UWindsor Together: Student Mental Health and Remote Learning Services

MSc Thesis Proposal of Narinder Pal Singh:"Structuring gene expression data for classification of disease subtypes in Deep Neural Networks "

Monday, April 19, 2021 - 12:30 to 14:30

SCHOOL OF COMPUTER SCIENCE

The School of Computer Science is pleased to present…

MSc Thesis Proposal by: Narinder Pal Singh 

 
Date: Monday April 19th 2021 
Time:  12:30 PM to 02:30 PM 
Passcode:      If interested in attending this event, contact the graduate secretary at csgradinfo@uwindsor.ca
 

Abstract:  

 
The introduction of genetic testing has profoundly enhanced the prospects of early detection of diseases and techniques to suggest precision medicines. The subtyping of critical diseases has proven to be an essential part of the development of individualized therapies and has led to deeper insights into the heterogeneity of the disease. Studies suggest that variants in particular genes have significant effects on certain types of immune system cells and are also involved in the risk of certain critical illnesses like cancer. By analyzing the genetic sequence of a patient, disease types and subtypes can be predicted. Recent research work has shown that the CNN's prediction quality within this context using gene intensity features could be improved when the input is structured into 2D images via transformations like kPCA, t-SNE, etc., to express certain types of relationships among the intensity features. Considering the increased computational complexity in transforming 1D data to images, we propose to induce similar relationships among the gene intensity features by way of 1D ordering to preserve the simplicity inherent to original gene data. The heterogeneity between the gene data and the clinical data is handled by feeding the latter directly into the fully connected layers. We will get more insight into the impact of different structuring techniques on the prediction quality in terms of CNN, RNN, and their combination. We will be applying our approach to The Cancer Genome Atlas (TCGA) dataset for cancer subtypes and compare our method with the state-of-the-art. 
 
Keywords: Convolutional neural networks, cancer subtype classification, HGNC data, RNA Seq, precision medicine 
 

MSc Thesis Committee:  

Internal Reader: Dr. Ahmad Biniaz            
External Reader: Dr. Balakumar Balasingan           
Advisor: Dr. Jessica Chen 
 

MSc Thesis Proposal Announcement     Vector Insitute approved artificial intelligence topic logo

 

5113 Lambton Tower 401 Sunset Ave. Windsor ON, N9B 3P4 (519) 253-3000 Ext. 3716 csgradinfo@uwindsor.ca