Modelling genetic variation through tissue-specific post-translational modifications using population-scale AI

Protein post-translational modifications (PTMs) are key regulatory mechanisms influencing protein stability, interactions, localisation, and signalling. Emerging evidence shows that PTMs contribute significantly to complex disease biology, shaping metabolic, cognitive, and mental-health outcomes in the general population. Meanwhile, coding genetic variants are known to alter protein structure/function but their downstream impact on PTM patterns remains poorly understood, particularly in clinically important proteins such as drug targeted ones.

The student will then examine how predicted PTMs relate to continuous traits such as BMI, HbA1c, cognitive scores and mental-health outcomes (e.g., depression, anxiety), using statistical genetics, ML prediction models (elastic net, deep learning), and mediation frameworks to quantify indirect PTM-mediated effects.

This multidisciplinary project integrates computational biology, structural modelling, population genomics, and AI. It will provide new mechanistic insights into how coding variation and PTMs influence health and may inform the future of personalised therapeutics for metabolic and mental-health disorders.

The student will be trained to integrate structural, sequence, physicochemical, and motif-based descriptors with machine learning–based PTM prediction tools, enabling personalised prediction of variant-induced PTM gain/loss. 

You will need to meet the minimum entry requirements for our PhD programme.

Open to any UK or international candidates. Up to 30% of our UKRI funded studentships can be awarded to candidates paying international rate fees. Find out more about eligibility.