Crystallisation is the process of forming a solid crystal from a solution of molecules. It is an important process in the development and manufacturing of small molecule new medicines. The crystalline particles that go into "solid dosage forms" of medicines like tablets and inhalation drugs (where clinical performance is directly correlated to particle behaviour) need to be well understood so that pharmaceutical scientists can design the processes and workflows that will allow them to manufacture new medicines quickly and safely. Currently, a significant body of experimental work is required to understand the crystallisation behaviour of a new pharmaceutical molecule. Getting this wrong can lead to significant problems during medicines manufacturing, requiring time and resource intensive experimental trials by industrial scientists to ensure effective control strategies for crystallisation and particle design. By developing new software to simulate crystallisation processes, scientists could do a lot of this exploratory work on a computer, eliminating the need for experiments that can generate significant harmful waste (such as solvents) in addition to considerable raw material and energy costs. This could make the development of new medicines much greener and help the pharmaceutical industry to meet its Net-Zero goals. These digital approaches could also increase efficiency in the way that pharmaceuticals are manufactured, meaning that new medicines can be delivered to patients faster. This project will take some software models that have been developed by chemical engineers at the University of California Santa Barbara and embed it into an existing computer programme that industrial scientists are familiar with. State of the art crystallisation experiments will be performed to validate, inform and improve the models. This will deliver a crystallisation prediction tool able to minimise the experiments required, resulting enabling greener solvent selection and reduced material and energy waste during pharmaceutical R&D and manufacturing.

The pharmaceutical industry is a major contributor to global greenhouse gas (GHG) emissions, with the UK healthcare sector accounting for 5% of the nation's total emissions, 20% of which are linked to medicines. Pharmaceutical emissions are 55% higher than those of the automotive industry, generating up to 100 kg of waste per kg of product. This carbon footprint is expected to increase further due to the rise in smaller production volumes, personalised therapies, and other emerging factors. To tackle this challenge, we need a strong partnership that can make the UK a leader in sustainable, innovative medicines production, benefiting the economy, society, and the environment. The Grand Challenge (GC) aims to transform how medicines are made by shifting from outdated, costly medicine development and manufacturing systems to automated and resource efficient approaches. This new approach will integrate advanced digital tools with medicines development and manufacturing technologies, allowing labs and factories to produce medicines more efficiently and with less waste. One key feature is the creation of a network of self-driving development and manufacturing systems, which can communicate, operate and share information securely in real-time. A cloud-based platform with different services will deliver new ways of data management, sustainability, and regulatory compliance. These tools will realise a step change in how the industry ensures safety, quality, and environmental impact of the medicines we produce. A user-friendly platform will allow companies to use these tools remotely and improve their processes. During the Expression of Interest (EoI) phase, we will work with key stakeholders to develop a detailed plan for this initiative. This will involve working groups that focus on different areas, such as building partnerships, developing use cases, creating digital infrastructure, and promoting sustainability. The goal is to create a roadmap for the future of medicines manufacturing.

The Pharmaceutical industry is really good at employing molecular-level chemistry models to help predict likely new cures for diseases. On the flip side it is bad (vs. other industries) at applying modelling to manufacturing to predict how and when to make products most effectively. This is for a number of reasons, one of which is the lack of good quality data. This would enable the models to make better predictions; as more good data, leads to better predictions. One way to get more data is to make it yourself, but that's expensive and wasteful as a solo effort. It's much better if you can share. Companies find it hard to trust each other sharing data though, as they are competitors. So sharing is blocked by cyber security concerns, commercial threats, and the lack of certainty that the data will be used as intended. One way to fix these concerns is to employ Federated Data sharing technologies. These novel digital tools address the concerns of 'who has access to data' and 'why', because you can control these aspects centrally. They are also very cyber secure. They do not solve the concerns of commercial threat, however. As, if you share all of your data, you may well give away valuable secrets. The obvious solution is to share data (through the new technologies) but share segments of the data, not the whole. This way modelling outcomes can be achieved more effectively, but you're not giving away valuable information. The trouble here is that there is little evidence that redacted datasets lead to better modelling outcomes. There is also a business risk, as there are very few practical tools available to determine how much data is 'too much' data shared. This project (SHARPEN) intends to deliver a platform for data sharing (so we can assess it) that runs across R&D data to manufacturing (ensuring good data transfer across all relevant data) and deliver a risk assessment tool (to enable rapid assessment and subsequent sharing of data), as well as working out what someone would pay for that service. We will deliver the outcomes through diverse partners who have significant experience in the pharmaceutical sector and who've successfully worked together in the past. We will enable a number of market ready digital tools in the process. Ensuring medicines manufacturing becomes more efficient through effective use of models to accurately predict what to do next.

