Modelling biological systems
Developing computational and AI-driven models that describe and predict how biological systems behave, from molecules and cells to organs and ecosystems. These models enable researchers to:
- simulate processes.
- explore hypotheses.
- accelerate discovery by integrating data from diverse sources such as genomics, imaging, and clinical studies.
Data as a research asset
Transforming Southampton’s computational infrastructure, including the IRIDIS high-performance computing facility, into a shared environment for curating, preparing, and documenting high-quality datasets. These AI-ready datasets enable reproducible research, collaborative analysis, and AI model development across the life sciences.
Predictive and translational biology
Using AI to model and predict biological functions, disease mechanisms, and therapeutic outcomes. This theme focuses on translating computational predictions into actionable insights, informing experimental design, guiding drug discovery, and supporting personalised and regenerative medicine.
Responsible and explainable AI
Ensuring that AI systems in biology are transparent, interpretable, and fair. This theme examines how algorithms make decisions, mitigate bias in data, and embed ethical principles and data stewardship into all stages of model development and deployment.