Nonparametric homogeneity tests and multiple change-point estimation for analyzing large Hi-C data matrices

TL;DR

This paper introduces a nonparametric method for detecting change-points in large symmetric matrices, specifically applied to Hi-C data, to identify shifts in chromosomal conformation.

Contribution

It develops a novel nonparametric approach for change-point detection in matrices, extending homogeneity tests to multiple groups and applying it to biological Hi-C data.

Findings

Theoretical validation of the proposed test statistics.

Numerical experiments demonstrating effectiveness.

Application to Hi-C data revealing biological insights.

Abstract

We propose a novel nonparametric approach for estimating the location of block boundaries (change-points) of non-overlapping blocks in a random symmetric matrix which consists of random variables having their distribution changing from one block to the other. Our method is based on a nonparametric two-sample homogeneity test for matrices that we extend to the more general case of several groups. We first provide some theoretical results for the two associated test statistics and we explain how to derive change-point location estimators. Then, some numerical experiments are given in order to support our claims. Finally, our approach is applied to Hi-C data which are used in molecular biology for better understanding the influence of the chromosomal conformation on the cells functioning.