<?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>2026-11-21T05:05:32Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/18471" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/18471</identifier><datestamp>2026-09-24T03:33:34Z</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">Smyth, W. F.</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Shafqat, Raazia</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department" lang="en_US">Computer Science</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2015-10-23T14:05:05Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2015-10-23T14:05:05Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2015-11</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/11375/18471</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/14166</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">Over the past several years, new DNA sequencing technologies have led to a great in-&#xd;
crease in the quantity of biological sequence data that can be generated. Typically there&#xd;
may be millions or even billions of short reads sequences of a few hundred base pairs&#xd;
that are to some degree redundant: the data fall naturally into clusters of sequences&#xd;
that are highly similar to each other. In order to reduce the time required for analysis&#xd;
of the data, it therefore becomes of interest to compute representatives of these clusters,&#xd;
based on some definition of similarity.&#xd;
In this thesis we examine two clustering software packages, USEARCH and DNACLUST,&#xd;
that seek to perform this clustering task efficiently. We provide an overview of the techniques used by these two packages; we compare and evaluate them both from a methodological and experimental perspective, and draw conclusions about their effectiveness and utility.</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">Master of Science (MSc)</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">Short reads</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Clusters</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Similarity</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">ANALYSIS AND COMPARISON OF USEARCH AND DNACLUST SOFTWARE PACKAGES</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>