Project Overview

Gene Selection in Classification of Cancer Patients

Faculty Sponsor

Ahmet Ay (aay@colgate.edu)

Department(s)

Mathematics
Biology
Computer Science

Abstract

Genome wide gene expression levels are used for classification of cancer states (e.g. cancer patient vs. normal patient). Due to the large number of genes in the gene expression data sets (20,000+ genes), the genes are statistically ranked and only a small number of these genes (~100) are selected for developing a classifier. Although, often the classifiers developed with these statistically highly ranked genes provide high accuracy, biological relevance of these genes to cancer is not clear. In this study, we will compare the accuracy of the feature selection methods in selecting the right set of cancer related genes.

Student Qualifications

Molecular Biology literature search skills. Students who have taken upper level molecular biology courses will be preferred. OR Programming skills from COSC 102 (Introduction to Computing II). Having taken Operating Systems (COSC 301) is preferred.

Number of Student Researchers

2 students

Project Length

10 weeks


Applications open on 01/15/2017 and close on 02/07/2017


<< Back to List





If you have questions, please contact Karyn Belanger (kgbelanger@colgate.edu).