Date of Defense

12-4-2003

Department

Computer Science

First Advisor

Dr. Ajay Gupta

Second Advisor

Dr. Mark Kerstetter

Third Advisor

Dr. John Geiser

Abstract

Bioinformatics is a new and exciting application of computer science which seeks to collect, store, manage and represent the vast amounts of molecular biological data that continues to be discovered everyday, in the post-genomic era. Two key technologies that help foster research in this growing field are genome sequencing technologies and microarrays. A microarray is typically a slide that can hold a great deal of genetic information. However, this information becomes useful only if analyzed in a sensible way so as to transform the genetic data into biological knowledge. This thesis seeks to provide an overview of the common algorithms and methods employed in the design and creation of software that seek to efficiently analyze microarray data; including those for unsupervised analysis or clustering (Hierarchical Clustering, K-means clustering, Self Organizing Maps, Principal Component Analysis), and those for supervised analysis or classification (Support Vector Machines, Artificial Neural Networks).

Access Setting

Honors Thesis-Campus Only

Download

Share

COinS