Prediction with Dimension Reduction of Multiple Molecular Data Sources for Patient Survival

TL;DR

This paper introduces a novel approach using Joint and Individual Variation Explained (JIVE) for dimension reduction in multi-source genomic data to improve patient survival prediction, demonstrating advantages over traditional PCA.

Contribution

It applies JIVE to multi-omics data for survival prediction, introduces a method for estimating JIVE scores for new samples, and provides theoretical analysis and implementation in R.

Findings

JIVE improves interpretability and prediction accuracy over PCA.

The method effectively integrates multiple omics data sources.

The R package R.JIVE facilitates practical application of the approach.

Abstract

Predictive modeling from high-dimensional genomic data is often preceded by a dimension reduction step, such as principal components analysis (PCA). However, the application of PCA is not straightforward for multi-source data, wherein multiple sources of 'omics data measure different but related biological components. In this article we utilize recent advances in the dimension reduction of multi-source data for predictive modeling. In particular, we apply exploratory results from Joint and Individual Variation Explained (JIVE), an extension of PCA for multi-source data, for prediction of differing response types. We conduct illustrative simulations to illustrate the practical advantages and interpretability of our approach. As an application example we consider predicting survival for Glioblastoma Multiforme (GBM) patients from three data sources measuring mRNA expression, miRNA expression, and DNA methylation. We also introduce a method to estimate JIVE scores for new samples that were not used in the initial dimension reduction, and study its theoretical properties; this method is implemented in the R package R.JIVE on CRAN, in the function 'jive.predict'.