Large-Scale Simultaneous Testing of Cross-Covariance Matrix with Applications to PheWAS
Tianxi Cai, Tony Cai, Katherine Liao and Weidong Liu
-
Abstract:
The electronic medical record (EMR) system linked with biorepository has led to the avail- ability of detailed patient level phenotypic data along with biological and genetic marker information. Such type of data expansion enables us to perform phenome-wide association studies (PheWAS) to examine the relationship between a set of genomic markers and a wide range of phenotypic outcomes by integrating multiple sources of information. Motivated by such PheWAS applications, we consider simultaneous testing of columns of high-dimensional cross-covariance matrices and develop a multiple testing procedure with theoretical guarantees.
It is shown that the proposed testing procedure maintains a desired false discovery rate (FDR) and false discovery proportion (FDP) under mild regularity conditions. We also provide results on the magnitudes of the signals that can be detected with high power. Simulation studies demonstrate that the proposed methods can be substantially more powerful than existing FDR controlling procedures in the presence of correlation. We applied the proposed procedures to a PheWAS of two auto-immune genetic markers using a cohort of Rheumatoid Arthritis (RA) constructed from the EMR of the Partners Healthcare.
- Paper:
pdf file.
- Software: A Matlab implementation of the multiple testing procedure.