We use systems-biology-based approaches, applying computational methods to multi-omic data with the goal of generating hypotheses of the underlying processes involved in disease activity. We test hypotheses with strong evidence in measured data in a laboratory for translation into actionable diagnostics and therapeutics.
We develop innovative computational, machine learning, deep learning, and statistical methods aimed at achieving actionable research outcomes in health and disease using high-dimensional omics data. The goals for these techniques are to provide approaches to find biological patterns in the zoomed-in personalized level and the zoomed-out population-level using omics data.