Professor of Statistics
The research programme of Mark Girolami and his group stands at the interface between Statistical Science, Computer Science and the Life Sciences. He has pioneered the adoption of Bayesian statistical inference methods in the modelling of cellular signalling which has provided cellular biologists with the tools to rationally and systematically reason about plausible pathway structures and mechanisms. Other innovations in collaboration with analytical chemists include the development of statistical methodology to detect dye labelled DNA oligo's in multiplexed Raman spectra as an analytic technique for in cellular protein detection.
Girolami, M., Calderhead, B. Riemann Manifold Langevin and Hamiltonian Monte Carlo Methods (2011). Journal of the Royal Statistical Society – Series B (with discussion), 73(2), 123 - 214.
Zhong, M., Girolami, M., Faulds, K., Graham, D. Bayesian Methods to Detect Dye Labelled DNA Oligonucelotides in Multiplexed Raman Spectra (2011). Journal of the Royal Statistical Society – Series C, 60(2), 187 - 206.
Xu, T.R, Vyshemirsky, V., Gormand, A., Girolami, M., Baillie, G.S., Ketley, D., Milligan, G., Dunlop, A.J., Houslay, M.D., and Kolch. W. Inferring Signalling Pathway Topologies from Single Species Multiple Perturbation Measurements (2010). Science Signaling, Vol.3, Issue 113, p. ra20.
Hopcroft, L., McBride, M., Harris, K., McClure, J., Dominiczak, A., Girolami, M. Predictive Response-Relevant Clustering Provides Insights into Disease Processes (2010). Nucleic Acids Research, 38(20), 6831 - 6840.