The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Abstract Details
|
Activity Number:
|
600
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 4, 2011 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #300341 |
|
Title:
|
A Stochastic Universal Cancer Classifier
|
|
Author(s):
|
Jeff Leek*+ and Hector Corrada Bravo and Vasyl Pihur and Matthew Nicholson McCall and Rafael Irizarry
|
|
Companies:
|
The Johns Hopkins University and University of Maryland and The Johns Hopkins University and University of Rochester Medical Center and The Johns Hopkins University
|
|
Address:
|
School of Public Health, Baltimore, MD, 21401, United States
|
|
Keywords:
|
genomics ;
prediction ;
cancer ;
batch effects ;
high-throughput
|
|
Abstract:
|
I will present a simple but highly accurate cancer prediction method based on genes that exhibit increased stochastic variability of expression across multiple tumor types compared to normal tissues. The predictor is based on selecting features that show increased variability in cancer and a simple outlier counting classifier. This method achieves high predictive accuracy for solid tumors, even when predicting cancer types not used to generate the prediction rule. I will also discuss practical issues involved with buidling predictors across multiple data sets including feature selection, normalization, and batch effects.
|
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 2011 program
|
2011 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.