AI-Driven Discovery of Virus–Host Molecular Interactions
Supervisors:
Prof David Robertson, School of Infection and Immunity
Prof Craig Macdonald, School of Computing Science
Dr Ke Yuan, School of Cancer Sciences
Prof Alfredo Castello, School of Infection and Immunity
Summary:
Viruses remain a major threat to human and animal health, causing chronic, opportunistic and recurrent diseases, including cancers. Their replication depends on intricate interactions between viral and host proteins that control how viruses enter cells, replicate, and evade our immune response. Understanding virus-host protein-protein, protein-RNA and regulatory interactions is crucial for identifying new therapeutic strategies. This PhD project will use artificial intelligence methods to predict these molecular relationships. The student will develop innovative models inspired by natural language processing to extend recent advances in transformer AI models such as AlphaFold and protein language models, already applied successfully for protein structure prediction, to predict biomolecular interactions. By treating protein and genome sequences as a biological “language,” the project will explore how AI can learn and predict the rules of virus–host interaction. Working with curated datasets of virus–host interactions, genome and structural data, the project will focus on RNA viruses of high medical and zoonotic importance. The student will collaborate with experimental groups for validation and biological insight. The successful candidate will gain cutting-edge skills in computational virology, deep learning, and virology, joining an interdisciplinary research environment at the forefront of AI-driven biology with applications in antiviral discovery and pandemic preparedness.