Open Access. Powered by Scholars. Published by Universities.®

Life Sciences Commons

Open Access. Powered by Scholars. Published by Universities.®

Theses/Dissertations

2021

Bioinformatics

Western University

Articles 1 - 2 of 2

Full-Text Articles in Life Sciences

Response Of The Soil Bacterial Community, Resistome, And Mobilome To A Decade Of Macrolide Antibiotic Contamination, Liam Paul Brown Sep 2021

Response Of The Soil Bacterial Community, Resistome, And Mobilome To A Decade Of Macrolide Antibiotic Contamination, Liam Paul Brown

Electronic Thesis and Dissertation Repository

Biosolids (treated sewage sludge) are used as agricultural fertilizer but are frequently contaminated with macrolide antibiotics, to which resistance is rising among historically susceptible bacteria. To determine if the land-application of macrolides carried in biosolids could promote antibiotic resistance in soil bacteria, soil plots were exposed annually to environmentally realistic or high doses of macrolides for ten years. I sequenced the bacterial 16S ribosomal DNA, metagenomic DNA, and integron gene cassettes within the treated and antibiotic-free soil to compare the compositions and diversities of the bacterial communities, antibiotic resistance genes, and mobile genetic elements. I determined that the high dose …


Visualization And Interpretation Of Protein Interactions, Dipanjan Chatterjee Apr 2021

Visualization And Interpretation Of Protein Interactions, Dipanjan Chatterjee

Electronic Thesis and Dissertation Repository

Visualization and interpretation of deep learning models' prediction is a very important area of research in machine learning nowadays. Researchers are not only focused on generating a model with good performance, but also they want to trust the model. Our aim in this thesis is to adapt existing interpretation methods to a protein-protein binding site prediction problem to visualize and understand the model's prediction and learning pattern.

We present three deep learning-based interpretation methods: sensitivity analysis, saliency map and integrated gradients to analyze the amino acid residues which create positive and negative relevance to the deep learning models' prediction. As …