A Graph Auto-Encoder for Haplotype Assembly and Viral Quasispecies Reconstruction

TL;DR

This paper introduces a graph auto-encoder neural network framework that improves the accuracy of reconstructing haplotypes and viral quasispecies from DNA sequencing data, outperforming existing methods.

Contribution

A novel graph auto-encoder approach tailored for haplotype and viral community reconstruction, leveraging structural data properties for enhanced accuracy.

Findings

Reliable assembly of haplotypes demonstrated on synthetic and experimental data

Significant performance improvements over state-of-the-art methods

Effective in ignoring sequencing errors during reconstruction

Abstract

Reconstructing components of a genomic mixture from data obtained by means of DNA sequencing is a challenging problem encountered in a variety of applications including single individual haplotyping and studies of viral communities. High-throughput DNA sequencing platforms oversample mixture components to provide massive amounts of reads whose relative positions can be determined by mapping the reads to a known reference genome; assembly of the components, however, requires discovery of the reads' origin -- an NP-hard problem that the existing methods struggle to solve with the required level of accuracy. In this paper, we present a learning framework based on a graph auto-encoder designed to exploit structural properties of sequencing data. The algorithm is a neural network which essentially trains to ignore sequencing errors and infers the posteriori probabilities of the origin of sequencing reads. Mixture components are then reconstructed by finding consensus of the reads determined to originate from the same genomic component. Results on realistic synthetic as well as experimental data demonstrate that the proposed framework reliably assembles haplotypes and reconstructs viral communities, often significantly outperforming state-of-the-art techniques.