension of continuous flow chemistry to synthesize functional materials.

Rapid planning and analysis of high-throughput experiment arrays for reaction discovery

High-throughput experimentation (HTE) is an increasingly important tool in reaction discovery. While the hardware for running HTE in the chemical laboratory has evolved significantly in recent years, there remains a need for software solutions to navigate data-rich experiments. Here we have developed phactor™, a software that facilitates the performance and analysis of HTE in a chemical laboratory. phactor™ allows experimentalists to rapidly design arrays of chemical reactions or direct-to-biology experiments in 24, 96, 384, or 1,536 wellplates. Users can access online reagent data, such as a chemical inventory, to virtually populate wells with experiments and produce instructions to perform the reaction array manually, or with the assistance of a liquid handling robot. After completion of the reaction array, analytical results can be uploaded for facile evaluation, and to guide the next series of experiments. All chemical data, metadata, and results are stored in machine-readable formats that are readily translatable to various software. We also demonstrate the use of phactor™ in the discovery of several chemistries, including the identification of a low micromolar inhibitor of the SARS-CoV-2 main protease. Furthermore, phactor™ has been made available for free academic use in 24- and 96-well formats via an online interface.

Bayesian Optimization-Assisted Screening to Identify Improved Reaction Conditions for Spiro-Dithiolane Synthesis

Bayesian optimization (BO)-assisted screening was applied to identify improved reaction conditions toward a hundred-gram scale-up synthesis of 2,3,7,8-tetrathiaspiro[4.4]nonane (1), a key synthetic intermediate of 2,2-bis(mercaptomethyl)propane-1,3-dithiol [tetramercaptan pentaerythritol]. Starting from the initial training set (ITS) consisting of six trials sampled by random screening for BO, suitable parameters were predicted (78% conversion yield of spiro-dithiolane 1) within seven experiments. Moreover, BO-assisted screening with the ITS selected by Latin hypercube sampling (LHS) further improved the yield of 1 to 89% within the eight trials. The established conditions were confirmed to be satisfactory for a hundred grams scale-up synthesis of 1.

Machine Learning Strategies for Reaction Development: Toward the Low-Data Limit

Machine learning models are increasingly being utilized to predict outcomes of organic chemical reactions. A large amount of reaction data is used to train these models, which is in stark contrast to how expert chemists discover and develop new reactions by leveraging information from a small number of relevant transformations. Transfer learning and active learning are two strategies that can operate in low-data situations, which may help fill this gap and promote the use of machine learning for tackling real-world challenges in organic synthesis. This Perspective introduces active and transfer learning and connects these to potential opportunities and directions for further research, especially in the area of prospective development of chemical transformations.

Substrate specific closed-loop optimization of carbohydrate protective group chemistry using Bayesian optimization and transfer learning

A new way of performing reaction optimization within carbohydrate chemistry is presented. This is done by performing closed-loop optimization of regioselective benzoylation of unprotected glycosides using Bayesian optimization. Both 6-O-monobenzoylations and 3,6-O-dibenzoylations of three different monosaccharides are optimized. A novel transfer learning approach, where data from previous optimizations of different substrates is used to speed up the optimizations, has also been developed. The optimal conditions found by the Bayesian optimization algorithm provide new insight into substrate specificity, as the conditions found are significantly different. In most cases, the optimal conditions include Et₃N and benzoic anhydride, a new reagent combination for these reactions, discovered by the algorithm, demonstrating the power of this concept to widen the chemical space. Further, the developed procedures include ambient conditions and short reaction times.

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 field guide to flow chemistry for synthetic organic chemists

Flow chemistry has unlocked a world of possibilities for the synthetic community, but the idea that it is a mysterious "black box" needs to go. In this review, we show that several of the benefits of microreactor technology can be exploited to push the boundaries in organic synthesis and to unleash unique reactivity and selectivity. By "lifting the veil" on some of the governing principles behind the observed trends, we hope that this review will serve as a useful field guide for those interested in diving into flow chemistry.

Self-driving laboratories: A paradigm shift in nanomedicine development

Nanomedicines have transformed promising therapeutic agents into clinically approved medicines with optimal safety and efficacy profiles. This is exemplified by the mRNA vaccines against COVID-19, which were made possible by lipid nanoparticle technology. Despite the success of nanomedicines to date, their design remains far from trivial, in part due to the complexity associated with their preclinical development. Herein, we propose a nanomedicine materials acceleration platform (NanoMAP) to streamline the preclinical development of these formulations. NanoMAP combines high-throughput experimentation with state-of-the-art advances in artificial intelligence (including active learning and few-shot learning) as well as a web-based application for data sharing. The deployment of NanoMAP requires interdisciplinary collaboration between leading figures in drug delivery and artificial intelligence to enable this data-driven design approach. The proposed approach will not only expedite the development of next-generation nanomedicines but also encourage participation of the pharmaceutical science community in a large data curation initiative.

Meta optimization based on real-time benchmarking of multiple surrogate models for autonomous flow synthesis

Optimizing a wide range of reaction parameters, steps, and pathways is currently considered one of the most complex and challenging problems in microflow-based organic synthesis. As a novel solution, Bayesian optimization (BO) has been utilized to efficiently guide the optimized conditions of flow reactors; however, the benchmarking process for selecting the optimal model among various surrogate models remains inefficient. In this work, we report meta optimization (MO) by benchmarking multiple surrogate models in real-time without any pre-work, which is realized by evaluating the expected values obtained by the regressor used to build each surrogate model, enabling efficient optimization of reaction conditions. By the comparison of the performance of MO with that of various BOs on four datasets of different flow syntheses, it was verified that MO consistently performs the best-in-class for all emulators developed through machine learning, while the conventional BOs based on surrogate models such as the Gaussian process, random forest, neural network ensemble, and gradient boosting demonstrated varying performances from each emulator, which implies that benchmarking is required.

AROPS: A Framework of Automated Reaction Optimization with Parallelized Scheduling

With the development of automated experimental platforms and optimization algorithms, chemists can easily optimize chemical reactions in an automated and high-throughput fashion. However, the modules in existing automated experimental platforms are operated in a linear fashion without orchestrating with the optimization algorithm, thus leaving room for further efficiency improvement. Here, we introduced a framework of automated reaction optimization with parallelized scheduling (AROPS) to realize the integration of the optimization algorithm and module scheduling. AROPS relies on a customized Bayesian optimizer to solve multi-reactor/analyzer reaction optimization problems with three different scheduling modes to arrange tasks for various experimental modules. In addition, a mechanism based on probability of improvement (PI) for discarding unpromising ongoing experiments was developed to facilitate freeing up valuable experimental resources in parallelized optimization. We tested the performance of AROPS using a hardware emulator on three representative benchmark reactions encountered in organic synthesis, illustrating that AROPS can trade off optimization time and cost according to the chemists' preference.