AI-driven robotic chemist for autonomous synthesis of organic molecules

The automation of organic compound synthesis is pivotal for expediting the development of such compounds. In addition, enhancing development efficiency can be achieved by incorporating autonomous functions alongside automation. To achieve this, we developed an autonomous synthesis robot that harnesses the power of artificial intelligence (AI) and robotic technology to establish optimal synthetic recipes. Given a target molecule, our AI initially plans synthetic pathways and defines reaction conditions. It then iteratively refines these plans using feedback from the experimental robot, gradually optimizing the recipe. The system performance was validated by successfully determining synthetic recipes for three organic compounds, yielding that conversion rates that outperform existing references. Notably, this autonomous system is designed around batch reactors, making it accessible and valuable to chemists in standard laboratory settings, thereby streamlining research endeavors.

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.

Navigating with chemometrics and machine learning in chemistry

Chemometrics and machine learning are artificial intelligence-based methods stirring a transformative change in chemistry. Organic synthesis, drug discovery and analytical techniques are incorporating machine learning techniques at an accelerated pace. However, machine-assisted chemistry faces challenges while solving critical problems in chemistry due to complex relationships in data sets. Even with increasing publishing volumes on machine learning, its application in areas of chemistry is not a straightforward endeavour. A particular concern in applying machine learning in chemistry is data availability and reproducibility. The present review article discusses the various chemometric methods, expert systems, and machine learning techniques developed for solving problems of organic synthesis and drug discovery with selected examples. Further, a concise discussion on chemometrics and ML deployed in analytical techniques such as, spectroscopy, microscopy and chromatography are presented. Finally, the review reflects the challenges, opportunities and future perspectives on machine learning and automation in chemistry. The review concludes by pondering on some tough questions on applying machine learning and their possibility of navigation in the different terrains of chemistry.

A versatile non-fouling multi-step flow reactor platform: demonstration for partial oxidation synthesis of iron oxide nanoparticles

In the last decade flow reactors for material synthesis were firmly established, demonstrating advantageous operating conditions, reproducible and scalable production via continuous operation, as well as high-throughput screening of synthetic conditions. Reactor fouling, however, often restricts flow chemistry and the common fouling prevention via segmented flow comes at the cost of inflexibility. Often, the difficulty of feeding reagents into liquid segments (droplets or slugs) constrains flow syntheses using segmented flow to simple synthetic protocols with a single reagent addition step prior or during segmentation. Hence, the translation of fouling prone syntheses requiring multiple reagent addition steps into flow remains challenging. This work presents a modular flow reactor platform overcoming this bottleneck by fully exploiting the potential of three-phase (gas-liquid-liquid) segmented flow to supply reagents after segmentation, hence facilitating fouling free multi-step flow syntheses. The reactor design and materials selection address the operation challenges inherent to gas-liquid-liquid flow and reagent addition into segments allowing for a wide range of flow rates, flow ratios, temperatures, and use of continuous phases (no perfluorinated solvents needed). This "Lego®-like" reactor platform comprises elements for three-phase segmentation and sequential reagent addition into fluid segments, as well as temperature-controlled residence time modules that offer the flexibility required to translate even complex nanomaterial synthesis protocols to flow. To demonstrate the platform's versatility, we chose a fouling prone multi-step synthesis, i.e., a water-based partial oxidation synthesis of iron oxide nanoparticles. This synthesis required I) the precipitation of ferrous hydroxides, II) the addition of an oxidation agent, III) a temperature treatment to initiate magnetite/maghemite formation, and IV) the addition of citric acid to increase the colloidal stability. The platform facilitated the synthesis of colloidally stable magnetic nanoparticles reproducibly at well-controlled synthetic conditions and prevented fouling using heptane as continuous phase. The biocompatible particles showed excellent heating abilities in alternating magnetic fields (ILP values >3 nH m² kg_Fe^-1), hence, their potential for magnetic hyperthermia cancer treatment. The platform allowed for long term operation, as well as screening of synthetic conditions to tune particle properties. This was demonstrated via the addition of tetraethylenepentamine, confirming its potential to control particle morphology. Such a versatile reactor platform makes it possible to translate even complex syntheses into flow, opening up new opportunities for material synthesis.

