My research interests focus on statistical applications of genomics and bioinformatics. We mainly work on data mining of high-throughput genomic, transcriptomic and proteomic data (such as microarray, next-generation sequencing and mass spectrometry data) and develop methods in study design, candidate marker detection, supervised machine learning (classification), unsupervised machine learning (clustering), high-dimensional feature selection and other topics driven by biological problems. Related research also include statistical modelling, statistical computing, graphical visualization of data, omics data integration and neuroimaging. Collaboration with biology labs plays an important role where most of our projects and methodological ideas come from.