Building upon our existing flagship industry-linked EPSRC & MRC CDT in Systems Approaches to Biomedical Science (SABS), the new EPSRC CDT in Sustainable Approaches to Biomedical Science: Responsible and Reproducible Research - SABS:R^3 - will train a further five cohorts, each of 15 students, in cutting-edge systems approaches to biomedical research and, uniquely within the UK, in advanced practices in software engineering. Our renewed goal is to bring about a transformation of the research culture in computational biomedical science. Computational methods are now at the heart of biomedical research. From the simulation of the behaviour of complex systems, through the design and automation of laboratory experiments, to the analysis of both small and large-scale data, well-engineered software has proved capable of transforming biomedical science. Biomedical science is therefore dependent as never before on research software. Industries reliant on this continued innovation in biomedical science play a critical role in the UK economy. The biopharmaceutical and medical technology industrial sectors alone generate an annual turnover of over £63 billion and employ 233,000 scientists and staff. In his foreword to the 2017 Life Sciences Industrial Strategy, Sir John Bell noted that, "The global life sciences industry is expected to reach >$2 trillion in gross value by 2023... there are few, if any, sectors more important to support as part of the industrial strategy." The report identifies the need to provide training in skills in "informatics, computational, mathematical and statistics areas" as being of major concern for the life sciences industry. Over the last 9 years, the existing SABS CDT has been working with its consortium of now 22 industrial and institutional partners to meet these training needs. Over this same period, continued advances in information technology have accelerated the shift in the biomedical research landscape in an increasingly quantitative and predictive direction. As a result, computational and hence software-driven approaches now underpin all aspects of the research pipeline. In spite of this central importance, the development of research software is typically a by-product of the research process, with the research publication being the primary output. Research software is typically not made available to the research community, or even to peer reviewers, and therefore cannot be verified. Vast amounts of research time is lost (usually by PhD students with no formal training in software development) in re-implementing already-existing solutions from the literature. Even if successful, the re-implemented software is again not released to the community, and the cycle repeats. No consideration is made of the huge benefits of model verification, re-use, extension, and maintainability, nor of the implications for the reproducibility of the published research. Progress in biomedical science is thus impeded, with knock-on effects into clinical translation and knowledge transfer into industry. There is therefore an urgent need for a radically different approach. The SABS:R^3 CDT will build on the existing SABS Programme to equip a new generation of biomedical research scientists with not only the knowledge and methods necessary to take a quantitative and interdisciplinary approach, but also with advanced software engineering skills. By embedding this strong focus on sustainable and open computational methods, together with responsible and reproducible approaches, into all aspects of the new programme, our computationally-literate scientists will be equipped to act as ambassadors to bring about a transformation of biomedical research.

Doctoral Training Partnerships: a range of postgraduate training is funded by the Research Councils. For information on current funding routes, see the common terminology at https://www.ukri.org/apply-for-funding/how-we-fund-studentships/. Training grants may be to one organisation or to a consortia of research organisations. This portal will show the lead organisation only.

Many existing challenges, from personalized health care to energy production and storage, require the design and manufacture of new molecules. However, identifying new molecules with desired properties is difficult and time-consuming. We aim at accelerating this process by exploiting advances in data availability, computing power, and AI. We will create generative models of molecules that operate by placing atoms in 3D space. These are more realistic and can produce better predictions than alternative approaches based on molecular graphs. Our models will guarantee that the generated molecules are synthetically accessible upfront. This will be achieved by mirroring realistic real-world processes for molecule generation where reactants are first selected, and then combined into more complex molecules via chemical reactions. Additionally, our methods will be reliable, by accounting for uncertainty in parameter estimation, and data-efficient, by jointly learning from different data sources. Our contributions will have a broad impact on materials science, leading to more effective flow batteries, solar cell components, and organic light-emitting diodes. We will also contribute to accelerate the drug discovery process, leading to more economic and effective drugs that can significantly improve the health and lifestyle of millions.