Autonomous Multi-Step and Multi-Objective Optimization Facilitated by Real-Time Process Analytics

Autonomous flow reactors are becoming increasingly utilized in the synthesis of organic compounds, yet the complexity of the chemical reactions and analytical methods remains limited. The development of a modular platform which uses rapid flow NMR and FTIR measurements, combined with chemometric modeling, is presented for efficient and timely analysis of reaction outcomes. This platform is tested with a four variable single-step reaction (nucleophilic aromatic substitution), to determine the most effective optimization methodology. The self-optimization approach with minimal background knowledge proves to provide the optimal reaction parameters within the shortest operational time. The chosen approach is then applied to a seven variable two-step optimization problem (imine formation and cyclization), for the synthesis of the active pharmaceutical ingredient edaravone. Despite the exponentially increased complexity of this optimization problem, the platform achieves excellent results in a relatively small number of iterations, leading to >95% solution yield of the intermediate and up to 5.42 kg L^-1 h^-1 space-time yield for this pharmaceutically relevant product.

Continuous conversion of furfural to furfuryl alcohol by transfer hydrogenation catalyzed by copper deposited in a monolith reactor

A polymer monolith catalytic reactor, which is fabricated by anchoring –SO3H groups on the surface of the fibers and by depositing Cu species, exhibits outstanding performance and high stability in continuous transfer hydrogenation of furfural.

Developing flow photo-thiol–ene functionalizations of cinchona alkaloids with an autonomous self-optimizing flow reactor

Continuous flow photo-thiol–ene reactions on cinchona alkaloids with a variety of organic thiols have been developed using enabling technologies such as a self-optimizing flow photochemical reactor.

Homogeneous catalyst modifier for alkyne semi-hydrogenation: systematic screening in an automated flow reactor and computational study on mechanisms

21 types of modifiers are screened for palladium catalysed semi-hydrogenation of alkynes with varying catalyst type, reaction time, and target substrate using an automated flow reactor system.

Rxn Rover: automation of chemical reactions with user-friendly, modular software

Automation of chemical reactions through tools such as Rxn Rover in research and development is an enabling technology to reduce cost and waste management in technology transformations towards renewable feedstocks and energy in the chemical industry.

Catalytic hydrogenation of nitrocyclohexane as an alternative pathway for the synthesis of value-added products

Catalytic hydrogenation of nitrocyclohexane could be an alternative source of various useful chemicals: cyclohexanone oxime, cyclohexanone, cyclohexanol, cyclohexylamine and dicyclohexylamine. Each one of these compounds found application in the modern...

Discovering New Chemistry with an Autonomous Robotic Platform Driven by a Reactivity-Seeking Neural Network

We present a robotic chemical discovery system capable of navigating a chemical space based on a learned general association between molecular structures and reactivity, while incorporating a neural network model that can process data from online analytics and assess reactivity without knowing the identity of the reagents. Working in conjunction with this learned knowledge, our robotic platform is able to autonomously explore a large number of potential reactions and assess the reactivity of mixtures, including unknown chemical spaces, regardless of the identity of the starting materials. Through the system, we identified a range of chemical reactions and products, some of which were well-known, some new but predictable from known pathways, and some unpredictable reactions that yielded new molecules. The validation of the system was done within a budget of 15 inputs combined in 1018 reactions, further analysis of which allowed us to discover not only a new photochemical reaction but also a new reactivity mode for a well-known reagent (p-toluenesulfonylmethyl isocyanide, TosMIC). This involved the reaction of 6 equiv of TosMIC in a "multistep, single-substrate" cascade reaction yielding a trimeric product in high yield (47% unoptimized) with the formation of five new C-C bonds involving sp-sp² and sp-sp³ carbon centers. An analysis reveals that this transformation is intrinsically unpredictable, demonstrating the possibility of a reactivity-first robotic discovery of unknown reaction methodologies without requiring human input.

