PhD Studentship in Generative AI for Structure-Based De Novo Drug Design

About the Project

De novo drug design seeks to generate novel drug-like molecules computationally, rather than identifying candidates from pre-existing chemical libraries. Recent advances in Generative Artificial Intelligence (AI) have enabled the automated design of molecules optimised for user-defined objectives such as biological activity, selectivity, toxicity, novelty and synthetic accessibility.

This PhD project will investigate how structure-based machine-learning scoring functions can enhance Generative AI methods for de novo drug design. Particular emphasis will be placed on integrating structural information into molecular generation workflows and rigorously benchmarking the resulting methods against existing virtual screening baselines.

Selection Criteria

Essential: University degree(s) awarded in an area directly relevant to the project. Courses in the application of machine learning algorithms to scientific problems. Excellent grades in first and/or master’s degrees. Skilled in implementing Python or R code for scientific data analysis. English language proficiency requirements.

Desirable: Research projects applying generative AI and discriminative AI to solve real-world biomedical problems. Experience with open-source chemical informatics toolkits (e.g. RDKit). Experience with machine learning platforms. Exposure to structural biology databases. Experience with medicinal chemistry databases.

What We Offer

The studentship covers living expenses at an enhanced tax-free rate of £23,805 per year. PhD tuition fees of £31,100 per year. Funding is for three years, with the possibility of extension to a fourth year.