Identifying Hosts of Families of Viruses: A Machine Learning Approach

TL;DR

This paper introduces a machine learning method that predicts viral hosts from protein sequences, offering a potentially more accurate alternative to phylogenetics, especially when data is limited or species are distant.

Contribution

It develops a sparse, tree-structured model based on decision rules from subsequences to improve viral host prediction from protein data.

Findings

Predictive motifs show strong host-specificity.

Motifs occur in conserved viral proteome regions.

Method outperforms traditional phylogenetic approaches.

Abstract

Identifying viral pathogens and characterizing their transmission is essential to developing effective public health measures in response to a pandemic. Phylogenetics, though currently the most popular tool used to characterize the likely host of a virus, can be ambiguous when studying species very distant to known species and when there is very little reliable sequence information available in the early stages of the pandemic. Motivated by an existing framework for representing biological sequence information, we learn sparse, tree-structured models, built from decision rules based on subsequences, to predict viral hosts from protein sequence data using popular discriminative machine learning tools. Furthermore, the predictive motifs robustly selected by the learning algorithm are found to show strong host-specificity and occur in highly conserved regions of the viral proteome.