Michigan State University Assistant Professor
A significant proportion of modern biology and biomedicine is gaining the character of data science. This transition is happening due to rapidly accumulating massive data and the biomedical community’s increasing need tograpple with computational data-driven hypotheses and predictions. In this talk, I will present some of our research in this domain, harnessing the power of machine learning to uncover the genetic and mechanistic basis of human health and disease from large heterogeneous data collections. I will describe our efforts to predict missing metadata, build molecular interaction networks, prioritize genes related to human diseases. I will also talk about our efforts towards teaching biologists the computational and analytical toolkit to critically think about and leverage data.Specifically, I will discuss a ‘coding-first’ and ‘caution-right-after’ approach we are taking to teach statistical data analysis at all levels including undergraduate and graduate students, faculty, high-school teachers, and the general public.