The efficiency of drug discovery has been falling for decades such that, for each new molecule that reaches the consumer, estimated research and development costs are in excess of $2 billion. The drug discovery process involves the design of, usually, a small organic molecule that is capable of binding to its target in vivo with therapeutic benefit. Part of the problem is that during this pipeline too many molecules are synthesised in the lab, at great expense, that turn out not to have the required binding affinity. A computational model that is capable of reliably predicting binding from structure is needed. Allied with structural biology methods, such as x-ray crystallography and cryo-electron microscopy, computational structure-based biomolecular simulation is an important part of the solution. At the simplest level, biomolecular simulation can be used to 'animate' the static pictures solved by structural biology, by finding the forces on the atoms, and hence solving for their dynamics. But we can also move beyond this, and use rigorous thermodynamics to predict the effects that changes in structures of potential drug molecules will have on binding to their target. Such approaches were employed by computational researchers all over the world during the COVID-19 pandemic to urgently provide new understanding of the SARS-CoV-2 virus and to design inhibitors of its function. Although we know that the forces on the atoms should be calculated using the equations of quantum mechanics, these are much too computationally costly to solve routinely for biological problems. Instead the dynamics and interactions of biological molecules are typically computed using a simplified computational model, known as a force field. The force field models the atoms as bonded by springs, and interacting with each other through electrostatic and van der Waals forces. The strengths of these interactions are modelled by thousands of adjustable parameters, which have been tuned to reproduce experimental data. These force fields are an important enabling technology for biomolecular simulation scientists, and the accuracy of their predictions depends on the realism of the force field model and its parameters. Traditionally, force field models evolved over periods of many decades. Design decisions taken early in the process became 'baked in', since re-training the model with new design rules was infeasible. The Open Force Field Initiative is an academic-industrial partnership aiming to advance the science and software infrastructure required to build the next generation of molecular mechanics force fields. In one example of our work from the first period of the Fellowship, we have co-developed a flexible framework to extend the Open Force Field software stack with custom force field models. In a proof-of-principle, we were able to train and test a new generalised force field model in a matter of weeks, rather than years, with improvements in accuracy over traditional force fields. My vision for the renewal period of the Future Leaders Fellowship is to deploy this software infrastructure to rapidly move from new hypotheses to trained force field models, with unambiguous determination of the effects of design decisions on model accuracy. For example, I will test whether machine learning models trained on high-level quantum mechanical datasets yield accurate force field atomic charges, and whether accurate protein force field models can be built using the new force field models described above. Force field models that show requisite accuracy will be deployed in molecular design workflows. Through working with the project partners in the pharmaceutical industry and at an open science antiviral discovery initiative, I will showcase the accuracy improvements in structure-based biomolecular simulations that will translate to improved efficiency of the drug discovery pipeline.

Computational biomedicine offers many avenues for taking full advantage of emerging exascale computing resources and provides a wealth of benefits as one of the use-cases within the wider ExCALIBUR initiative. The CompBioMedEE project aims to promote and support the use of computational biomedical modelling and simulation at the exascale within the biomedical research community. We shall demonstrate to our community how to develop and deploy applications on emerging exascale machines to achieve increasingly high-fidelity descriptions of the proteins and small molecules of the human body in health and disease. Within the biomedical research domain, we will focus on the discipline of structural and molecular biology. This will enable us to provide the support needed to achieve a wide range of outcomes from determining how the functional and mechanistic understanding of how molecular components in a biological system interact to the use of drug discovery methods to the design of novel therapeutics for a diversity of inherited and acquired diseases. CompBioMedEE will use the IMPECCABLE drug discovery workflow from the UKRI-funded CompBioMedX project. The IMPECCABLE software has been taken through extreme scaling and is eminently suited to bringing computational biomedicine researchers, particularly those from experimental backgrounds who do molecular modelling, to the exascale. The molecular dynamics engine that is part of the IMPECCABLE code is suited to standalone use, enabling biomedical researchers new to HPC to perform molecular dynamics simulations and, through this, to develop the computational expertise required for peta- and exascale use of the IMPECCABLE code. The CompBioMedEE project will engage with biomedical researchers at all career stages, providing them with the compute resource needed to support computational research projects. Through proactive engagement with medical and undergraduate biosciences students, we will illustrate the benefits of using modelling and supercomputers and establish a culture and practice of using computational methods to inform the experimental and clinical work from bench to bedside.

Chemistry impacts most areas of our lives, including healthcare, energy production, and the environment. It is also the UK's second largest manufacturing industry, employing 140,00 people. This hub will bring the transformative power of artificial intelligence (AI) to the area of chemistry, and by doing so have a major societal impact. Both AI and chemistry are fast-moving and historically separated research disciplines, and there is huge untapped potential to collaborate at the interface of these two fields. Today, relatively few UK experimental chemists are exploiting AI (e.g., for reaction optimization), and few have corresponding automation facilities to do this, which is a missed opportunity. The use of machine learning methods is more common in computational chemistry, but here also we are often data poor, and data is sparse. In some AI fields, such as natural language processing, there is also rapidly evolving, leading-edge industrial research, necessitating a cross-sector approach if we are to exploit the cutting edge of this technology. This hub (AIchemy) will bring together leading researchers in AI and trailblazers at the interface of AI for chemistry, spanning both university and industry. We will exploit unique established facilities and institutes in the four core partner institutions (Universities of Liverpool, Imperial, Cambridge, and Southampton) where cross-discipline working has already been achieved: this includes the Materials Innovation Factory (MIF), the Institute for Digital Molecular Design and Fabrication (DigiFAB), and the I-X Centre for AI in Science. In addition to the 6 lead investigators, we have aligned 25 other investigators across nine institutions, spanning the areas of AI, robotics, and a diverse range of experimental and computational chemistry sub-disciplines, and career stages. The team also includes unique expertise in robotics and automation (Liverpool & Imperial), natural language processing for chemistry problems (Cambridge) and data curation in the Physical Sciences Data Infrastructure (PSDI, Southampton). This diverse team and associated facilities give us the breadth of expertise and critical mass to become the core of a UK hub for this activity. AIchemy will carry out world-leading research at the AI/chemistry interface, building on distinctive UK strengths in this area and developed initially via 6 Forerunner Projects. The Hub will also build an approach for sharing chemistry research data and code in a common format to unite the currently fragmented UK research landscape. We also aim to dramatically broaden the number of AI researchers tackling chemistry problems, and vice versa, through a mixture of pump-priming funding in the hub, bespoke training, access to datasets, and events (e.g., AI challenges using hub-generated data). To ensure the long-term health of this discipline, we will also focus resource on projects that are led by early career academics. The hub will build a UK-wide consortium involving university and industry stakeholders outside of the core partners, including a broad set of 15 day-one industry partners across the sectors of AI and chemistry, to be further expanded in the full proposal. The team has an excellent collective track record in industry engagement and knowledge transfer; e.g. MIF collocates 100 industry researchers in a common facility with academics; Chemistry is co-located with IX at Imperial's £2 Bn White City campus, and there are shared spaces to enable 800 scientists and industry partners to work together on common challenges, with tailor-made labs and offices for early stage companies. Mirroring the enormous benefits that have been achieved in other science areas, such as structural biology, this hub will transform the UK landscape for the discipline of chemistry, transforming engagement with AI from a relatively niche activity to a core, platform methodology.