Viral Host Identification Using Machine Learning and Viral Genome Sequences - A Thesis - Master of Science in Population Medicine

Aug 2, 2026

Viral host identification supports emergency disease preparedness and more effective response planning across human and animal health. The thesis investigates host identification using viral genome sequences combined with machine learning, surveying the evidence base and then applying classifiers to the hemagglutinin sequence of H3 influenza. A scoping review in chapter 2 charts 53 eligible publications, revealing substantial variation in methods. Chapter 3 uses multiple classifiers to assign seven hosts with high accuracy, demonstrating strong potential for machine learning within virus management frameworks.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages127

Reading Time5 h 20 min

AccessFree to download

Abstract

Acknowledgments

List of Tables

List of Figures

List of Supplementary Materials

Chapter One: Introduction, Literature Review, and Thesis Objectives

General Introduction

Objectives of Thesis

Chapter Two: Predicting Host Species Susceptibility to Viral Infections Using Genome Data and Machine Learning: A Scoping Review

Materials & Methods

Viral Host Identification Using Machine Learning and Viral Genome Sequences by Famke Alberts A Thesis presented to The University of Guelph In partial fulfilment of requirements for the degree of Master of Science in Population Medicine Guelph, Ontario, Canada © Famke Pasman Alberts, January, 2024 Abstract Viral Host Identification Using Machine Learning and Viral Genome Sequences Famke Pasman Alberts Advisor: University of Guelph, 2024 Dr. Zvonimir Poljak Virus host identification is important for emergency disease preparedness and effective response planning in both human and animal health. Host identification can be done using viral genome sequences and machine learning. This thesis seeks to address the topic of virus host identification using machine learning through identifying the current body of evidence and applying machine learning classifiers to the hemagglutinin sequence of H3 influenza. In chapter 2, a scoping review was performed. Data were charted for 53 publications that were identified tobe within the scope. There was a wide variety in methodology used within these publications. In chapter 3, different classifiers were utilized to assign seven hosts to H3 influenza viral sequences. This was achieved with high accuracy. These applications show the potential of machine learning as a method for host identification and the different circumstances in which it could be applied within a virus management framework. Acknowledgments Thank you to Dr. Zvonimir Poljak for being my advisor and giving me the opportunity to complete this thesis. As well thank you to my advisory committee Dr. Olaf Berke and Dr. Grazieli Maboni for helping me through the process of this thesis. I would also like to thank Dr. Sheila Keay for helping with the scoping review and protocol development presented in chapter 2 and Leilani Rocha for helping with data screening for the scoping review. Lastly, thank you tomy friends and family for allowing me to use them for practicing presentations and processing thoughts. Table of Contents Abstract ........................................................................................................................................... ii Acknowledgments.......................................................................................................................... iii Table of Contents ........................................................................................................................... iv List of Tables ............................................................................................................................... viii List of Figures ................................................................................................................................ ix List of Supplementary Materials..................................................................................................... x 1 Chapter One: Introduction, Literature Review, and Thesis Objectives .................................... 1 1.1 General Introduction .......................................................................................................... 1 1.1.1 Interspecies Transmission Impact ............................................................................... 2 1.1.1.1 Coronavirus ......................................................................................................... 3 1.1.1.2 Influenza virus .................................................................................................... 4 1.1.2 Interspecies Transmission Identification .................................................................... 7 1.1.2.1 Traditional Methodology .................................................................................... 8 1.1.2.2 Machine Learning ............................................................................................... 8 1.2 Objectives of Thesis ....

FAQs

Why is viral host identification important?

Viral host identification is critical for emergency disease preparedness and for planning effective responses in both human and animal health.

How does the thesis approach virus host identification?

It combines viral genome sequences with machine learning, using a scoping review to assess the evidence and classifiers applied to the hemagglutinin sequence of H3 influenza.

What were the key results of applying classifiers to H3 influenza sequences?

Chapter 3 assigns seven hosts to H3 influenza viral sequences with high accuracy, indicating strong potential for machine learning in host identification.

Aug 2, 2026

Upload by River Wang