Variational inference for coupled Hidden Markov Models applied to the joint detection of copy number variations

TL;DR

This paper introduces a variational inference method for coupled Hidden Markov Models to efficiently detect copy number variations in genomics, especially when handling multiple correlated data series.

Contribution

It develops a novel variational EM algorithm for coupled HMMs, enabling scalable inference in complex genomic CNV detection tasks.

Findings

The proposed method performs well in simulation studies.

Application to plant genomes demonstrates practical utility.

Efficient inference in large-scale, correlated data series.

Abstract

Hidden Markov models provide a natural statistical framework for the detection of the copy number variations (CNV) in genomics. In this paper, we consider a Hidden Markov Model involving several correlated hidden processes at the same time. When dealing with a large number of series, maximum likelihood inference (performed classically using the EM algorithm) becomes intractable. We thus propose an approximate inference algorithm based on a variational approach (VEM). A simulation study is performed to assess the performance of the proposed method and an application to the detection of structural variations in plant genomes is presented.