Speaker: Nasimeh Asgarian
M.Sc.
Computer Sciences
University of Alberta, Canada

Title: Machine Learning for Medical Informatics

Local Host: Mohsen Taghaddosi

Time: Tuesday, December 30th, 2008, 11:45am-12:30 pm
Kharazmi Hall, Department of Computer Engineering
Sharif University of Technology, Tehran

Abstract:

A DNA-microarray measures the gene expression levels of tens of thousands of genes under different experimental conditions (samples). These values describe the unique properties to each cell type. The samples may have come from different time points, different organs, diseased or healthy tissues, or different individuals. This technology benefits biological research greatly in understanding of biological processes. It also has very important applications in pharmaceutical and clinical research.
Our goal is to learn a microarray classifier that can distinguish members of various classes, based on their expression levels. Unfortunately, the large number of genes and the small number of samples make analyzing microarray data very challenging. We propose a method for sample classification by first reducing the dimensionality of the data matrix, then using machine learning algorithms. We have microarray data for breast cancer patients. Despite surgery and/or chemotherapy and/or hormonal
therapy and/or regional radiotherapy, approximately 30% of patients will eventually have an early recurrence. The biological reasons for recurrence/resistance to treatment are poorly understood. Our goal is to compare gene expression profiles in breast tumors collected prior to treatment from patients that have an early relapse and patients who have not relapsed and predict which patients will have an early relapse. If we can predict which patients will have early recurrence, then alternative drugs can be used to treat those that have higher probability of recurrence.