Nonparametric Bayes multiresolution testing for high-dimensional rare events

TL;DR

This paper introduces a flexible nonparametric Bayesian method for detecting spatial clusters of rare variants in high-dimensional data, with applications in genomics and disease subtype analysis.

Contribution

It develops multiresolution nonparametric Bayes tests specifically designed for high-dimensional rare event detection, with theoretical guarantees and superior small sample performance.

Findings

Effective detection of spatial clusters of rare variants.

Theoretical proof of weak consistency of the method.

Successful application to genomic data identifying disease-related variants.

Abstract

In a variety of application areas, there is interest in assessing evidence of differences in the intensity of event realizations between groups. For example, in cancer genomic studies collecting data on rare variants, the focus is on assessing whether and how the variant profile changes with the disease subtype. Motivated by this application, we develop multiresolution nonparametric Bayes tests for differential mutation rates across groups. The multiresolution approach yields fast and accurate detection of spatial clusters of rare variants, and our nonparametric Bayes framework provides great flexibility for modeling the intensities of rare variants. Some theoretical properties are also assessed, including weak consistency of our Dirichlet Process-Poisson-Gamma mixture over multiple resolutions. Simulation studies illustrate excellent small sample properties relative to competitors, and we apply the method to detect rare variants related to common variable immunodeficiency from whole exome sequencing data on 215 patients and over 60,027 control subjects.