|
Activity Number:
|
250
|
|
Type:
|
Invited
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
IMS
|
| Abstract - #302992 |
|
Title:
|
Prediction of Patient Outcomes Based on High-Throughput Genetic Data Using Supervised Principal Components
|
|
Author(s):
|
Eric Bair*+
|
|
Companies:
|
The University of North Carolina at Chapel Hill
|
|
Address:
|
School of Dentistry, Chapel Hill, NC, Chapel Hil,
|
|
Keywords:
|
microarray ; principal components ; high-dimensional ; genetic ; genome-wide ; association
|
|
Abstract:
|
Supervised principal components is a useful method for predicting continuous response variables (particularly patient survival) based on DNA microarray data. It has been successfully applied to several microarray data sets. Additionally, there is preliminary data indicating that it can help identify significant features in high-dimensional data sets and solve classification problems, particularly when some of the response variables are mislabeled. It can also be applied to problems where the predictor variables are discrete, such as data collected from genome-wide association studies. These types of data sets are very common in biological experiments, and the ability to analyze these data sets has the potential to help us learn more about many complex diseases.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2009 program |
