Overview
Can AI design molecules that are both truly novel and actually makeable? This PhD will combine 3D generative modelling, structural informatics, and chemical insight to tackle a central challenge in modern drug discovery, training researchers at the interface of AI, synthesis, and automation.
About this opportunity
The molecule design process is often hampered by high costs and lengthy development cycles. Recent advances in 3D-aware generative models offer a promising route to accelerate novel molecule discovery, yet these approaches frequently produce compounds that are not practically synthesisable. This project will systematically investigate how 3D-molecular novelty impacts synthesisability and will develop methods to mitigate this loss. Building on state-of-the-art 3D architectures, the research will quantify the synthesisability gap by integrating conditioning constraints from high-quality informatics sources such as the Cambridge Structural Database. Multiple levels of 3D complexity, e.g., the incorporation of interaction field constraints from resources like Isostar, Superstar, and hotspot potentials—will be developed to understand their impact on synthesisability. Validation will be achieved through case studies targeting well-characterised systems (e.g., hERG and neglected tropical disease targets), ensuring that the outputs have direct relevance to molecule discovery pipelines. The project is positioned to bridge the gap between digital design innovation and practical synthesis, addressing a critical bottleneck in AI-driven materials chemistry.
This project will be supervised by Dr Anthony Bradley (Department of Chemistry), Dr Gabriella Pizzuto (Department of Computer Science and Informatics), Dr John Ward (Department of Chemistry), Dr Ian Wall (GlaxoSmithKline) and Dr Bojana Popovic (Cambridge Crystallographic Data Centre).
The team is world-leading in this topic and provides a cross- and inter-disciplinary environment across Chemistry Automation, Drug Discovery, AI, and Robotics. Anthony Bradley, is an ECA on a joint appointment between Chemistry and Computer Science, and his research is in experimental and computational automation in molecule development. He co-developed the first 3D-aware generative deep models and has designed molecules in clinical studies. Gabriella Pizzuto is an ECA on a joint appointment between Computer Science and Chemistry, holds a RAEng Research Fellowship, is Co-I and ECR committee co-chair on AIchemy and RAL at the Royce Institute. Her research at the intersection of robot learning and control have been outstanding paper finalists at flagship robotics conferences. Ian Wall, as Head of Computer Aided Molecule Design at GSK, offers decades of expertise in designing molecules using computation. Bojana Popovic contributes deep knowledge in 3D molecule design and function as Discovery Sciences Lead at CCDC. Together, their collective strengths and proven track records in both methodological innovation and practical application provide an ideal mentoring environment.
This project is expected to start in October 2026 and is offered under the EPSRC Centre for Doctoral Training in Digital and Automated Materials Chemistry based in the Materials Innovation Factory at the University of Liverpool, the largest industry-academia colocation in UK physical science. The successful candidate will benefit from training in robotic, digital, chemical and physical thinking, which they will apply in their domain-specific research in materials design, discovery and processing. PhD training has been developed with 35 industrial partners and is designed to generate flexible, employable, enterprising researchers who can communicate across domains.
Further reading
Imrie, F., Bradley, A.R., van der Schaar, M. and Deane, C.M. Deep Generative Models for 3D Linker Design. Journal of Chemical Information and Modeling 60(4), 1983–1995 (2020). A foundational paper in 3D-aware generative molecular design and highly relevant background for this project’s focus on geometry-informed generation. Publication URL: https://pubs.acs.org/doi/10.1021/acs.jcim.9b01120
Groom, C.R., Bruno, I.J., Lightfoot, M.P. and Ward, S.C. The Cambridge Structural Database. Acta Crystallographica Section B 72, 171–179 (2016). The core reference for the Cambridge Structural Database, which underpins the structural informatics and constraint-based aspects of the proposed work. Publication URL: https://journals.iucr.org/b/issues/2016/02/00/bm5086/
Radoux, C.J., Olsson, T.S.G., Pitt, W.R., Groom, C.R. and Blundell, T.L. Identifying Interactions that Determine Fragment Binding at Protein Hotspots. Journal of Medicinal Chemistry 59(9), 4314–4325 (2016). An important reference for hotspot-based interaction modelling and the use of 3D interaction preferences in structure-guided molecule design. Publication URL: https://pubs.acs.org/doi/10.1021/acs.jmedchem.5b01980