Multiple two-sample testing under arbitrary covariance dependency with an application in imaging mass spectrometry

TL;DR

This paper develops a new statistical method for large-scale two-sample testing that accounts for complex dependencies among tests, specifically applied to imaging mass spectrometry data in cancer research.

Contribution

It introduces a marginal model-based inference procedure that estimates the correlation structure among test statistics for improved false discovery control.

Findings

Method effectively controls false discovery proportion in dependent data

Application to MALDI IMS data reveals significant molecular associations

Provides a practical workflow for high-dimensional dependent hypothesis testing

Abstract

Large-scale hypothesis testing has become a ubiquitous problem in high-dimensional statistical inference, with broad applications in various scienfitic disciplines. One relevant application is constituted by imaging mass spectrometry (IMS) association studies, where a large number of tests are performed simultaneously in order to identify molecular masses that are associated with a particular phenotype, e. g., a cancer subtype. Mass spectra obtained from Matrix-assisted laser desorption/ionization (MALDI) experiments are dependent, when considered as statistical quantities. False discovery proportion (FDP) control under arbitrary dependency structure among test statistics is an active topic in modern multiple testing research. In this context, we are concerned with the evaluation of associations between the binary outcome variable (describing the phenotype) and multiple predictors derived from MALDI measurements. We propose an inference procedure in which the correlation matrix of the test statistics is utilized. The approach is based on multiple marginal models (MMM). Specifically, we fit a marginal logistic regression model for each predictor individually. Asymptotic joint normality of the stacked vector of the marginal regression coefficients is established under standard regularity assumptions, and their (limiting) correlation matrix is estimated. The proposed method extracts common factors from the resulting empirical correlation matrix. Finally, we estimate the realized FDP of a thresholding procedure for the marginal $p$-values. We demonstrate a practical application of the proposed workflow to MALDI IMS data in an oncological context.