Abstract:

In cancer studies with high-throughput “-omics” measurements, the analysis of a single dataset often suffers from a lack of power. Integrative analysis of multiple independent datasets/multidimensional studies provides an effective way of pooling information and outperforms single-dataset and several alternative multi-datasets methods. In this talk, we consider an application of such joint learning in studying precision matrices under the Gaussian graphical model. The Gaussian graphical model is a popular tool for inferring the relationships among random variables, where the precision matrix has a natural interpretation of conditional independence. Under quite a few important scenarios, it is desirable to conduct the joint estimation of multiple precision matrices. We develop a regularization method for the joint estimation of multiple precision matrices. It effectively promotes the sign consistency of group parameters and hence can lead to more interpretable results, while still allowing for conflicting signs to achieve full flexibility.