Closed-Loop Multitarget Optimization for Discovery of New Emulsion Polymerization Recipes

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.

Transfer Learning of Full Molecular Weight Distributions via High-Throughput Computer-Controlled Polymerization

The skew and shape of the molecular weight distribution (MWD) of polymers have a significant impact on polymer physical properties. Standard summary metrics statistically derived from the MWD only provide an incomplete picture of the polymer MWD. Machine learning (ML) methods coupled with high-throughput experimentation (HTE) could potentially allow for the prediction of the entire polymer MWD without information loss. In our work, we demonstrate a computer-controlled HTE platform that is able to run up to 8 unique variable conditions in parallel for the free radical polymerization of styrene. The segmented-flow HTE system was equipped with an inline Raman spectrometer and offline size exclusion chromatography (SEC) to obtain time-dependent conversion and MWD, respectively. Using ML forward models, we first predict monomer conversion, intrinsically learning varying polymerization kinetics that change for each experimental condition. In addition, we predict entire MWDs including the skew and shape as well as SHAP analysis to interpret the dependence on reagent concentrations and reaction time. We then used a transfer learning approach to use the data from our high-throughput flow reactor to predict batch polymerization MWDs with only three additional data points. Overall, we demonstrate that the combination of HTE and ML provides a high level of predictive accuracy in determining polymerization outcomes. Transfer learning can allow exploration outside existing parameter spaces efficiently, providing polymer chemists with the ability to target the synthesis of polymers with desired properties.

CONTROL-CORE: A Framework for Simulation and Design of Closed-Loop Peripheral Neuromodulation Control Systems

Closed-loop Vagus Nerve Stimulation (VNS) based on physiological feedback signals is a promising approach to regulate organ functions and develop therapeutic devices. Designing closed-loop neurostimulation systems requires simulation environments and computing infrastructures that support i) modeling the physiological responses of organs under neuromodulation, also known as physiological models, and ii) the interaction between the physiological models and the neuromodulation control algorithms. However, existing simulation platforms do not support closed-loop VNS control systems modeling without extensive rewriting of computer code and manual deployment and configuration of programs. The CONTROL-CORE project aims to develop a flexible software platform for designing and implementing closed-loop VNS systems. This paper proposes the software architecture and the elements of the CONTROL-CORE platform that allow the interaction between a controller and a physiological model in feedback. CONTROL-CORE facilitates modular simulation and deployment of closed-loop peripheral neuromodulation control systems, spanning multiple organizations securely and concurrently. CONTROL-CORE allows simulations to run on different operating systems, be developed in various programming languages (such as Matlab, Python, C++, and Verilog), and be run locally, in containers, and in a distributed fashion. The CONTROL-CORE platform allows users to create tools and testbenches to facilitate sophisticated simulation experiments. We tested the CONTROL-CORE platform in the context of closed-loop control of cardiac physiological models, including pulsatile and nonpulsatile rat models. These were tested using various controllers such as Model Predictive Control and Long-Short-Term Memory based controllers. Our wide range of use cases and evaluations show the performance, flexibility, and usability of the CONTROL-CORE platform.

Autonomous polymer synthesis delivered by multi-objective closed-loop optimisation

Application of artificial intelligence and machine learning for polymer discovery offers an opportunity to meet the drastic need for the next generation high performing and sustainable polymer materials. Here, these...

Utilization of machine learning to accelerate colloidal synthesis and discovery

Machine learning techniques are seeing increased usage for predicting new materials with targeted properties. However, widespread adoption of these techniques is hindered by the relatively greater experimental efforts required to test the predictions. Furthermore, because failed synthesis pathways are rarely communicated, it is difficult to find prior datasets that are sufficient for modeling. This work presents a closed-loop machine learning-based strategy for colloidal synthesis of nanoparticles, assuming no prior knowledge of the synthetic process, in order to show that synthetic discovery can be accelerated despite limited data availability.

