A Pairwise Imputation Strategy for Retaining Predictive Features When Combining Multiple Datasets

Abstract

In the training of predictive models using high-dimensional genomic data, multiple studies worth of data are often combined to increase sample size and improve generalizability. A drawback of this approach is that there may be different sets of features measured in each study due to variations in expression measurement platform or technology. It is often common practice to work only with the intersection of features measured in common across all studies, which results in the blind discarding of potentially useful feature information that is measured only in individual or subsets of all studies. We characterize the loss in predictive performance incurred by using only the intersection of feature information available across all studies when training predictors using gene expression data from microarray and sequencing datasets. We study the properties of linear and polynomial regression for imputing discarded features and demonstrate improvements in the external performance of predictors through simulation and in gene expression data collected on breast cancer patients. We propose and evaluate a pairwise imputation strategy that imputes cross-study missing features in each pair of studies and averages imputed features across pairs. Finally, we provide insights on which subsets of intersected and study-specific features should be used so that missing-feature imputation best promotes cross-study replicability. All code with directions to reproduce results in this paper is available at https://github.com/YujieWuu/Pairwise_imputation