A1330
Title: Integrate co-expression networks into multivariate regression for multi-omics analysis
Authors: Shuo Chen - University of Maryland (United States) [presenting]
Hwiyoung Lee - University of Maryalnd (United States)
Abstract: Accounting for dependence among high-dimensional variables in omics data analysis is critical to obtain accurate and reliable statistical inference. Although latent, omics variables often exhibit structured correlation/co-expression patterns. However, there are few methods explicitly accounting for such structured dependence in the statistical analysis of omics data. To address this methodological gap, the aim is to propose CoReg, which integrates co-expression patterns into multivariate regression analysis. Computationally efficient algorithms are developed to implement CoReg, and they are applied to extensive simulation studies and real-world omics data analyses. It is shown in simulations that CoReg substantially improves the accuracy of statistical inference and replicability across studies. These findings suggest that CoReg is well-suited for omics data analysis with dependence adjustment, analogous to how mixed-effects models handle repeated measures in lower-dimensional settings.
