<?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>2026-11-22T14:59:03Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/4412" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/4412</identifier><datestamp>2017-03-21T17:30:13Z</datestamp><setSpec>com_10012_9924</setSpec><setSpec>com_10012_1</setSpec><setSpec>col_10012_9930</setSpec><setSpec>col_10012_6</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:doc="http://www.lyncode.com/xoai" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="author" authority="b35a2a6e-e706-4f35-9c7b-2e76178cfbd9" confidence="600">Wong, William Wai Lun</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2009-05-14T15:55:35Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2009-05-14T15:55:35Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2009-05-14T15:55:35Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2009-05-04</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/10012/4412</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en">A drug is typically a small molecule that interacts with the binding site of some&#xd;
target protein. Drug design involves the optimization of this interaction so that the&#xd;
drug effectively binds with the target protein while not binding with other proteins&#xd;
(an event that could produce dangerous side effects). Computational drug design&#xd;
involves the geometric modeling of drug molecules, with the goal of generating&#xd;
similar molecules that will be more effective drug candidates. It is necessary that&#xd;
algorithms incorporate strategies to measure molecular similarity by comparing&#xd;
molecular descriptors that may involve dozens to hundreds of attributes. We use&#xd;
kernel-based methods to define these measures of similarity. Kernels are general&#xd;
functions that can be used to formulate similarity comparisons.&#xd;
&#xd;
The overall goal of this thesis is to develop effective and efficient computational&#xd;
methods that are reliant on transparent mathematical descriptors of molecules with&#xd;
applications to affinity prediction, detection of multiple binding modes, and generation&#xd;
of new drug leads. While in this thesis we derive computational strategies for&#xd;
the discovery of new drug leads, our approach differs from the traditional ligandbased&#xd;
approach. We have developed novel procedures to calculate inverse mappings&#xd;
and subsequently recover the structure of a potential drug lead. The contributions&#xd;
of this thesis are the following:&#xd;
&#xd;
1. We propose a vector space model molecular descriptor (VSMMD) based on&#xd;
a vector space model that is suitable for kernel studies in QSAR modeling.&#xd;
Our experiments have provided convincing comparative empirical evidence&#xd;
that our descriptor formulation in conjunction with kernel based regression&#xd;
algorithms can provide sufficient discrimination to predict various biological&#xd;
activities of a molecule with reasonable accuracy.&#xd;
&#xd;
2. We present a new component selection algorithm KACS (Kernel Alignment&#xd;
Component Selection) based on kernel alignment for a QSAR study. Kernel&#xd;
alignment has been developed as a measure of similarity between two kernel&#xd;
functions. In our algorithm, we refine kernel alignment as an evaluation tool,&#xd;
using recursive component elimination to eventually select the most important&#xd;
components for classification. We have demonstrated empirically and proven&#xd;
theoretically that our algorithm works well for finding the most important&#xd;
components in different QSAR data sets.&#xd;
&#xd;
3. We extend the VSMMD in conjunction with a kernel based clustering algorithm&#xd;
to the prediction of multiple binding modes, a challenging area of&#xd;
research that has been previously studied by means of time consuming docking&#xd;
simulations. The results reported in this study provide strong empirical&#xd;
evidence that our strategy has enough resolving power to distinguish multiple&#xd;
binding modes through the use of a standard k-means algorithm.&#xd;
&#xd;
4. We develop a set of reverse engineering strategies for QSAR modeling based&#xd;
on our VSMMD. These strategies include:&#xd;
&#xd;
(a) The use of a kernel feature space algorithm to design or modify descriptor&#xd;
image points in a feature space.&#xd;
(b) The deployment of a pre-image algorithm to map the newly defined&#xd;
descriptor image points in the feature space back to the input space of&#xd;
the descriptors.&#xd;
(c) The design of a probabilistic strategy to convert new descriptors to meaningful&#xd;
chemical graph templates.&#xd;
&#xd;
The most important aspect of these contributions is the presentation of strategies that actually generate the structure of a new drug candidate. While the training&#xd;
set is still used to generate a new image point in the feature space, the reverse engineering&#xd;
strategies just described allows us to develop a new drug candidate that is&#xd;
independent of issues related to probability distribution constraints placed on test&#xd;
set molecules.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en">en</dim:field>
   <dim:field mdschema="dc" element="publisher" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">drug design</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">kernel methods</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">QSAR</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">inverse-QSAR</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en">feature selection</dim:field>
   <dim:field mdschema="dc" element="subject" qualifier="program" lang="en">Computer Science</dim:field>
   <dim:field mdschema="dc" element="title" lang="en">Kernel Methods in Computer-Aided Constructive Drug Design</dim:field>
   <dim:field mdschema="dc" element="type" lang="en">Doctoral Thesis</dim:field>
   <dim:field mdschema="dc" element="pending" lang="en">false</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="department" lang="en">School of Computer Science</dim:field>
   <dim:field mdschema="uws-etd" element="degree" lang="en">Doctor of Philosophy</dim:field>
   <dim:field mdschema="uws" element="typeOfResource" lang="en">Text</dim:field>
   <dim:field mdschema="uws" element="peerReviewStatus" lang="en">Unreviewed</dim:field>
   <dim:field mdschema="uws" element="scholarLevel" lang="en">Graduate</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>