Predicting Zoonotic Risk of Influenza A Viruses from Host Tropism Protein Signature Using Random Forest.

Christine Eng,Joo Tong,Tin Tan

doi:10.3390/ijms18061135

Abstract

Influenza A viruses remain a significant health problem, especially when a novel subtype emerges from the avian population to cause severe outbreaks in humans. Zoonotic viruses arise from the animal population as a result of mutations and reassortments, giving rise to novel strains with the capability to evade the host species barrier and cause human infections. Despite progress in understanding interspecies transmission of influenza viruses, we are no closer to predicting zoonotic strains that can lead to an outbreak. We have previously discovered distinct host tropism protein signatures of avian, human and zoonotic influenza strains obtained from host tropism predictions on individual protein sequences. Here, we apply machine learning approaches on the signatures to build a computational model capable of predicting zoonotic strains. The zoonotic strain prediction model can classify avian, human or zoonotic strains with high accuracy, as well as providing an estimated zoonotic risk. This would therefore allow us to quickly determine if an influenza virus strain has the potential to be zoonotic using only protein sequences. The swift identification of potential zoonotic strains in the animal population using the zoonotic strain prediction model could provide us with an early indication of an imminent influenza outbreak.

Highlights

Influenza A viruses primarily reside in avian species, yet in recent years, there have been an increasing number of documented zoonotic infections in humans
Each host tropism protein prediction is associated with a probability estimate which represents the confidence of the prediction by each individual protein prediction model, loosely describing how “avian-like” or “human-like” the proteins are, as illustrated by the intensity of the color (Figure 1). This allows us to inspect with greater detail the host tropism protein signature of an influenza virus strain, which could provide a clue as to how much it has deviated from a typical strain
Using host tropism protein signatures of influenza viruses which are predicted from protein sequences, the zoonotic strain prediction model can accurately distinguish between typical avian strains found in avian species, seasonal influenza circulating in humans, and zoonotic strains originating from avian species that have caused human infections

Summary

Introduction

Influenza A viruses primarily reside in avian species, yet in recent years, there have been an increasing number of documented zoonotic infections in humans. While there was no direct evidence of human transmissibility or stable adaptation in humans, many of these zoonotic infections of H5N1 and H7N9 subtypes, cause severe illnesses, with the mortality rate for H5N1 estimated to be as high as 60% [13]. These zoonotic strains originated from avian species, having acquired sufficient mutations or new segments from reassortment to overcome host range restriction and successfully cause infections in humans

Objectives

Methods

Results

Discussion

Conclusion