MSc Thesis Defense Announcement of Ann Reba Thomas Alexander:"A Network-Based Approach for Computational Drug Repurposing on Cancer Data "

Thursday, June 17, 2021 - 10:00 to 12:00


The School of Computer Science is pleased to present… 

MSc Thesis Defense by: Ann Reba Thomas Alexander 

Date: Thursday June 17, 2021 
Time:  10:00am-12:00pm 
Passcode:  If interested in attending this event, contact the graduate secretary at


Breast Cancer is the leading cause of cancer-related death which makes up a 25 % of all new cancer diagnoses globally to the American Cancer Society (ACS). Developing an effective drug can be a time-consuming and expensive crucible. Drug Repurposing is an effective method that takes away both time and cost compared to traditional drug discovery. It is the process of determining whether a drug currently approved for a disease, say disease A, can be indicated for another disease, say disease B. Network-based machine learning methods are used for predicting a given drug for A that can be used for B. It aims at finding new indications for already existing drugs and therefore increases the available therapeutic choices at a fraction of the cost of new drug development. In previous studies, the network-based method is a tremendous platform for drug repositioning as there exist more biological networks that can be used to model the interaction between the biological concepts. In this thesis, we are interested in finding the best drugs that can be repurposed for the disease, Breast Cancer using the existing Protein-protein interaction (PPI) networks. For each gene in the drug dataset, the p-value based on the z-score was calculated. The proposed method is based on the idea that if a perturbation gene expression profile inversely correlates with the disease gene expression profile, the drug may have a curing effect on the disease. Similarly, Perturbation gene expression profile correlates with the disease gene expression profile, the drug may have an adverse effect on the disease. Six samples of stroma surrounding invasive breast primary tumors and six matched samples of the normal stroma are extracted from the public functional genomics data repository, Gene Expression Omnibus. The perturbation gene expression data corresponding to the MCF7 cell line was extracted from the National Institute of Health’s (NIH), Library of Integrated Network-Based Cellular Signatures (LINCS) dataset. Using Louvain Clustering Algorithm, we detect community Networks and obtain Disease-Drug Data Network. Finally, we propose Edmond's matching algorithm to obtain the best-suited drug that could be repurposed for breast cancer disease. 
Keywords: Drug Repurposing, Protein-protein interaction (PPI) networks, perturbation gene expression, Network-based approach, Hungarian Algorithm, Reporting Odds Ratio

MSc Thesis Committee:  

Internal Reader: Dr. Dima Alhadidi  
External Reader: Dr. Myron Hlynka  
Advisor: Dr. Alioune Ngom 
Chair:     Dr. Jianguo Lu 

 MSc Thesis Defense Announcement    Vector Institute in Artificial Intelligence, artificial intelligence approved topic logo


5113 Lambton Tower 401 Sunset Ave. Windsor ON, N9B 3P4 (519) 253-3000 Ext. 3716 (working remotely)