Abstract

The human microbiome is a main contributor for the health and welfare of the human body. It is affected by many factors like diet and hygiene. These factors differ between different populations. Testing the population-microbiome differences using healthy samples from different countries is the first objective of this study. This data was then used in training and testing machine learning models (Random Forest and L2-logistic Regression Classifiers) for the prediction of the geographical location based on the microbiome data. Random Forest Classifier had the highest accuracy. Feature importance analysis showed that the data for Proteobacteria, Actinobacteria, and Bacteroidetes improved the Random Forest Classifier’s performance. The second objective of the study was to compare the gut microbiome from healthy individuals and Coronavirus disease of 2019 (COVID-19) patients from China. COVID-19 caused lots of deaths besides an economic crisis. According to the World Health Organization (WHO), it has caused more than 227 million cases and more than 4.5 million deaths till September 16th, 2021. It was caused by severe acute respiratory syndrome coronavirus - 2 (SARS-CoV-2) which can enter the cells through the receptor for Angiotensin-converting enzyme 2 (ACE2). Proteobacteria, Actinobacteria, and Bacteroidetes had the most distinguished patterns between healthy and patient samples. Proteobacteria contain many human pathogens. Actinobacteria can cause many respiratory disorders. Bacteroidetes can regulate the expression of ACE2 receptors in mice. In conclusion, there was a correlation between being infected with SARS-CoV-2 and modifications in the gut microbiome.

School

School of Sciences and Engineering

Department

Biotechnology Program

Degree Name

MS in Biotechnology

Graduation Date

Winter 1-31-2022

Submission Date

1-26-2022

First Advisor

Asma Amleh

Second Advisor

Ahmed Moustafa

Committee Member 1

Walid Fouad

Committee Member 2

Ramy Aziz

Committee Member 3

Ahmed Abdellatif

Extent

77 p.

Document Type

Master's Thesis

Institutional Review Board (IRB) Approval

Not necessary for this item

Share

COinS