In the proposed research project I would build computational tools and analyses that help to improve the efficiency of drug discovery through enhanced analysis of protein-ligand interactions. The continuing influx of genetic information has lead to an explosion in the number of putative macromolecular disease targets including proteins. Small molecules (<900 Da) can bind to and then modulate the activity of those protein targets. Small molecules can thus be used as drugs to treat diseases and as tools to reveal linkages between potential targets and disease. Tools and drugs must bind strongly to their protein of interest (potency). Most small molecule drugs and tools do so through non-covalent interactions such as hydrogen bonds, electrostatic and hydrophobic interactions (protein-ligand interactions). The quantitative understanding of such interactions remains poor and so the automated design of small molecules with optimised interactions is currently not possible. Current state of the art in small molecule optimisation involves multiple time-consuming and expensive cycles of subjective human-driven design, chemical synthesis and experimental testing. For each potent small molecule this typically takes years and costs millions of pounds, often ending in expensive failure. A major reason for the lack of understanding of protein-ligand interactions and routes to optimising them is that high quality, systematic data has until now been the preserve of specialised industry groups (and very expensive to generate). The XChem collaboration between Diamond Light Source and the Structural Genomics Consortium (SGC) Oxford enables medium-throughput generation of such structural data for the first time. Over two years, XChem has generated thousands of high-quality 3D protein-ligand structures on more than 30 biomolecule targets. Crucially, it is now conceivable to generate systematic datasets (e.g. exploring the effect of small chemical alterations on binding and of the role of solvation) at atomistic resolution. In this fellowship, I will build such a systematic dataset on five protein targets involving 100s of novel experimentally determined protein-ligand structures. I will do so by combining novel computational tools with the breakthrough XChem facility for high-throughput protein-ligand X-ray crystallography. Specifically, I will build on the small molecule Astex Graph Database that connects experimental XChem hits with easily synthesised molecules provided by vendors and collaborators. These connections will be used to design future experiments that explore protein-ligand binding systematically but in a feasible manner. I will then combine the experimental protein-ligand interaction data and computational energetics methods with the small molecule data in this Graph Database. Finally, I will use this comprehensive and connected Graph Database to design automated routes for compound optimisation using structural data.

PhD projects will be organised in three central themes that represent the core of our programme. The themes are aligned to the strategic priorities of our NHS partners and the overall vision of the CDT: A. AI-enabled diagnostics or prognostics [lead; McKendry]. Deep learning - the subset of machine learning that is based on a network structure loosely inspired by the human brain - enables networks to learn features from clinical data automatically. This gives them the ability to model complex non-linear relationships and such AI methods have found application in clinical diagnosis using either parameters typically embedded in an electronic health record (like blood test results) or the images produced during radiographic exams or in digital pathology suites. This theme will help us create, initiate and deploy academic research projects centred on clinical use cases of direct applicability in the hospitals where our Centre is based. Example projects might include the detection of radiology abnormality; characterisation of tissues and tissue abnormality (e.g. cancer staging); or the serial monitoring of disease. B. AI-enabled operations [lead; Marshall] The proximity of our Centre to the end-users of health technology prompts a second focus, on the use of AI methods to optimise care processes and pathways. We will ensure that our projects are academically focused, but will seek to create new approaches to investigate and characterise the performance of hospitals systems and processes - such as the flow of patients through emergency departments, AI-enabled projects that might shorten time-to-treatment or cancer waits. This will be the most translationally focused theme, seeking to surface and address key use cases of the greatest academic interest. C. AI-enabled therapeutics [lead; Denaxas]. Our final theme is forward looking; the use of deep learning and other AI methods in therapeutic inference or even in a therapy itself. AI methods may be most applicable here in mental health, where deployment of 'talking therapies' is as efficacious through the internet or telephony as face-to-face; or in the development of 'avatar therapies' such as that recently proposed at UCL for hallucinations. But a wide variety of research projects are conceivable, including rehabilitation following stroke; or indeed the use of AI monitoring of radiological change as a proxy endpoint for drug trials. This theme will help us focus cutting-edge work in our Centre around such use cases and novel methodology. The UK leads in the development of artificial intelligence technologies, investing around $850M between 2012-16, the third highest of any country. This has catalysed significant UK involvement of major global technology companies such as Alphabet and Apple, the creation of new UK-based AI companies such as Benevolent AI and DeepMind (both partners in our Centre) and the emergence of a vibrant UK SME community. 80% of AI companies on the UK Top 50 list are based in London, most with 30 minutes travel from UCL. Many of the most successful AI companies now focus on the application of AI in health, but the successful application of AI technologies such as deep learning has three key unmet needs; the identification of clinically relevant use cases, the availability of large quantities of high quality labelled data from NHS patients, and the availability of scientists and software engineers with the requisite algorithmic and programming skills. All three are addressed by our CDT, its novel NHS-embedded approach to training, linked to primary and social care and with close involvement of commercial partners, structured internships and leadership and entrepreneurship. This will create an entirely new cadre of individuals with both clinical knowledge and algorithmic/programming expertise, but also catalyse the creation and discovery of new large labelled datasets and exceptional clinical use cases informed by real-world clinical care.