Integrative genetic risk prediction using nonparametric empirical Bayes classification
arXiv:1607.06976 · doi:10.1111/biom.12619
Abstract
Genetic risk prediction is an important component of individualized medicine, but prediction accuracies remain low for many complex diseases. A fundamental limitation is the sample sizes of the studies on which the prediction algorithms are trained. One way to increase the effective sample size is to integrate information from previously existing studies. However, it can be difficult to find existing data that examine the target disease of interest, especially if that disease is rare or poorly studied. Furthermore, individual-level genotype data from these auxiliary studies are typically difficult to obtain. This paper proposes a new approach to integrative genetic risk prediction of complex diseases with binary phenotypes. It accommodates possible heterogeneity in the genetic etiologies of the target and auxiliary diseases using a tuning parameter-free nonparametric empirical Bayes procedure, and can be trained using only auxiliary summary statistics. Simulation studies show that the proposed method can provide superior predictive accuracy relative to non-integrative as well as integrative classifiers. The method is applied to a recent study of pediatric autoimmune diseases, where it substantially reduces prediction error for certain target/auxiliary disease combinations. The proposed method is implemented in the R package ssa.
References in corpus (7)
- Classifier Technology and the Illusion of Progress
- High-dimensional classification using features annealed independence rules
- General maximum likelihood empirical Bayes estimation of normal means
- Nonparametric empirical Bayes and compound decision approaches to estimation of a high-dimensional vector of normal means
- Optimal classification in sparse Gaussian graphic model
- Nonparametric empirical Bayes and maximum likelihood estimation for high-dimensional data analysis
- Approximate nonparametric maximum likelihood inference for mixture models via convex optimization