The inference of network structure is a key approach we use in applications spanning multiple fields, from molecular biology to health and economics.

We have developed novel methods and technical for network learning, including Bayesian approaches, MCMC and penalized likelihood methods.

In cancer protein signalling networks the approaches we have developed are breaking new ground in the field and have implications for other diseases as well as signalling biology more generally.

Another study addresses plant pathology, specifically the response of the model organism A. Thaliana to infection by the fungal pathogen B. cinerea, using high-dimensional biochemical data.

An intriguing question in public health is whether relationships, as captured in a social network, can influence health status (over and above the contribution of other factors): we are developing statistical network models to analyse a suitable database on adolescent health.

Venturing into Social Economics, we have used advanced inference approaches to probe the relationship between subjective well-being and risk-taking.

Application areas:

• cancer
• biology
• biological networks
• empirical economics
  

People: