This project aims to create a new artificially intelligent continuous flow platform for the development of multistep chemical and biocatalysed reactions. Pharmaceuticals are complex molecules which require multiple transformations to synthesise from readily available starting materials. Traditionally they are produced via batch manufacturing, where after each step intermediates are stored in containers or shipped to other facilities around the world to complete the manufacturing process. This adds a significant amount of processing time, contributes to a large carbon footprint, and is at significant risk of supply chain disruptions. In contrast, continuous manufacturing addresses each of these challenges by enabling end-to-end production within the same facility. Catalysts are substances which are added to reactions which influence the rate and/or outcome of the reaction without been consumed. A well-designed catalyst will minimise the generation of waste by being highly selective, recyclable, and only required in very small quantities, often replacing the use of larger amounts of toxic reagents. Hence, it is economically and environmentally desirable to include multiple catalysed steps in a manufacturing process. Alone, the benefits of catalysis and continuous flow are becoming increasingly relevant due to the drive for decarbonisation, but in combination, they have the potential to truly transform the next generation of sustainable manufacturing. However, combining different types of catalysis into continuous flow processes remains highly challenging, due to poor compatibility between catalysts and the large number of variables that need to be optimised. In this project we will develop a fully autonomous and artificially intelligent multistep continuous flow platform, which is capable of simultaneously optimising interconnected catalytic reactions. New multipoint analysis and automated reconfiguration capabilities will enable the creation of individual feedback loops for each reaction, which will be driven by machine learning algorithms suitable for multiobjective and mixed variable systems. We will then demonstrate this approach for the optimisation of industrially relevant chemoenzymatic cascades in sustainable and mutually compatible reaction media (e.g., deep eutectic solvents), thus combining the versatile reactivity of chemocatalysis with the high selectivity of biocatalysis.

KEYWORDS: chemistry, computer vision, image processing, manufacturing, productivity, process monitoring. Chemical and biochemical manufacturing are dominated by colour changes, both subtle and stark. Such phenomena are often reported by-eye but not routinely quantified, especially over time. This renewal of a research and leadership programme aims to empower any chemist with any camera to capture any visible trend from any high-value chemical process, all without having to disturb the process under study. Most industrial chemists are accustomed to extracting chemical monitoring information using invasive, probe-based technologies. These technologies are robust and trusted. However, no current technologies are seamlessly applicable to monitoring chemical processes in real-time on BOTH the high throughput lab scale (the 'teacup') AND process/plant scales (the 'swimming pool'). Instead, current process analytical technologies are oftentimes tied to one specific hardware platform, and each example of such probe-based hardware can only monitor one process at a time. Ultimately, this can produce bottlenecks in analysis, slowing chemical product development and deployment. To address this productivity and chemical data throughput challenge, there is a real drive from R&D budget holders to invest in digital-ready analytical technologies. Computer Vision is the science of digitally quantifying real-world colours and objects using cameras. With cameras and computer vision, and further development through this fellowship renewal, the hardware and software needed for more time-, cost-, and safety-effective monitoring of high-value chemical processes can be realised in an accessible and globally adoptable manner. The global investment for digitalisation of process analytical technology (PAT) in the chemical industry is expected to reach $31 billion by 2028, representing an annual growth rate of approximately 6% from the present $23.5 billion market (sources: Made Smarter Review, 2017. Frost & Sullivan, 2017, and 2022). Underpinning this trend, R&D managers across chemical manufacturing are driving the streamlined adoption of new digital-ready chemical technology, to improve productivity, process safety, and ability to exploit the adjacent evolution of artificial intelligence.

The switch from traditional organic solvents, many of which are hazardous, volatile or non-sustainable, to modern green solvents is one of the key sustainability objectives in High Value Chemical Manufacture. Currently, the use of green solvents is often explored at process development stage, instead of discovery stage. This necessitates re-optimisation of processes, due to changes in yield, selectivity, impurity profile and purification. These lead to longer development time, cost, and additional uncertainty. On the other hand, selecting the right solvent early may enhance chemoselectivity, avoid additional reaction steps, and simplify purification of the products. Predicting these changes is an important underpinning capability for wider adaptation of green solvents in manufacturing. Unfortunately, the scarcity of reaction data in green solvents is a key obstacle in developing this capability. Thus, there is an urgent need for ML models which predict reactivity in green solvents based on available data in traditional solvents. In addition to addressing the short time-scale of early-stage process development, these will increase the confidence in utilising green solvents at discovery stage, support sophisticated synthetic routes planning tools which takes into account side products, impurity and purification methods, and act as valuable regulatory tools for assessing hazardous impurities. This project will address these challenges through the following objectives: O1 Addressing the scarcity of reactivity data in the literature through curation of reaction data with reliable reaction time and inclusion of rate laws. O2 Developing solvent-dependent reactivity and reaction selectivity prediction models for green solvents. O3 Producing a set of standard substrates based on cheminformatics analysis of industrially relevant reactions and collecting their reactivity data in green solvents. These outputs will have transformative impacts in the chemical manufacture industry, delivering rapid, more sustainable and better quality-controlled processes through shorter development time, and confidence in predicting reaction outcomes in green solvents. The project will be carried out with support from industrial partners working in the field of cheminformatics and AI/Machine learning, e.g. Lhasa Ltd. and Molecule One. Its outputs will be guided and exploited by partners who are end-users in the High Value Chemical Manufacturing sectors: AstraZeneca, CatSci, and Concept Life Science.