Self-optimising reactive extractions: towards the efficient development of multi-step continuous flow processes

Downstream purification of products and intermediates is essential for the development of continuous flow processes. Described herein, is a study on the use of a modular and reconfigurable continuous flow platform for the self-optimisation of reactive extractions and multi-step reaction-extraction processes. The selective extraction of one amine from a mixture of two similar amines was achieved with an optimum separation of 90%, and in this case, the black-box optimisation approach was superior to global polynomial modelling. Furthermore, this methodology was utilised to simultaneously optimise the continuous flow synthesis and work-up of N-benzyl-α-methylbenzylamine with respect to four variables, resulting in a significantly improved purity.

Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns

Computational Chemistry is currently a synergistic assembly between ab initio calculations, simulation, machine learning (ML) and optimization strategies for describing, solving and predicting chemical data and related phenomena. These include accelerated literature searches, analysis and prediction of physical and quantum chemical properties, transition states, chemical structures, chemical reactions, and also new catalysts and drug candidates. The generalization of scalability to larger chemical problems, rather than specialization, is now the main principle for transforming chemical tasks in multiple fronts, for which systematic and cost-effective solutions have benefited from ML approaches, including those based on deep learning (e.g. quantum chemistry, molecular screening, synthetic route design, catalysis, drug discovery). The latter class of ML algorithms is capable of combining raw input into layers of intermediate features, enabling bench-to-bytes designs with the potential to transform several chemical domains. In this review, the most exciting developments concerning the use of ML in a range of different chemical scenarios are described. A range of different chemical problems and respective rationalization, that have hitherto been inaccessible due to the lack of suitable analysis tools, is thus detailed, evidencing the breadth of potential applications of these emerging multidimensional approaches. Focus is given to the models, algorithms and methods proposed to facilitate research on compound design and synthesis, materials design, prediction of binding, molecular activity, and soft matter behavior. The information produced by pairing Chemistry and ML, through data-driven analyses, neural network predictions and monitoring of chemical systems, allows (i) prompting the ability to understand the complexity of chemical data, (ii) streamlining and designing experiments, (ii) discovering new molecular targets and materials, and also (iv) planning or rethinking forthcoming chemical challenges. In fact, optimization engulfs all these tasks directly.

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.

Autonomous Molecular Design: Then and Now

The success of deep machine learning in processing of large amounts of data, for example, in image or voice recognition and generation, raises the possibilities that these tools can also be applied for solving complex problems in materials science. In this forum article, we focus on molecular design that aims to answer the question on how we can predict and synthesize molecules with tailored physical, chemical, or biological properties. A potential answer to this question could be found by using intelligent systems that integrate physical models and computational machine learning techniques with automated synthesis and characterization tools. Such systems learn through every single experiment in an analogy to a human scientific expert. While the general idea of an autonomous system for molecular synthesis and characterization has been around for a while, its implementations for the materials sciences are sparse. Here we provide an overview of the developments in chemistry automation and the applications of machine learning techniques in the chemical and pharmaceutical industries with a focus on the novel capabilities that deep learning brings in.

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.

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.

Optimum catalyst selection over continuous and discrete process variables with a single droplet microfluidic reaction platform

A mixed-integer nonlinear program (MINLP) algorithm to optimize catalyst turnover number (TON) and product yield by simultaneously modulating discrete variables—catalyst types—and continuous variables—temperature, residence time, and catalyst loading—was implemented and validated.

Self-optimisation and model-based design of experiments for developing a C-H activation flow process

A recently described C(sp3)-H activation reaction to synthesise aziridines was used as a model reaction to demonstrate the methodology of developing a process model using model-based design of experiments (MBDoE) and self-optimisation approaches in flow. The two approaches are compared in terms of experimental efficiency. The self-optimisation approach required the least number of experiments to reach the specified objectives of cost and product yield, whereas the MBDoE approach enabled a rapid generation of a process model.

Towards dial-a-molecule by integrating continuous flow, analytics and self-optimisation

The employment of continuous-flow platforms for synthetic chemistry is becoming increasingly popular in research and industrial environments. Integrating analytics in-line enables obtaining a large amount of information in real-time about the reaction progress, catalytic activity and stability, etc. Furthermore, it is possible to influence the reaction progress and selectivity via manual or automated feedback optimisation, thus constituting a dial-a-molecule approach employing digital synthesis. This contribution gives an overview of the most significant contributions in the field to date.