Null-free False Discovery Rate Control Using Decoy Permutations

TL;DR

This paper introduces a null distribution-free method for controlling the false discovery rate in multiple hypothesis testing, using decoy permutations to improve stability and power without relying on traditional null distribution assumptions.

Contribution

The paper proposes a novel target-decoy procedure that controls FDR without requiring knowledge of the null distribution, applicable under independence of test statistics.

Findings

The method effectively controls FDR in simulations.

It demonstrates higher stability and power than existing approaches.

Validated on real dataset with promising results.

Abstract

The traditional approaches to false discovery rate (FDR) control in multiple hypothesis testing are usually based on the null distribution of a test statistic. However, all types of null distributions, including the theoretical, permutation-based and empirical ones, have some inherent drawbacks. For example, the theoretical null might fail because of improper assumptions on the sample distribution. Here, we propose a null distribution-free approach to FDR control for multiple hypothesis testing. This approach, named target-decoy procedure, simply builds on the ordering of tests by some statistic or score, the null distribution of which is not required to be known. Competitive decoy tests are constructed from permutations of original samples and are used to estimate the false target discoveries. We prove that this approach controls the FDR when the statistics are independent between different tests. Simulation demonstrates that it is more stable and powerful than two existing popular approaches. Evaluation is also made on a real dataset.