Institute of Communications and Connected Systems


Vaccine development through graph-based machine learning generated host-pathogen interactome

Image of graph with pathogen artistic impression superimpsoed

1 September 2019

Using graph-based machine learning to infer structure and exploitation for prediction of protein-protein interactions.ted electromagnetic environments

Funder BBSRC

Research theme logos - Sensing, Information and Data Processing
Research topics graph-based machine learning | protein-to-protein interaction | structural learning  


Protein-protein interactions (PPIs) underlie most cellular functions, where pathogens interact with hubs and bottlenecks of the host PPI network.

Modelling proteins as graphs allows us to study PPI as phenomena on irregular but structured geometry. Graph-based machine learning allows inference of structure and exploitation for PPI prediction.

This project will generate a host-pathogen interactome map using graph-based machine learning for coccidiosis, a disease caused by Eimeria with annual losses exceeding €2 billion.

Current vaccines are sub-optimal and new subunit vaccines are required. The model generated will significantly advance our ability to identify vaccine targets and utilize host-networks to optimize responses.



Publications will be updated during the project - the most recent publications will be available within the Principal Investigators listed publications.