Ensuring reliable access to affordable, safe, effective, sustainable, and high-quality 21st-century medicines requires 21st-century technologies and, crucially, harmonised, effective and innovative regulatory approaches. This UK regulatory science network aims to deliver the 21st-century regulatory science and innovation needed to unlock the benefits of the digital transformation of medicines development and manufacturing for the pharmaceutical industry, regulators, and society. The network will address sector-specific challenges, such as unclear regulatory frameworks, the complexity of AI-based models, data quality and security concerns, regulatory expertise shortages, and trust issues among patients and the public. A particular focus will be on AI and predictive models, as well as autonomous and regulatory-ready data generation through robotics and automation. This strategic initiative aims to bring the UK development, manufacturing and regulatory ecosystem together to transform these emerging digital technologies into critical components of medicines regulatory submission, assessment, and inspection by building consensus on standards to enable the digital transformation of these processes essential for delivering new medicines. The network will unite research institutions, small and medium-sized enterprises, pharma, biotech, technology vendors, and regulators to achieve its objectives. The fourfold strategy includes forging collaborations, creating evidence-based research for digital technologies, advocating and enabling regulatory science and modern practices, and providing training and translation programmes. Leveraging existing partnerships with global pharma companies, technology and software providers, academic networks, and strategic alliances with innovation centres, the network aims to drive international regulatory policy and practice in the sector and reposition regulation as an enabler of growth, able to adopt new, adaptive approaches and regulatory models. This network brings direct benefits to a range of stakeholders. By accelerating and streamlining the regulatory process, it accelerates the development of life-saving drugs, ensuring faster patient access while increasing operational efficiency and improving sustainability. Global technology providers gain advantages through seamless alignment with regulatory standards, positioning them at the forefront of innovation. In the academic sector, the network fosters collaboration between academia, industry, and regulators, contributing to a pro-innovation regulatory system, while regulators benefit from an enhanced, efficient, and digitally supported regulation system, leading to faster decision-making. The ultimate beneficiaries are the general public, as the network facilitates the accelerated supply of new, effective medicines, addressing critical healthcare needs promptly and safely and contributing to improved public health outcomes. Overall, the regulatory science and innovation network emerges as a dynamic force advancing healthcare to benefit individuals and communities.

To develop and bring to market a state-of-the-art digital design platform to significantly automate, streamline and accelerate the design, development and manufacturing processes for pharmaceutical products.

New therapeutic products in the pharma industries are invariably large, complex chemical molecules -- e.g., synthetic active ingredients, amino acids, peptides etc. In the consumer goods and food industries, complex emulsions form the backbone of products such as detergents, beauty products, milk and other liquid-based foods. An essential pre-requisite for model-based Digital Design and Production of these materials is the accurate prediction of their physical and other behavioural properties. Quick and reliable property calculations will allow a transformational way of working which will benefit customers, e.g. by accelerating access to novel oncology therapies with improved efficacy.Traditional approaches for material property prediction for complex systems rely primarily on empirical methods that require extensive experimentation and offer limited predictive accuracy beyond the range of experimental data. This severely limits their applicability within Digital Design, where the ability to investigate a wide range of alternatives _in silico_ without the need for extensive experimentation is key.Recent advances in statistical mechanics of fluids are beginning to offer the promise of a more systematic and rigorous approach to addressing at least some key challenges, e.g., the prediction of solid/liquid equilibria (solubility) for pharmaceutical systems of industrial importance, speciation of complex reactive mixtures, and transport properties for a wide range of systems. These academic developments have been paralleled by the emergence of a new commercially-available software code called gPROMS Properties, which incorporates recent academic advances in this area and is already fully coupled within process modelling tools used to underpin Digital Design applications in the pharmaceutics, food and chemicals sectors.Today, gPROMS Properties is being successfully applied to the Oil & Gas and chemical/petrochemical industries, where the systems of interest are primarily gases and simple fluids. This fast-track project aims to develop and extend gPROMS Properties to become an enabling technology able to meet the more complex needs of the formulated products industries, using a two-pronged approach. The technological basis will be developed by expanding the _types_ of systems that can be handled (e.g. emulsions) and the _types_ of properties that can be predicted (e.g. solid/liquid equilibria, micelle formation conditions, and rheological properties). Simultaneously, the _ranges_ of molecules that can be modelled will be expanded by further exploration of publicly available data. These developments will be applied by industrial partners to solve business problems, demonstrating that virtual product and process design in the formulated products industries is now coming within reach.

.