Correlation-sharing for detection of differential gene expression

TL;DR

This paper introduces a correlation-sharing method for detecting differential gene expression, leveraging gene correlations to improve accuracy and reduce false discoveries, with potential applications in other correlated feature prediction problems.

Contribution

The paper presents a novel correlation-sharing approach that enhances differential gene expression detection by utilizing gene correlation neighborhoods, outperforming traditional t-statistic methods.

Findings

Lower false discovery rates compared to t-statistic thresholding

Effective in real and simulated gene expression data

Applicable to other correlated feature prediction problems

Abstract

We propose a method for detecting differential gene expression that exploits the correlation between genes. Our proposal averages the univariate scores of each feature with the scores in correlation neighborhoods. In a number of real and simulated examples, the new method often exhibits lower false discovery rates than simple t-statistic thresholding. We also provide some analysis of the asymptotic behavior of our proposal. The general idea of correlation-sharing can be applied to other prediction problems involving a large number of correlated features. We give an example in protein mass spectrometry.