Empirical Bayes methods corrected for small numbers of tests

TL;DR

This paper introduces bias-corrected empirical Bayes estimators for small-scale biological data, improving false discovery rate estimates and highlighting the importance of estimator choice in biological feature analysis.

Contribution

It develops new bias correction methods for empirical Bayes estimators of the local false discovery rate applicable to small and medium datasets.

Findings

Corrected estimators reduce negative bias in LFDR estimation.

Simulations demonstrate improved accuracy over traditional MLEs.

Combining estimators enhances robustness in practical applications.

Abstract

Histogram-based empirical Bayes methods developed for analyzing data for large numbers of genes, SNPs, or other biological features tend to have large biases when applied to data with a smaller number of features such as genes with expression measured conventionally, proteins, and metabolites. To analyze such small-scale and medium-scale data in an empirical Bayes framework, we introduce corrections of maximum likelihood estimators (MLE) of the local false discovery rate (LFDR). In this context, the MLE estimates the LFDR, which is a posterior probability of null hypothesis truth, by estimating the prior distribution. The corrections lie in excluding each feature when estimating one or more parameters on which the prior depends. An application of the new estimators and previous estimators to protein abundance data illustrates how different estimators lead to very different conclusions about which proteins are affected by cancer. The estimators are compared using simulated data of two different numbers of features, two different detectability levels, and all possible numbers of affected features. The simulations show that some of the corrected MLEs substantially reduce a negative bias of the MLE. (The best-performing corrected MLE was derived from the minimum description length principle.) However, even the corrected MLEs have strong negative biases when the proportion of features that are unaffected is greater than 90%. Therefore, since the number of affected features is unknown in the case of real data, we recommend an optimally weighted combination of the best of the corrected MLEs with a conservative estimator that has weaker parametric assumptions.