His research focusses on Bayesian models and machine learning for high dimensional biomedical data, including single-cell and cancer genomics.
Recently, he has led efforts to develop statistical machine learning methodology to integrate single-cell RNA and DNA sequencing data to uncover the effects of tumour clonal identity on gene expression, as well as methods to automatically delineate the tumour microenvironment from single-cell RNA-sequencing data. Such findings can improve our understanding of cancer progression and of why certain tumours are resistant to therapies, leading to relapse.