Download the full-sized PDF of Pattern Recognition of Time-dependent Cellular Response of Chemicals Based on Profile Shape SimilarityDownload the full-sized PDF



Permanent link (DOI):


Export to: EndNote  |  Zotero  |  Mendeley


This file is in the following communities:

Graduate Studies and Research, Faculty of


This file is in the following collections:

Theses and Dissertations

Pattern Recognition of Time-dependent Cellular Response of Chemicals Based on Profile Shape Similarity Open Access


Other title
Hierarchical Classification
Functional Data Analysis
Time-dependent Cellular Response Profiles
Principal Component Analysis
Feature Extraction
Type of item
Degree grantor
University of Alberta
Author or creator
Xi, Zhankun
Supervisor and department
Huang, Biao (Chemical and Materials Engineering)
Examining committee member and department
Shah, Sirish (Chemical and Materials Engineering)
Huang, Biao (Chemical and Materials Engineering)
Unsworth, Larry (Chemical and Materials Engineering)
Department of Chemical and Materials Engineering
Process Control
Date accepted
Graduation date
Master of Science
Degree level
As a potential approach to interpret Mode of Action (MoA), the shape of cellular response profiles associated with chemicals has been a key consideration. In this thesis, statistical pattern recognition methods using multiconcentration time-dependent cellular response profiles (TCRPs) are explored. Cell Index (CI) values are used to reflect changes in cell population, morphology and the degree of cell attachment and are recorded dynamically as multiple time series data via the xCELLigence real-time cell analysis high-throughput (RTCA HT) system. Data processing techniques such as denoising and TCRP selection are applied to generate appropriate data for further analysis. These techniques also screen out the TCRPs which are not responsive enough and retain only those TCRPs which are the representative of action of the chemical compound based on the given cell population. Therefore, all the designed approaches are aimed at pattern recognition of TCRPs and classifying chemicals represented by different numbers of TCRPs. The results of these data-driven classification approaches show reasonable discrimination of chemicals based on profile shape similarity, which provides a potential guideline to determine Mode of Action of chemicals.
Permission is hereby granted to the University of Alberta Libraries to reproduce single copies of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. Where the thesis is converted to, or otherwise made available in digital form, the University of Alberta will advise potential users of the thesis of these terms. The author reserves all other publication and other rights in association with the copyright in the thesis and, except as herein before provided, neither the thesis nor any substantial portion thereof may be printed or otherwise reproduced in any material form whatsoever without the author's prior written permission.
Citation for previous publication

File Details

Date Uploaded
Date Modified
Audit Status
Audits have not yet been run on this file.
File format: pdf (Portable Document Format)
Mime type: application/pdf
File size: 1342643
Last modified: 2015:10:12 17:20:38-06:00
Filename: Xi_Zhankun_Spring 2014.pdf
Original checksum: 7c5d6e4eac01cb01516ee237c462c7bb
Well formed: true
Valid: true
Page count: 135
Activity of users you follow
User Activity Date