<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-21T02:44:27Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/32239" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/32239</identifier><datestamp>2026-09-24T08:00:20Z</datestamp><setSpec>com_11375_271</setSpec><setSpec>col_11375_272</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Magarvey, Nathan A.</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Spencer, Norman R.</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department" lang="en_US">Biochemistry and Biomedical Sciences</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2025-08-26T17:44:51Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2025-08-26T17:44:51Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2025</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/11375/32239</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/21958</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">Bacterial specialized metabolite (SM) scaffolds are fundamental to many important&#xd;
medicines, including antibiotics. Widespread dissemination of antimicrobial resistance&#xd;
demands the isolation of mechanistically and structurally novel therapeutics to enable&#xd;
lifesaving medical interventions. The meteoric growth of genomic sequencing data has&#xd;
uncovered millions of biosynthetic gene clusters (BGCs) encoding SMs. However, much&#xd;
of this chemical space remains unexplored due to technical limitations in BGC comparison&#xd;
and limited strategies for BGC prioritization. In this thesis, I develop deep learning&#xd;
algorithms which enable high-throughput comparison, structural rationalization,&#xd;
bioactivity prediction, and defragmentation of BGCs to enable large-scale BGC&#xd;
prioritization for SM-based drug discovery efforts. Firstly, I develop Transformer-based&#xd;
deep learning algorithms to identify and represent BGCs using highly scalable, vectorized&#xd;
representations. These algorithms drastically outperform the current state of the art and&#xd;
enable rapid comparison, grouping, and prioritization of BGCs at an immense (>1 million&#xd;
BGC) scale. Secondly, I develop computational methods to biosynthetically link SMs to&#xd;
candidate BGCs, increasing the dataset of potential SM-BGC relationships eight-fold&#xd;
relative to current datasets. This method also enables prioritization of BGCs encoding&#xd;
structural novelty and streamlines the isolation of SMs in a rationalizable fashion, leading&#xd;
to the isolation of a novel lipopeptide. Thirdly, I develop computational methods to identify&#xd;
bioactive molecular and genetic signatures present in BGCs and use these methods to&#xd;
streamline the isolation of a novel antitubercular peptide. Finally, I demonstrate a method&#xd;
enabling BGC defragmentation with scalable BGC fragment representations, facilitating the identification and comparison of discontiguous BGCs. Critically, the advances in this&#xd;
thesis leverage highly scalable vectorized representations which are capable of managing&#xd;
the extreme dataset sizes being created in the era of “multi-omics” data. Together, this&#xd;
work provides a means to leverage the immense wealth of genomic data to prioritize novel&#xd;
BGCs for streamlined, targeted SM-based drug discovery.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degreetype" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degree" lang="en_US">Doctor of Philosophy (PhD)</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="layabstract" lang="en_US">Bacteria sometimes produce unique “specialized metabolites” (SMs) with potent&#xd;
bioactivities (e.g. antibacterial, antifungal) that humans have developed into some of the&#xd;
most important medicines, antibiotics, and pesticides in use today. The instructions&#xd;
governing SM construction are found in genome regions known as “biosynthetic gene&#xd;
clusters” (BGCs). Widespread application of SM therapeutics has produced pests and&#xd;
pathogens that are resistant to these drugs, so new SMs are desperately needed. However,&#xd;
it is increasingly difficult to find new SMs without targeted approaches. In this work, I use&#xd;
deep learning approaches to identify and compare BGCs, producing significant&#xd;
improvements in accuracy, speed, and scalability relative to current methods. In addition,&#xd;
I introduce tools which predict SM-structure components and bioactivity from SM data,&#xd;
enabling the identification and prioritization of new, bioactive SMs for isolation. Using&#xd;
this approach, we isolate two novel SMs, one of which has potent antitubercular activity.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en_US">en</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Natural Products</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Genomics</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Artificial Intelligence</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Transformer</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Graphormer</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Specialized Metabolism</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Metabolism</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Knowledge Graphs</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Biosynthesis</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Bacteria</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">Deep Learning Augmented Genome Mining in the "omics" Era</dim:field>
   <dim:field mdschema="dc" element="title" qualifier="alternative" lang="en_US">DEEP LEARNING AUGMENTED GENOME MINING IN THE “OMICS” ERA</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim></metadata></record></GetRecord></OAI-PMH>