Chemputation and the Standardization of Chemical Informatics

The explosion in the use of machine learning for automated chemical reaction optimization is gathering pace. However, the lack of a standard architecture that connects the concept of chemical transformations universally to software and hardware provides a barrier to using the results of these optimizations and could cause the loss of relevant data and prevent reactions from being reproducible or unexpected findings verifiable or explainable. In this Perspective, we describe how the development of the field of digital chemistry or chemputation, that is the universal code-enabled control of chemical reactions using a standard language and ontology, will remove these barriers allowing users to focus on the chemistry and plug in algorithms according to the problem space to be explored or unit function to be optimized. We describe a standard hardware (the chemical processing programming architecture-the ChemPU) to encompass all chemical synthesis, an approach which unifies all chemistry automation strategies, from solid-phase peptide synthesis, to HTE flow chemistry platforms, while at the same time establishing a publication standard so that researchers can exchange chemical code (χDL) to ensure reproducibility and interoperability. Not only can a vast range of different chemistries be plugged into the hardware, but the ever-expanding developments in software and algorithms can also be accommodated. These technologies, when combined will allow chemistry, or chemputation, to follow computation-that is the running of code across many different types of capable hardware to get the same result every time with a low error rate.

Toward autonomous design and synthesis of novel inorganic materials

Autonomous experimentation driven by artificial intelligence (AI) provides an exciting opportunity to revolutionize inorganic materials discovery and development. Herein, we review recent progress in the design of self-driving laboratories, including robotics to automate materials synthesis and characterization, in conjunction with AI to interpret experimental outcomes and propose new experimental procedures. We focus on efforts to automate inorganic synthesis through solution-based routes, solid-state reactions, and thin film deposition. In each case, connections are made to relevant work in organic chemistry, where automation is more common. Characterization techniques are primarily discussed in the context of phase identification, as this task is critical to understand what products have formed during synthesis. The application of deep learning to analyze multivariate characterization data and perform phase identification is examined. To achieve "closed-loop" materials synthesis and design, we further provide a detailed overview of optimization algorithms that use active learning to rationally guide experimental iterations. Finally, we highlight several key opportunities and challenges for the future development of self-driving inorganic materials synthesis platforms.

Selectivity of the Lindlar catalyst in alkyne semi-hydrogenation: a direct liquid-phase adsorption study

Pd catalysts contain active sites that strongly adsorb alkyne and alkene molecules. The presence of the latter, alkene sites, defines the low semi-hydrogenation selectivity.

Development of a continuous-flow system with immobilized biocatalysts towards sustainable bioprocessing

Implementing immobilized biocatalysts in continuous-flow systems can enable a sustainable process through enhanced enzyme stability, better transport and process continuity as well as simplified recycle and downstream processing.

Artificial intelligence and automation in computer aided synthesis planning

In this perspective we deal with questions pertaining to the development of synthesis planning technologies over the course of recent years.

Catalysis-in-a-Box: Robotic Screening of Catalytic Materials in the Time of COVID-19 and Beyond

This work describes the design and implementation of an automated device for catalytic materials testing by direct modifications to a gas chromatograph (GC). The setup can be operated as a plug-flow isothermal reactor and enables the control of relevant parameters such as reaction temperature and reactant partial pressures directly from the GC. High-quality kinetic data (including reaction rates, product distributions, and activation barriers) can be obtained at almost one-tenth of the fabrication cost of analogous commercial setups. With these key benefits including automation, low cost, and limited experimental equipment instrumentation, this implementation is intended as a high-throughput catalyst screening reactor that can be readily utilized by materials synthesis researchers to assess the catalytic properties of their synthesized structures in vapor-phase chemistries.

Monitoring Chemistry In Situ with a Smart Stirrer: A Magnetic Stirrer Bar with an Integrated Process Monitoring System

Inspired by the miniaturization and efficiency of the sensors for telemetry, we have developed a device that provides the functionalities of laboratory magnetic stirring and integrated multisensor monitoring of various chemical reaction parameters. The device, called "Smart Stirrer", when immersed in a solution, can in situ monitor physical properties of the chemical reaction such as the temperature, conductivity, visible spectrum, opaqueness, stirring rate, and viscosity. This data is transmitted real-time over a wireless connection to an external system, such as a PC or smartphone. The flexible open-source software architecture allows effortless programming of the operation parameters of the Smart Stirrer in accordance with the end-user needs. The concept of the Smart Stirrer device with an integrated process monitoring system has been demonstrated in a series of experiments showing its capability for many hours of continuous telemetry with fine accuracy and a high data rate. Such a device can be used in conventional research laboratories, industrial production lines, flow reactors, and others where it can log the state of the process to ensure repeatability and operational consistency.

