The state-of-the-art in computer-aided drug design is physics-based modelling, in which candidate drugs and their targets are simulated at the atomistic level. The most widely-used tool for this are molecular mechanics force fields, such as those developed by the Open Force Field Initiative[https://doi.org/10.1021/acs.jpcb.4c01558], but they lack accuracy for predictive modelling. Transferable machine learning potentials, like MACE-OFF[https://doi.org/10.1021/jacs.4c07099], effectively achieve quantum mechanical accuracy for small organic molecule energetics, but are too slow for routine use in medicinal chemistry.
This collaborative, industry-funded, computational project will i) use state-of-the-art machine learning potentials to rapidly generate new condensed phase training data, ii) develop automated workflows to train molecular mechanics force fields against these accurate data sources, and iii) validate force field accuracy with industry partners for computer-aided drug design applications.
The successful applicant will work closely with project partners at SandboxAQ. The supervisory team will provide highly sought-after training in the fields of computational molecular modeling, medicinal chemistry, and machine learning. As such, this project is ideal for a candidate with ambitions towards a career in the pharmaceutical industry or academic computational chemistry.
You can find further details about the supervisory team and collaborators at the following links:
https://blogs.ncl.ac.uk/danielcole/
https://www.ncl.ac.uk/nes/people/profile/ioanmagdau.html
https://www.sandboxaq.com
Deadline: 18 January 2026
For more information and to apply visit https://www.ncl.ac.uk/postgraduate/fees-funding/search-funding/?code=DLA2611
