Feature learning of virus genome evolution with the nucleotide skip-gram neural network

TL;DR

This paper introduces a neural network-based method inspired by NLP techniques to analyze virus genome evolution, revealing mutation patterns and interactions from time-series genomic data.

Contribution

It presents a novel application of the skip-gram neural network to encode allele relationships and detect mutation interactions in viral genomes.

Findings

Identified mutations linked to disinfectant adaptation.

Clustered allele vectors reveal mutation groups.

Model accounts for recombination rates in genome interactions.

Abstract

Recent studies reveal even the smallest genomes such as viruses evolve through complex and stochastic processes, and the assumption of independent alleles is not valid in most applications. Advances in sequencing technologies produce multiple time-point whole-genome data, which enable potential interactions between these alleles to be investigated empirically. To investigate these interactions, we represent alleles as distributed vectors that encode for relationships with other alleles in the course of evolution, and apply artificial neural networks to time-sampled whole-genome datasets for feature learning. We build this platform using methods and algorithms derived from Natural Language Processing (NLP), and we denote it as the nucleotide skip-gram neural network. We learn distributed vectors of alleles using the changes in allele frequency of echovirus 11 in the presence or absence of the disinfectant from the experimental evolution data. Results from the training using a new open-source software TensorFlow show that the learned distributed vectors can be clustered using Principal Component Analysis and Hierarchical Clustering to reveal a list of non-synonymous mutations that arise on the structural protein VP1 in connection to the candidate mutation for disinfectant adaptation. Furthermore, this method can account for recombination rates by setting the extent of interactions as a biological hyper-parameter, and the results show the most realistic scenario of mid-range interactions across the genome is most consistent with the previous studies.