The Medicinal Chemistry in the Era of Machines and Automation: Recent Advances in Continuous Flow Technology

Medicinal chemistry plays a fundamental and underlying role in chemical biology, pharmacology, and medicine to discover safe and efficacious drugs. Small molecule medicinal chemistry relies on iterative learning cycles composed of compound design, synthesis, testing, and data analysis to provide new chemical probes and lead compounds for novel and druggable targets. Using traditional approaches, the time from hypothesis to obtaining the results can be protracted, thus limiting the number of compounds that can be advanced into clinical studies. This challenge can be tackled with the recourse of enabling technologies that are showing great potential in improving the drug discovery process. In this Perspective, we highlight recent developments toward innovative medicinal chemistry strategies based on continuous flow systems coupled with automation and bioassays. After a discussion of the aims and concepts, we describe equipment and representative examples of automated flow systems and end-to-end prototypes realized to expedite medicinal chemistry discovery cycles.

Multivariate analysis of inline benchtop NMR data enables rapid optimization of a complex nitration in flow

Multivariate analysis is applied to inline benchtop NMR data for a complex nitration in flow. This rapid quantification enables reaction optimization using advanced techniques in flow, such as design of experiments and dynamic experimentation.

An automated flow platform for accurate determination of gas–liquid–solid reaction kinetics

An automated flow platform based on a tube-in-tube contactor and micro-packed bed reactor is developed to measure the kinetics of gas–liquid–solid hydrogenation reactions.

Reconfigurable Flow Platform for Automated Reagent Screening and Autonomous Optimization for Bioinspired Lignans Synthesis

Naturally occurring benzoxanthenones, which belong to the vast family of lignans, are promising biologically relevant targets. They are biosynthetically produced by the oxidative dimerization of 2-propenyl phenols. In this manuscript, we disclose a powerful automated flow-based strategy for identifying and optimizing a cobalt-catalyzed oxidizing system for the bioinspired dimerization of 2-propenyl phenols. We designed a reconfigurable flow reactor associating online monitoring and process control instrumentation. Our machine was first configured as an automated screening platform to evaluate a matrix of 4 catalysts (plus the blank) and 5 oxidants (plus the blank) at two different temperatures, resulting in an array of 50 reactions. The automated screening was conducted on micromole scale at a rate of one fully characterized reaction every 26 min. After having identified the most promising cobalt-catalyzed oxidizing system, the automated screening platform was straightforwardly reconfigured to an autonomous self-optimizing flow reactor by implementation of an optimization algorithm in the closed-loop system. The optimization campaign allowed the determination of very effective experimental conditions in a limited number of experiments, which allowed us to prepare the natural products carpanone and polemannone B as well as synthetic analogues.

An autonomous self-optimizing flow machine for the synthesis of pyridine–oxazoline (PyOX) ligands

A continuous flow synthesis of PyOX ligands has been developed using an autonomous self-optimizing flow reactor.

An autonomous microreactor platform for the rapid identification of kinetic models

Rapid estimation of kinetic parameters with high precision is facilitated by automation combined with online Model-Based Design of Experiments.

Digital methods and tools for chemical equipment and plants

The Internet of Things (IoT), Industry 4.0, and the digitalization of business processes offer new opportunities and business models for the process industry, including education and training.

Algorithms for the self-optimisation of chemical reactions

Self-optimising chemical systems have experienced a growing momentum in recent years. Herein, we review algorithms used for the self-optimisation of chemical reactions in an accessible way for the general chemist.

Uniting laboratory automation, DoE data, and modeling techniques to accelerate chemical process development

Rapid knowledge building of chemical processes with highly automated DoE (HAD) and statistical analyses and modeling.

Automated platforms for reaction self-optimization in flow

This article highlights recent progress in continuous flow self-optimizing platforms.

Counting bubbles: precision process control of gas–liquid reactions in flow with an optical inline sensor

A 10$ optical liquid sensor allows precise control of reaction conversion in gas-consuming reactions for high selectivity and catalyst utilization.