Our society is highly dependent on catalytic science which is central to major global challenges such as efficient conversion of energy, mitigation of greenhouse gases, destroying pollutants in the atmosphere and in water, and processing biomass which all rely intrinsically on catalysis. In addition, catalysis is a key technology for the chemical industry; it is estimated that catalytic science contributes to 90% of chemical manufacturing processes. Chemistry-using industries are is a major component of the UK's manufacturing output and vital part of the overall UK economy, generating in excess of £50 billion per annum. The ONS Annual Business Survey (2012) estimated chemical and pharma manufacturing to be worth £19 billion p.a. and predicted that by 2030, the UK chemical industry will have enabled the chemistry-using industries to increase their Gross Value Added contribution to the UK economy by 50%, from £195 billion to £300 billion. Understanding how catalyst work is notoriously difficult because of the low concentrations and transient nature of catalytically active species. In this project will develop new equipment based on state-of-the-art flow NMR methods that will enable the rapid development of new catalysts for academic research and industrial processes. Crucially the equipment we propose will allow high sensitivity and real-time monitoring of catalytic reactions under a wide range of realistic reaction conditions (e.g., concentrations, temperatures and pressures). This will provide a unique facility to study the scope, productivity, selectivity and deactivation of catalysts, which in turn will provide insight into mechanisms and allow us to develop new catalytic systems. The equipment will be utilized by academic and industrial scientists and engineers at the University of Bath and throughout the UK to understand and develop catalysts for a wide range of processes of academic and industrial relevance. Areas that will benefit from the equipment will include; catalysts for renewable polymers, catalysts for utilisation and valorisation of biomass, catalysts for sustainable energy, and catalysts for sustainable synthesis of pharmaceuticals and fine chemicals. The progress that will be enabled by the equipment will be exploited, particularly within the pharma and fine chemicals sectors, through collaboration with a wide variety of UK catalyst companies and chemical producers.

Humanity faces critical global challenges in supplying clean energy, food, medicines and materials for a population forecast to reach 10 billion by 2050. Chemical synthesis will play a central role in addressing these challenges, as organic molecules are the fundamental building blocks of drugs, agrochemicals, and materials. However, the synthesis of most chemicals remains energy intensive, requiring fossil fuel feedstocks and endangered metal catalysts, and produces huge levels of waste - far from what is needed for a net-zero future. The essential transition to a circular chemistry economy will materialise only with a total re-think of organic synthesis: a 'Chemical Revolution' is urgently needed, for which Industry users will require a 'next generation' of suitably trained graduates. Without such change, the chemical industry will not be able to sustain the necessary pace of innovation in new chemical technologies, in the face of rapidly changing chemical regulation and policy, thus rendering this CDT crucial for the future of UK PLC. The Oxford-York ESPRC CDT in Chemical Synthesis for a Healthy Planet will deliver world-leading, ground-breaking training to a next generation of synthetic chemists, developing a sustainable, innovative chemistry culture that equips them to address major emerging and future global challenges in Human Health, Energy and Materials, and Food Security. In doing so, we meet a critical User Need, by supplying the workforce that is essential to create the innovative solutions UK chemical industries urgently require. Our overarching objective is to train students to supersede current practices for the synthesis of functional organic molecules by developing sustainable, field-advancing synthetic pathways to the complex targets needed in drug discovery, agrochemistry, and materials development. Our student cohorts will work together in a training period at both Oxford and York, before engaging with industry co-supervised projects in four research fields that develop innovative, sustainable transformations and synthetic strategies, and apply them in pharma, agro and materials chemistry contexts. With around a third of projects supervised jointly at Oxford and York, we will ensure a strong cross-institute connection; whole programme meetings and research field seminars will enable students across multiple cohorts to contribute to and elevate each others' science. Our association with the Eur1.25bn Center for the Transformation of Chemistry brings a unique connection for our students to a major initiative that is aiming to revolutionise chemical synthesis, as well its >140 chemical organisations across Europe. Our partnership with >10 SMEs and their Entrepreneurs-in-Residence will develop entrepreneurial skills and ensure students are exposed to the cutting-edge of chemical innovation in UK PLC. The applications and benefits from the CSHP CDT are many: Primarily, we will develop a UK-wide network of sustainably-minded, innovative chemists ready to meet the urgent User Needs of the UK chemical industry, bolstering this major sector of UK PLC. The scientists graduating from the CSHP CDT, the high-level science they produce, along with the related tools and technologies, will all contribute to the UK's ambitions as a Physical and Mathematical Sciences Powerhouse. We will set new benchmarks for graduate training by ensuring sustainability is embedded and visible in all research and its outputs, as well as influencing and connecting to graduates across the UK through biennial symposia. Our cohorts' work as Sustainability Ambassadors will permeate our exciting discoveries and the message of the future role of synthetic chemistry throughout society - from school to the general public. Above all, we believe this rigorous and inspirational programme is utterly essential if the UK is to remain globally competitive in the rapidly evolving chemistry landscape.