Prediction of host-pathogen gene expression from dual RNA-seq data during a bacterial infection

Barani Lonbani, Nima (2024) Prediction of host-pathogen gene expression from dual RNA-seq data during a bacterial infection. Masters thesis, Memorial University of Newfoundland.

[English] PDF - Accepted Version Available under License - The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission. Download (1MB)

Abstract

Understanding the mechanisms by which bacteria cause disease, such as apoptosis and inflammatory signals, necessitates a comprehensive knowledge of the genes expressed during infection by both the host and the pathogen. Dual RNA-seq technology enables simultaneous detection of transcripts of the pathogen and host during an infection. In this study, we utilized machine learning to predict the expression levels of genes involved in bacterial infection from their RNA sequence using dual RNA-seq data to obtain gene expression levels. We developed two predictive models: one specifically tailored to the host and the other to the pathogen. Results from these models are promising in terms of macro-average F1-score and macro-average Area Under Receiver Operating Characteristic Curve (AUROC) and demonstrate that machine learning can be applied to dual RNA-seq data to predict gene expression levels during bacterial infection, opening new prospects for future research to build upon these methods and insights.

Actions (login required)

View Item