My research focus is at the interface of Statistics and Computational Biology, addressing high-dimensional and missing data problems in genomics, especially relating to gene regulation. I have been involved in the development of several statistical methods for the discovery of transcription factor binding sites from DNA sequence in a variety of genomes, ranging from bacteria to human. I am also interested in the development of Bayesian methodologies for the elucidation of gene regulatory networks in eukaryotic genomes combining multiple data types, and feature discovery in high throughput genomic data from genome tiling arrays. More recently I have been involved in developing Bayesian methods for variable selection in high-dimensional data, in particular relating to the problem of discovery of SNP associations in genome-wide association studies, in which I collaborate with researchers at the Framingham Heart Study in Boston, U.S.A. My other research interests include Bayesian model selection, model-based classification and clustering techniques and statistical inference in hidden Markov and other latent class models.

EPSRC-DST workshop on "Solving Big Data Challenges from Modern Science through Statistical Modelling" on 5-8 May, 2015 at ICMS, Edinburgh

Tenth Meeting of New Researchers in Statistics and Probability, Salt Lake City, UT, 2007