|
Activity Number:
|
487
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 10, 2006 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Committee on Women in Statistics
|
| Abstract - #305116 |
|
Title:
|
Joint Statistical Models for Genome-Wide Tiling Array and Sequence Data
|
|
Author(s):
|
Sunduz Keles*+ and Heejung Shim
|
|
Companies:
|
University of Wisconsin-Madison and University of Wisconsin-Madison
|
|
Address:
|
Departments of Statistics and Biostatistics, Madison, WI, 53710,
|
|
Keywords:
|
genome-wide tiling array ; transcription factor ; mixture regression models ; motif discovery
|
|
Abstract:
|
Tiling arrays that interrogate the genome in a systematic, unbiased fashion are becoming instrumental for the genome-wide identification and characterization of functional elements. We propose a class of statistical models to analyze data from these arrays in combination with sequence data to effectively identify transcription factors binding sites. These joint models carefully address the cases where tiling array data show enrichment in regions that do not correspond to transcription factor binding sites. We discuss inference procedures for such models and illustrate their utility with several real data examples.
|
