Advancing Gene Expression Microarray Analysis: Assessing and Enhancing the Linear Combination Test Through Integration with Machine Learning Tools

Understanding which genes are involved in diseases is incredibly important because it helps us develop better treatments. By identifying these genes, scientists can better understand how diseases operate in our bodies and create more effective treatments. This also allows for the creation of personalized treatments based on a person’s unique genes, increasing their chances of recovery. However, finding these genes is a difficult task as there are thousands of genes in the human body and vast amounts of genetic data to sift through. This project aims to enhance a method called the Linear Combination Test (LCT) and use machine learning tools to optimize further its ability to identify disease-related genes, such as those responsible for COVID-19 and cancer. In the second step of this project, the improved LCT will be tested on real-world data to gauge its effectiveness. Additionally, user-friendly software tools will be designed to make it simple for other scientists to use. Our ultimate goal is to help find cures and improve the lives of those who suffer from diseases.

Faculty Supervisor:

Irina Dinu

Student:

Partner:

INSA Lyon

Discipline:

Computer science

Sector:

Health and Related Sciences & Technology

University:

University of Alberta

Program: